We lifted 14 functions out of this paper's own repositories and ran 11 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| xingjian-zhang/massw | canonical | 11 of 14 |
| Function | Status | Where it lives |
|---|---|---|
| add_messages_and_run | Ran | xingjian-zhang/massw/massw/models/gpt_azure.py code served (permissive licence) · get_code("ad034ce77d764f7d") |
| best_demos | Ran | xingjian-zhang/massw/factscore/atomic_facts.py code served (permissive licence) · get_code("510528f4db1006bc") |
| flatten_metrics | Ran | xingjian-zhang/massw/massw/metrics.py code served (permissive licence) · get_code("65b281d7162641cc") |
| handle_mixtral_model | Ran | xingjian-zhang/massw/massw/models/mixtral_azure.py code served (permissive licence) · get_code("387f336b1c4b3c25") |
| is_invalid_paragraph_ppl | Ran | xingjian-zhang/massw/factscore/abstain_detection.py code served (permissive licence) · get_code("8eb846a8e76a79b8") |
| is_invalid_ppl | Ran | xingjian-zhang/massw/factscore/abstain_detection.py code served (permissive licence) · get_code("672bd38d830be48d") |
| normalize_answer | Ran | xingjian-zhang/massw/factscore/atomic_facts.py code served (permissive licence) · get_code("6a96435eba311b08") |
| prompts_to_raw_output | Ran | xingjian-zhang/massw/massw/models/mixtral_azure.py code served (permissive licence) · get_code("8732e3cee65072f2") |
| raw_output_to_dict | Ran | xingjian-zhang/massw/massw/models/mixtral_azure.py code served (permissive licence) · get_code("8cdcb69190dee2a5") |
| remove_citation | Ran | xingjian-zhang/massw/factscore/abstain_detection.py code served (permissive licence) · get_code("3635046105ae0fce") |
| text_to_sentences | Ran | xingjian-zhang/massw/factscore/atomic_facts.py code served (permissive licence) · get_code("13867f872a481bd3") |
| prompts_to_raw_output | Not yet run | xingjian-zhang/massw/massw/models/gpt_azure.py code served (permissive licence) · get_code("add7cc2c75fac6a5") |
| raw_output_to_dict | Not yet run | xingjian-zhang/massw/massw/models/gpt_azure.py code served (permissive licence) · get_code("c804619a1c095b59") |
| recover_instruct_llama | Not yet run | xingjian-zhang/massw/factscore/download_data.py code served (permissive licence) · get_code("02c83d89394be1c7") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Scientific innovation relies on detailed workflows, which include critical steps such as analyzing literature, generating ideas, validating these ideas, interpreting results, and inspiring follow-up research. However, scientific publications that document these workflows are extensive and unstructured. This makes it difficult for both human researchers and AI systems to effectively navigate and explore the space of scientific innovation. To address this issue, we introduce MASSW, a comprehensive text dataset on Multi-Aspect Summarization of Scientific Workflows. MASSW includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. Using Large Language Models (LLMs), we automatically extract five core aspects from these publications -- context, key idea, method, outcome, and projected impact -- which correspond to five key steps in the research workflow. These structured summaries facilitate a variety of downstream tasks and analyses. The quality of the LLM-extracted summaries is validated by comparing them with human annotations. We demonstrate the utility of MASSW through multiple novel machine-learning tasks that can be benchmarked using this new dataset, which make various types of predictions and recommendations along the scientific workflow. MASSW holds significant potential for researchers to create and benchmark new AI methods for optimizing scientific workflows and fostering scientific innovation in the field. Our dataset is openly available at \url{https://github.com/xingjian-zhang/massw}.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.06357")
get_code_for_paper("2406.06357")
have("2406.06357")
Connect an agent — have() is free.