{"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/normalized-columns-initializer","entry":"normalized_columns_initializer","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":8,"n_papers_ran":7,"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":5,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":1,"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":"2402.15546","paper":"/paper/himap-learning-heuristics-informed-policies","title":"HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaist-silab/himap","path":"src/models/vggnet.py","file_url":"https://github.com/kaist-silab/himap/blob/HEAD/src/models/vggnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"157c2af2dc5c2860","mcp_get_code":{"code_sha256":"157c2af2dc5c2860"}},{"arxiv_id":"2003.07069","paper":"/paper/self-supervised-discovering-of-causal","title":"Self-Supervised Discovering of Interpretable Features for Reinforcement Learning","date":"2020-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shiwj16/SSINet","path":"src/networks.py","file_url":"https://github.com/shiwj16/SSINet/blob/HEAD/src/networks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96708b203eb62ef3","mcp_get_code":{"code_sha256":"96708b203eb62ef3"}},{"arxiv_id":"2001.06680","paper":"/paper/tree-structured-policy-based-progressive","title":"Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video","date":"2020-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WuJie1010/TSP-PRL","path":"model.py","file_url":"https://github.com/WuJie1010/TSP-PRL/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0cbd595581568d9","mcp_get_code":{"code_sha256":"e0cbd595581568d9"}},{"arxiv_id":"1907.02874","paper":"/paper/attentive-multi-task-deep-reinforcement","title":"Attentive Multi-Task Deep Reinforcement Learning","date":"2019-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","path":"model.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef2d50dfca29c664","mcp_get_code":{"code_sha256":"ef2d50dfca29c664"}},{"arxiv_id":"1705.05363","paper":"/paper/curiosity-driven-exploration-by-self","title":"Curiosity-driven Exploration by Self-supervised Prediction","date":"2017-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pathak22/noreward-rl","path":"src/model.py","file_url":"https://github.com/pathak22/noreward-rl/blob/HEAD/src/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ef2d50dfca29c664","mcp_get_code":{"code_sha256":"ef2d50dfca29c664"}},{"arxiv_id":"1703.03864","paper":"/paper/evolution-strategies-as-a-scalable","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","date":"2017-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atgambardella/pytorch-es","path":"model.py","file_url":"https://github.com/atgambardella/pytorch-es/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b7f271057272097","mcp_get_code":{"code_sha256":"2b7f271057272097"}},{"arxiv_id":"1611.05763","paper":"/paper/learning-to-reinforcement-learn","title":"Learning to reinforcement learn","date":"2016-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awjuliani/Meta-RL","path":"helper.py","file_url":"https://github.com/awjuliani/Meta-RL/blob/HEAD/helper.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef2d50dfca29c664","mcp_get_code":{"code_sha256":"ef2d50dfca29c664"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dsinghnegi/atari_RL_agent","path":"models/a3c.py","file_url":"https://github.com/dsinghnegi/atari_RL_agent/blob/HEAD/models/a3c.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"96708b203eb62ef3","mcp_get_code":{"code_sha256":"96708b203eb62ef3"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/universe-starter-agent","path":"model.py","file_url":"https://github.com/openai/universe-starter-agent/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef2d50dfca29c664","mcp_get_code":{"code_sha256":"ef2d50dfca29c664"}}]}