{"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/load-model-answers","entry":"load_model_answers","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":5,"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":2,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":0},"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":"2410.11623","paper":"/paper/videgothink-assessing-egocentric-video","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adacheng/egothink","path":"common.py","file_url":"https://github.com/adacheng/egothink/blob/HEAD/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"270d3eb4371b0d85","mcp_get_code":{"code_sha256":"270d3eb4371b0d85"}},{"arxiv_id":"2409.15254","paper":"/paper/archon-an-architecture-search-framework-for","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","date":"2024-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scalingintelligence/archon","path":"src/archon/benchmarks/arena_hard_auto/arena_hard_auto_utils.py","file_url":"https://github.com/scalingintelligence/archon/blob/HEAD/src/archon/benchmarks/arena_hard_auto/arena_hard_auto_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"28bbb1e46eb5f17c","mcp_get_code":{"code_sha256":"28bbb1e46eb5f17c"}},{"arxiv_id":"2309.16240","paper":"/paper/beyond-reverse-kl-generalizing-direct","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alecwangcq/f-divergence-dpo","path":"mt_bench/common.py","file_url":"https://github.com/alecwangcq/f-divergence-dpo/blob/HEAD/mt_bench/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"270d3eb4371b0d85","mcp_get_code":{"code_sha256":"270d3eb4371b0d85"}},{"arxiv_id":"2025.findings-acl.979","paper":null,"title":"arXiv:2025.findings-acl.979","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Mrshenshen/FRUIT","path":"common.py","file_url":"https://github.com/Mrshenshen/FRUIT/blob/HEAD/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"270d3eb4371b0d85","mcp_get_code":{"code_sha256":"270d3eb4371b0d85"}},{"arxiv_id":"2025.acl-long.851","paper":null,"title":"arXiv:2025.acl-long.851","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"uw-nsl/SafeDecoding","path":"mt_bench/common.py","file_url":"https://github.com/uw-nsl/SafeDecoding/blob/HEAD/mt_bench/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"270d3eb4371b0d85","mcp_get_code":{"code_sha256":"270d3eb4371b0d85"}}]}