SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.01062 · 2026

SPoRC-VIST: A Benchmark for Evaluating Generative Natural Narrative in Vision-Language Models

Yunlin Zeng

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 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 0 have no contract verdict; 7 failures of our instrument; 8 no recorded run), measured 2026-11-22; 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/2601.01062.json · badge: /api/ran/2601.01062.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
Yunlin-Zeng/visual-podcast-VLM canonical (classifier label)
classifier basis: census
8 ran · 8 no recorded run
FunctionStatusWhere it lives
clean_prompt Ran
ran; our contract draft was wrong, not the code
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/2025-11-24_generate_images.py
pointer only (licence: NOASSERTION) · get_code("1627a59e4de4ab71")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

compute_distinct_n Ran
ran, honoured the contract we drafted
Yunlin-Zeng/visual-podcast-VLM/evaluation_50_samples/evaluate_metrics.py
pointer only (licence: NOASSERTION) · get_code("3b1e4fe1c35a715d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

load_dataset Ran
ran; our contract draft was wrong, not the code
Yunlin-Zeng/visual-podcast-VLM/scripts_235B/precompute_vision_embeddings_235b.py
pointer only (licence: NOASSERTION) · get_code("81e9e093f2fff831")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

load_transcript Ran
ran; our contract draft was wrong, not the code
Yunlin-Zeng/visual-podcast-VLM/evaluation_50_samples/evaluate_metrics.py
pointer only (licence: NOASSERTION) · get_code("6b6ce8f17c73e260")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

normalize_text Ran
ran; our contract draft was wrong, not the code
Yunlin-Zeng/visual-podcast-VLM/evaluation_50_samples/evaluate_metrics.py
pointer only (licence: NOASSERTION) · get_code("017711da98a034fb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

process_podcast Ran
ran; our contract draft was wrong, not the code
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/extract_excerpts.py
pointer only (licence: NOASSERTION) · get_code("cbba8fdf5f64ec33")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

resolve_image_paths Ran
ran; our contract draft was wrong, not the code
Yunlin-Zeng/visual-podcast-VLM/scripts_235B/precompute_vision_embeddings_235b.py
pointer only (licence: NOASSERTION) · get_code("1ce170dbdbf5bfbe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

validate_excerpt Ran
ran; our contract draft was wrong, not the code
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/extract_excerpts_2025-11-24.py
pointer only (licence: NOASSERTION) · get_code("a12e9590dd99e847")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

call_claude Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/extract_excerpts.py
pointer only (licence: NOASSERTION) · get_code("4ddc98171ac805c1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

call_claude Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/extract_excerpts_2025-11-24.py
pointer only (licence: NOASSERTION) · get_code("fd6d9ed42ff95570")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

generate_image Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/2025-11-24_generate_images.py
pointer only (licence: NOASSERTION) · get_code("57addbe111d83710")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

load_model_and_processor Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_235B/precompute_vision_embeddings_235b.py
pointer only (licence: NOASSERTION) · get_code("dc782ec4f7c2a5d2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

load_training_data Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_235B/finetune_235B.py
pointer only (licence: NOASSERTION) · get_code("3e00dc55066dfff6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

prepare_dataset Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_235B/finetune_235B.py
pointer only (licence: NOASSERTION) · get_code("a5c5ad9dfba730d2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

process_podcast Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/extract_excerpts_2025-11-24.py
pointer only (licence: NOASSERTION) · get_code("815a04180fcfa667")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

process_scene Not yet run
unverified (harvested, no recorded run)
Yunlin-Zeng/visual-podcast-VLM/scripts_bedrock/2025-11-24_generate_images.py
pointer only (licence: NOASSERTION) · get_code("3dc8411d11ee2742")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Yunlin-Zeng/visual-podcast-VLM (NOASSERTION). 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.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 16 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.

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

Vision-Language Models (VLMs) have achieved remarkable success in descriptive tasks such as image captioning and visual question answering (VQA). However, their ability to generate engaging, long-form narratives-specifically multi-speaker podcast dialogues-remains under-explored and difficult to evaluate. Standard metrics like BLEU and ROUGE fail to capture the nuances of conversational naturalness, personality, and narrative flow, often rewarding safe, repetitive outputs over engaging storytelling. In this work, we present a novel pipeline for end-to-end visual podcast generation, and fine-tune a Qwen3-VL-32B model on a curated dataset of 4,000 image-dialogue pairs. Crucially, we use a synthetic-to-real training strategy: we train on high-quality podcast dialogues from the Structured Podcast Research Corpus (SPoRC) paired with synthetically generated imagery, and evaluate on real-world photo sequences from the Visual Storytelling Dataset (VIST). This rigorous setup tests the model's ability to generalize from synthetic training data to real-world visual domains. We propose a comprehensive evaluation framework that moves beyond textual overlap, and use AI-as-a-judge (Gemini 3 Pro, Claude Opus 4.5, GPT 5.2) and novel style metrics (average turn length, speaker switch rate) to assess quality. Our experiments demonstrate that our fine-tuned 32B model significantly outperforms a 235B base model in conversational naturalness (>80% win rate) and narrative depth (+50% turn length), while maintaining identical visual grounding capabilities (CLIPScore: 20.39).

For agents

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

get_harvested_code_for_paper("2601.01062")
get_code_for_paper("2601.01062")
have("2601.01062")

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

curl https://syntology.ai/api/ran/2601.01062.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.01062.svg)](https://syntology.ai/paper/2601.01062)

Connect an agent — have() is free.