SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.09781 · 2018

Self-Attentive Sequential Recommendation

arXiv · PDF · Open in the Atlas

Code that ran

12 of 20 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 2 failures of our instrument; 8 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1808.09781.json · badge: /api/ran/1808.09781.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
otto-de/recsys-dataset community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
mangushev/mfgan community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
kang205/SASRec community (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
paddorch/SASRec.paddle community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
pmixer/SASRec.pytorch community (classifier label)
classifier basis not recorded on the link
0 ran · 2 no recorded run
FunctionStatusWhere it lives
dropout Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mangushev/mfgan/model.py
pointer only (licence: MIT); the stored copy get_code serves, from huawei-noah/Pretrained-Language-Model, is pointer only (licence: NONE) · get_code("873e08c3f15eb1e4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from huawei-noah/Pretrained-Language-Model, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_session Ran
ran on a synthesized input
otto-de/recsys-dataset/src/evaluate.py
code served (permissive licence) · get_code("fcc7874cdb3add47")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T21:51:12Z. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
torch.manual_seed(0)

# Construct valid arguments for evaluate_session
labels = {
    'clicks': [101],
    'carts': [201, 202, 203],
    'orders': [301, 302]
}

prediction = {
    'clicks': [101, 102, 103, 104, 105],
    'carts': [201, 204, 205, 206, 207],
    'orders': [301, 308, 309, 310, 311]
}

k = 3

ARGS = {
    'labels': labels,
    'prediction': prediction,
    'k': k
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
example Ran
ran on a synthesized input
mangushev/mfgan/prepare_data.py
code served (permissive licence) · get_code("51a55750bad649a9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Example. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy as np

ARGS = {
    'input': [1, 2, 3, 4],
    'factors': np.array([[2, 3], [4, 5]]),
    'products': np.array([[6, 15], [20, 25]]),
    'is_real_example': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Example — a Example output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Example output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_max_ts Ran
ran on a synthesized input
otto-de/recsys-dataset/src/testset.py
code served (permissive licence) · get_code("eab2ac5ffc1c2836")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T21:51:12Z. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import json
import tempfile
from pathlib import Path

# Create a temporary JSONL file with session data
temp_dir = tempfile.mkdtemp()
sessions_path = Path(temp_dir) / "sessions.jsonl"

# Write sample session data to the file
sessions_data = [
    {
        "session_id": "1",
        "events": [
            {"ts": 100},
            {"ts": 200},
            {"ts": 350}
        ]
    },
    {
        "session_id": "2",
        "events": [
            {"ts": 50},
            {"ts": 150},
            {"ts": 400}
        ]
    },
    {
        "session_id": "3",
        "events": [
            {"ts": 10},
            {"ts": 500}
        ]
    }
]

with open(sessions_path, 'w') as f:
    for session in sessions_data:
        f.write(json.dumps(session) + '\n')

ARGS = {
    "sessions_path": sessions_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ground_truth Ran
ran on a synthesized input
otto-de/recsys-dataset/src/labels.py
code served (permissive licence) · get_code("c573805ca4f55418")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T21:51:12Z. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Construct a valid argument for the ground_truth function
# The function expects a list of dicts with 'type' and 'aid' keys

events = [
    {'type': 'clicks', 'aid': 101},
    {'type': 'carts', 'aid': 102},
    {'type': 'orders', 'aid': 103},
    {'type': 'clicks', 'aid': 104},
]

ARGS = {
    'events': events
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
positional_encoding Ran
ran on a synthesized input
kang205/SASRec/modules.py
code served (permissive licence) · get_code("9567ab1b29ad4797")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 2, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T21:51:12Z. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy as np

# Analyzing the function:
# - dim: used in range(dim) and np.power(10000, 2 * i / dim) - needs to be int
# - sentence_length: used in range(sentence_length) - needs to be int
# - dtype: passed to tf.convert_to_tensor - defaults to tf.float32

ARGS = {
    "dim": 4,
    "sentence_length": 2,
    "dtype": tf.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
prepare_labels Ran
ran on a synthesized input
otto-de/recsys-dataset/src/evaluate.py
code served (permissive licence) · get_code("89eb96b11b86a9c2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T21:51:12Z. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import json

