{"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/extract-json-from-text","entry":"extract_json_from_text","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":7,"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":8,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":6},"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":"2605.02815","paper":"/paper/arxiv-2605-02815","title":"FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"StringNLPLAB/FlexSQL","path":"src/planning.py","file_url":"https://github.com/StringNLPLAB/FlexSQL/blob/HEAD/src/planning.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d4d75181a4cb0cfb","mcp_get_code":{"code_sha256":"d4d75181a4cb0cfb"}},{"arxiv_id":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"data_synthesis/generate_qa.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/data_synthesis/generate_qa.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4a112a7b36bef292","mcp_get_code":{"code_sha256":"4a112a7b36bef292"}},{"arxiv_id":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"data_synthesis/generate_qa_eval.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/data_synthesis/generate_qa_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5dd1d503bf65c0c3","mcp_get_code":{"code_sha256":"5dd1d503bf65c0c3"}},{"arxiv_id":"2603.10303","paper":"/paper/arxiv-2603-10303","title":"Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas #","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"TimSchopf/RINoBench","path":"src/eval/llm_call.py","file_url":"https://github.com/TimSchopf/RINoBench/blob/HEAD/src/eval/llm_call.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b3bf762740f26d51","mcp_get_code":{"code_sha256":"b3bf762740f26d51"}},{"arxiv_id":"2603.08035","paper":"/paper/arxiv-2603-08035","title":"CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ldcan/CDRRM","path":"rubric_synthesis/rubric_generation.py","file_url":"https://github.com/ldcan/CDRRM/blob/HEAD/rubric_synthesis/rubric_generation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3658e51d3c3d4553","mcp_get_code":{"code_sha256":"3658e51d3c3d4553"}},{"arxiv_id":"2602.01539","paper":"/paper/arxiv-2602-01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BattleWen/MAGIC","path":"eval/pattern/src/classify_attacker_prompts.py","file_url":"https://github.com/BattleWen/MAGIC/blob/HEAD/eval/pattern/src/classify_attacker_prompts.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":"604ab67dbc79c543","mcp_get_code":{"code_sha256":"604ab67dbc79c543"}},{"arxiv_id":"2601.06966","paper":"/paper/arxiv-2601-06966","title":"RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"AvatarMemory/RealMemBench","path":"eval/compute_llm_metrics_for_realmem.py","file_url":"https://github.com/AvatarMemory/RealMemBench/blob/HEAD/eval/compute_llm_metrics_for_realmem.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":"b649490e72b4f988","mcp_get_code":{"code_sha256":"b649490e72b4f988"}},{"arxiv_id":"2510.17671","paper":"/paper/arxiv-2510-17671","title":"LILO: Bayesian Optimization with Natural Language Feedback","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"facebookresearch/lilo","path":"lilo/utils.py","file_url":"https://github.com/facebookresearch/lilo/blob/HEAD/lilo/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e587fc3fb16bc3d6","mcp_get_code":{"code_sha256":"e587fc3fb16bc3d6"}}]}