{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/score-string-similarity","entry":"score_string_similarity","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":2,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":1},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2209.14610","paper":"/paper/dynamic-prompt-learning-via-policy-gradient","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","date":"2022-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lupantech/promptpg","path":"run_gpt3_rl/learn_policy.py","file_url":"https://github.com/lupantech/promptpg/blob/HEAD/run_gpt3_rl/learn_policy.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc627ffb4d816873","mcp_get_code":{"code_sha256":"cc627ffb4d816873"}},{"arxiv_id":"2205.09224","paper":"/paper/entailment-tree-explanations-via-iterative","title":"Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner","date":"2022-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-research/irgr","path":"src/entailment_bank/utils/eval_utils.py","file_url":"https://github.com/amazon-research/irgr/blob/HEAD/src/entailment_bank/utils/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"00139853f0c3a89e","mcp_get_code":{"code_sha256":"00139853f0c3a89e"}},{"arxiv_id":"2203.07540","paper":"/paper/scienceworld-is-your-agent-smarter-than-a-5th","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","date":"2022-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/macaw","path":"macaw/eval_utils.py","file_url":"https://github.com/allenai/macaw/blob/HEAD/macaw/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"00139853f0c3a89e","mcp_get_code":{"code_sha256":"00139853f0c3a89e"}},{"arxiv_id":"2202.12359","paper":"/paper/unifiedqa-v2-stronger-generalization-via","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","date":"2022-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/unifiedqa","path":"evaluation/evaluate_v2.py","file_url":"https://github.com/allenai/unifiedqa/blob/HEAD/evaluation/evaluate_v2.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1494041ab87b9a6b","mcp_get_code":{"code_sha256":"1494041ab87b9a6b"}},{"arxiv_id":"2104.08661","paper":"/paper/explaining-answers-with-entailment-trees","title":"Explaining Answers with Entailment Trees","date":"2021-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/entailment_bank","path":"utils/eval_utils.py","file_url":"https://github.com/allenai/entailment_bank/blob/HEAD/utils/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"00139853f0c3a89e","mcp_get_code":{"code_sha256":"00139853f0c3a89e"}}]}