# Construct valid arguments for prepare_labels function
# The function expects a list of strings, where each string is a JSON object
# with 'session' and 'labels' keys

label_1 = json.dumps({
    'session': 'session_001',
    'labels': {
        'clicks': 5,
        'carts': ['item_1', 'item_2'],
        'orders': ['item_3']
    }
})

label_2 = json.dumps({
    'session': 'session_002',
    'labels': {
        'clicks': 3,
        'carts': ['item_4', 'item_5', 'item_6'],
        'orders': ['item_7', 'item_8']
    }
})

label_3 = json.dumps({
    'session': 'session_003',
    'labels': {
        'clicks': None,
        'carts': [],
        'orders': []
    }
})

labels = [label_1, label_2, label_3]

ARGS = {
    'labels': labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
prepare_predictions Ran
ran on a synthesized input
otto-de/recsys-dataset/src/evaluate.py
code served (permissive licence) · get_code("62f28fd0561698f8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from beartype import beartype
from tqdm.auto import tqdm

@beartype
def prepare_predictions(predictions: list[str]):
    prepared_predictions = dict()
    for prediction in tqdm(predictions, desc='Preparing predictions'):
        sid_type, preds = prediction.strip().split(',')
        sid, event_type = sid_type.split('_')
        preds = [int(aid) for aid in preds.split(' ')] if preds != '' else []
        if not int(sid) in prepared_predictions:
            prepared_predictions[int(sid)] = dict()
        prepared_predictions[int(sid)][event_type] = preds
    return prepared_predictions

# Construct valid arguments for prepare_predictions
predictions_list = [
    "1_click,1 2 3",
    "1_view,4 5",
    "2_click,",
    "2_view,6 7 8 9",
    "3_click,10",
]

ARGS = {
    "predictions": predictions_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
random_neq Ran
ran, honoured the contract we drafted
kang205/SASRec/sampler.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from nancheng58/recmamba, is pointer only (licence: NONE) · get_code("13e1db5681123f3a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from nancheng58/recmamba, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reshape_to_matrix Ran
ran; our contract draft was wrong, not the code
mangushev/mfgan/model.py
pointer only (licence: MIT); the stored copy get_code serves, from huawei-noah/Pretrained-Language-Model, is pointer only (licence: NONE) · get_code("7b84f3e6a96584b4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from huawei-noah/Pretrained-Language-Model, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sample_function Ran
ran on a synthesized input
paddorch/SASRec.paddle/sasrec/data.py
code served (permissive licence) · get_code("f54d868213b75be7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned zip. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Set seed for reproducibility
np.random.seed(42)

# Build user_train: dict mapping user_id -> list of item interactions
# Each user needs at least 2 items (len > 1) for the while loop to pass
usernum = 5
itemnum = 10
maxlen = 4
batch_size = 2

user_train = {}
for user_id in range(1, usernum + 1):
    # Give each user a sequence of items (at least 2)
    user_train[user_id] = [np.random.randint(1, itemnum + 1) for _ in range(np.random.randint(3, 7))]

ARGS = {
    'user_train': user_train,
    'usernum': usernum,
    'itemnum': itemnum,
    'batch_size': batch_size,
    'maxlen': maxlen,
    'result_queue': None,
    'SEED': 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type zip — a zip output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a zip output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
trim_session Ran
ran on a synthesized input
otto-de/recsys-dataset/src/testset.py
code served (permissive licence) · get_code("77689c32893561dc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Construct a valid session dict with events
session = {
    'events': [
        {'ts': 5, 'type': 'click', 'data': 'event1'},
        {'ts': 15, 'type': 'scroll', 'data': 'event2'},
        {'ts': 25, 'type': 'hover', 'data': 'event3'},
        {'ts': 35, 'type': 'click', 'data': 'event4'},
    ]
}

max_ts = 20

ARGS = {
    'session': session,
    'max_ts': max_ts,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_index Not yet run
unverified (harvested, no recorded run)
pmixer/SASRec.pytorch/python/utils.py
code served (permissive licence) · get_code("8f34807990e04010")
How it ran

no invocation recorded.

data_partition Not yet run
unverified (harvested, no recorded run)
paddorch/SASRec.paddle/sasrec/utils.py
code served (permissive licence) · get_code("b69fecb2a2840c7b")
How it ran

no invocation recorded.

