{"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/dict-mean","entry":"dict_mean","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":12,"n_papers_ran":9,"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":7,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"unverified":3},"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":"2604.13592","paper":"/paper/arxiv-2604-13592","title":"Foresight Optimization for Strategic Reasoning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wangjs9/ForesightOptim","path":"agent_trainers/trainers.py","file_url":"https://github.com/wangjs9/ForesightOptim/blob/HEAD/agent_trainers/trainers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e154ffa50c4434d1","mcp_get_code":{"code_sha256":"e154ffa50c4434d1"}},{"arxiv_id":"2502.15760","paper":"/paper/digi-q-learning-q-value-functions-for","title":"Digi-Q: Learning Q-Value Functions for Training Device-Control Agents","date":"2025-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0cfea60f8eda39cf","mcp_get_code":{"code_sha256":"0cfea60f8eda39cf"}},{"arxiv_id":"2411.02337","paper":"/paper/webrl-training-llm-web-agents-via-self","title":"WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/WebRL","path":"webrl/algorithms/webrl/trainer.py","file_url":"https://github.com/THUDM/WebRL/blob/HEAD/webrl/algorithms/webrl/trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"32579324c0d766ef","mcp_get_code":{"code_sha256":"32579324c0d766ef"}},{"arxiv_id":"2410.14803","paper":"/paper/distrl-an-asynchronous-distributed","title":"DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"distrl-lab/distrl-open","path":"distrl/algorithms/digirl/trainer.py","file_url":"https://github.com/distrl-lab/distrl-open/blob/HEAD/distrl/algorithms/digirl/trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0cfea60f8eda39cf","mcp_get_code":{"code_sha256":"0cfea60f8eda39cf"}},{"arxiv_id":"2410.07745","paper":"/paper/steptool-a-step-grained-reinforcement","title":"StepTool: A Step-grained Reinforcement Learning Framework for Tool Learning in LLMs","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuyq18/steptool","path":"src/baseline-archer/archer_trainer.py","file_url":"https://github.com/yuyq18/steptool/blob/HEAD/src/baseline-archer/archer_trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e154ffa50c4434d1","mcp_get_code":{"code_sha256":"e154ffa50c4434d1"}},{"arxiv_id":"2406.18139","paper":"/paper/look-m-look-once-optimization-in-kv-cache-for","title":"LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sustechbruce/look-m","path":"score.py","file_url":"https://github.com/sustechbruce/look-m/blob/HEAD/score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"184a512ccc58837f","mcp_get_code":{"code_sha256":"184a512ccc58837f"}},{"arxiv_id":"2406.11896","paper":"/paper/digirl-training-in-the-wild-device-control","title":"DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"digirl-agent/digirl","path":"digirl/algorithms/digirl/trainer.py","file_url":"https://github.com/digirl-agent/digirl/blob/HEAD/digirl/algorithms/digirl/trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0cfea60f8eda39cf","mcp_get_code":{"code_sha256":"0cfea60f8eda39cf"}},{"arxiv_id":"2406.08506","paper":"/paper/rgfn-synthesizable-molecular-generation-using","title":"RGFN: Synthesizable Molecular Generation Using GFlowNets","date":"2024-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"koziarskilab/rgfn","path":"rgfn/utils/helpers.py","file_url":"https://github.com/koziarskilab/rgfn/blob/HEAD/rgfn/utils/helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"13dff94f6985e4a8","mcp_get_code":{"code_sha256":"13dff94f6985e4a8"}},{"arxiv_id":"2402.19446","paper":"/paper/archer-training-language-model-agents-via","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifeizhou02/archer","path":"archer/algorithms/archer/trainer.py","file_url":"https://github.com/yifeizhou02/archer/blob/HEAD/archer/algorithms/archer/trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e154ffa50c4434d1","mcp_get_code":{"code_sha256":"e154ffa50c4434d1"}},{"arxiv_id":"2308.16463","paper":"/paper/sparkles-unlocking-chats-across-multiple","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HYPJUDY/Sparkles","path":"i4_score.py","file_url":"https://github.com/HYPJUDY/Sparkles/blob/HEAD/i4_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"184a512ccc58837f","mcp_get_code":{"code_sha256":"184a512ccc58837f"}},{"arxiv_id":"2106.10800","paper":"/paper/lossy-compression-for-lossless-prediction","title":"Lossy Compression for Lossless Prediction","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YannDubs/lossyless","path":"lossyless/helpers.py","file_url":"https://github.com/YannDubs/lossyless/blob/HEAD/lossyless/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a9a3c914c967c7d","mcp_get_code":{"code_sha256":"8a9a3c914c967c7d"}},{"arxiv_id":"2009.04416","paper":"/paper/phasic-policy-gradient","title":"Phasic Policy Gradient","date":"2020-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/phasic-policy-gradient","path":"phasic_policy_gradient/minibatch_optimize.py","file_url":"https://github.com/openai/phasic-policy-gradient/blob/HEAD/phasic_policy_gradient/minibatch_optimize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"80025f416c031ad6","mcp_get_code":{"code_sha256":"80025f416c031ad6"}}]}