embedding Not yet run
unverified (harvested, no recorded run)
kang205/SASRec/modules.py
code served (permissive licence) · get_code("fdc971ebe26e3773")
How it ran

no invocation recorded.

get_assignment_map_from_checkpoint Not yet run
unverified (harvested, no recorded run)
mangushev/mfgan/training.py
pointer only (licence: MIT); the stored copy get_code serves, from toggle1995/RIS-DMMI, is pointer only (licence: NONE) · get_code("50958618b65e514e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from toggle1995/RIS-DMMI, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

normalize Not yet run
unverified (harvested, no recorded run)
kang205/SASRec/modules.py
code served (permissive licence) · get_code("2a23cef922cb4b79")
How it ran

no invocation recorded.

reshape_from_matrix Not yet run
unverified (harvested, no recorded run)
mangushev/mfgan/model.py
code served (permissive licence) · get_code("3370499aacadb239")
How it ran

no invocation recorded.

sample_function Not yet run
unverified (harvested, no recorded run)
kang205/SASRec/sampler.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ghdtjr/a-llmrec, is pointer only (licence: NONE) · get_code("ed413c5d2cc8afc9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ghdtjr/a-llmrec, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sample_function Not yet run
unverified (harvested, no recorded run)
pmixer/SASRec.pytorch/python/utils.py
code served (permissive licence) · get_code("d64812b980f1617e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 7 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 7 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_assignment_map_from_checkpoint 26 other papers
1 dated earlier, 25 later
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.04085 (2019-01)
Passage Re-ranking with BERT
and 23 more not named here
dropout 9 other papers
1 dated earlier, 8 later · 4 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2003.01950 (2020-03)
AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment
and 6 more not named here
reshape_from_matrix 8 other papers
1 dated earlier, 7 later · 2 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2003.01950 (2020-03)
AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment
and 5 more not named here
random_neq 7 other papers
7 later
2002.07962 (2020-02)
Inductive Representation Learning on Temporal Graphs
2204.06517 (2022-04)
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
2401.02913 (2024-01)
Plug-In Diffusion Model for Sequential Recommendation
and 4 more not named here
reshape_to_matrix 7 other papers
1 dated earlier, 6 later · 4 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2003.01950 (2020-03)
AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment
and 4 more not named here
normalize 4 other papers
1 dated earlier, 3 later
1706.03762 (2017-06)
Attention Is All You Need
1902.09362 (2019-02)
Session-based Social Recommendation via Dynamic Graph Attention Networks
2310.20487 (2023-10)
Large Language Model Can Interpret Latent Space of Sequential Recommender
and 1 more not named here
sample_function 1 other paper
1 later
2404.11343 (2024-04)
Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Sequential dynamics are a key feature of many modern recommender systems, which seek to capture the `context' of users' activities on the basis of actions they have performed recently. To capture such patterns, two approaches have proliferated: Markov Chains (MCs) and Recurrent Neural Networks (RNNs). Markov Chains assume that a user's next action can be predicted on the basis of just their last (or last few) actions, while RNNs in principle allow for longer-term semantics to be uncovered. Generally speaking, MC-based methods perform best in extremely sparse datasets, where model parsimony is critical, while RNNs perform better in denser datasets where higher model complexity is affordable. The goal of our work is to balance these two goals, by proposing a self-attention based sequential model (SASRec) that allows us to capture long-term semantics (like an RNN), but, using an attention mechanism, makes its predictions based on relatively few actions (like an MC). At each time step, SASRec seeks to identify which items are `relevant' from a user's action history, and use them to predict the next item. Extensive empirical studies show that our method outperforms various state-of-the-art sequential models (including MC/CNN/RNN-based approaches) on both sparse and dense datasets. Moreover, the model is an order of magnitude more efficient than comparable CNN/RNN-based models. Visualizations on attention weights also show how our model adaptively handles datasets with various density, and uncovers meaningful patterns in activity sequences.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1808.09781")
get_code_for_paper("1808.09781")
have("1808.09781")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1808.09781.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1808.09781.svg)](https://syntology.ai/paper/1808.09781)

Connect an agent — have() is free.