{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:35TESAL5TZYZIKB2746EZ72Q62","short_pith_number":"pith:35TESAL5","canonical_record":{"source":{"id":"2310.18940","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"4f484f353352a7426b02b4caf8ac92c67bcf7ba7d88cfac8c1f231ce9d5c29d6","abstract_canon_sha256":"69ed2284114fc30edc7b2c559b60029ec3b95cedaf2a6a3f2cc622a5fe2b2637"},"schema_version":"1.0"},"canonical_sha256":"df6649017d9e7194283aff3c4cff50f6a817a297a01344e01f002b7c53a8b136","source":{"kind":"arxiv","id":"2310.18940","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18940","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18940v4","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18940","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_12","alias_value":"35TESAL5TZYZ","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_16","alias_value":"35TESAL5TZYZIKB2","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_8","alias_value":"35TESAL5","created_at":"2026-07-05T11:11:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:35TESAL5TZYZIKB2746EZ72Q62","target":"record","payload":{"canonical_record":{"source":{"id":"2310.18940","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"4f484f353352a7426b02b4caf8ac92c67bcf7ba7d88cfac8c1f231ce9d5c29d6","abstract_canon_sha256":"69ed2284114fc30edc7b2c559b60029ec3b95cedaf2a6a3f2cc622a5fe2b2637"},"schema_version":"1.0"},"canonical_sha256":"df6649017d9e7194283aff3c4cff50f6a817a297a01344e01f002b7c53a8b136","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:30.425473Z","signature_b64":"/b3qiBCQvBkJFDltxxDk+4vsUv6CL5hW5idOy/ju/v/6S7UZSPVREk6PnbquncdNayNjEdVDKGfQHbk9ujiCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df6649017d9e7194283aff3c4cff50f6a817a297a01344e01f002b7c53a8b136","last_reissued_at":"2026-07-05T11:11:30.424929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:30.424929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.18940","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSv23y6TrjYuzuPtofdcv3mgut3e2YoIIKOcs0W2xK0KPt7DFNnH/glxzssr0dGymR+P60Le7msjEW7PUVxjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:50:45.157817Z"},"content_sha256":"543af93c880f0ccac66e002947fe5dd296595af7faa9d7348da041dc867053cf","schema_version":"1.0","event_id":"sha256:543af93c880f0ccac66e002947fe5dd296595af7faa9d7348da041dc867053cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:35TESAL5TZYZIKB2746EZ72Q62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Chao Yu, Fei Fang, Yi Wu, Yu Wang, Zelai Xu","submitted_at":"2023-10-29T09:02:57Z","abstract_excerpt":"Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is inherited from the model's training data and results in suboptimal performance. To develop strategic language agents, i.e., agents that generate flexible language actions and possess strong decision-making abilities, we propose a novel framework that powers LLM-based agents with reinforcement learning (RL). We consider Werewolf, a popular social deduction gam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18940","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.18940/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJLS7YHFIooe7GxqPnHcCYC1lZlv2qf8twj6JPURTT+jbe9jxtZumaw0y23/9pQazhdtkOmu4mQYdLeQ4/x9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:50:45.158404Z"},"content_sha256":"af550d7704c9a4e6e5f6301df7381b9db462a0c898e04eac602f6d887e989979","schema_version":"1.0","event_id":"sha256:af550d7704c9a4e6e5f6301df7381b9db462a0c898e04eac602f6d887e989979"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35TESAL5TZYZIKB2746EZ72Q62/bundle.json","state_url":"https://pith.science/pith/35TESAL5TZYZIKB2746EZ72Q62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35TESAL5TZYZIKB2746EZ72Q62/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T23:50:45Z","links":{"resolver":"https://pith.science/pith/35TESAL5TZYZIKB2746EZ72Q62","bundle":"https://pith.science/pith/35TESAL5TZYZIKB2746EZ72Q62/bundle.json","state":"https://pith.science/pith/35TESAL5TZYZIKB2746EZ72Q62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35TESAL5TZYZIKB2746EZ72Q62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:35TESAL5TZYZIKB2746EZ72Q62","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"69ed2284114fc30edc7b2c559b60029ec3b95cedaf2a6a3f2cc622a5fe2b2637","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","title_canon_sha256":"4f484f353352a7426b02b4caf8ac92c67bcf7ba7d88cfac8c1f231ce9d5c29d6"},"schema_version":"1.0","source":{"id":"2310.18940","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18940","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18940v4","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18940","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_12","alias_value":"35TESAL5TZYZ","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_16","alias_value":"35TESAL5TZYZIKB2","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_8","alias_value":"35TESAL5","created_at":"2026-07-05T11:11:30Z"}],"graph_snapshots":[{"event_id":"sha256:af550d7704c9a4e6e5f6301df7381b9db462a0c898e04eac602f6d887e989979","target":"graph","created_at":"2026-07-05T11:11:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.18940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is inherited from the model's training data and results in suboptimal performance. To develop strategic language agents, i.e., agents that generate flexible language actions and possess strong decision-making abilities, we propose a novel framework that powers LLM-based agents with reinforcement learning (RL). We consider Werewolf, a popular social deduction gam","authors_text":"Chao Yu, Fei Fang, Yi Wu, Yu Wang, Zelai Xu","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18940","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:543af93c880f0ccac66e002947fe5dd296595af7faa9d7348da041dc867053cf","target":"record","created_at":"2026-07-05T11:11:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"69ed2284114fc30edc7b2c559b60029ec3b95cedaf2a6a3f2cc622a5fe2b2637","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","title_canon_sha256":"4f484f353352a7426b02b4caf8ac92c67bcf7ba7d88cfac8c1f231ce9d5c29d6"},"schema_version":"1.0","source":{"id":"2310.18940","kind":"arxiv","version":4}},"canonical_sha256":"df6649017d9e7194283aff3c4cff50f6a817a297a01344e01f002b7c53a8b136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df6649017d9e7194283aff3c4cff50f6a817a297a01344e01f002b7c53a8b136","first_computed_at":"2026-07-05T11:11:30.424929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:30.424929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/b3qiBCQvBkJFDltxxDk+4vsUv6CL5hW5idOy/ju/v/6S7UZSPVREk6PnbquncdNayNjEdVDKGfQHbk9ujiCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:30.425473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18940","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:543af93c880f0ccac66e002947fe5dd296595af7faa9d7348da041dc867053cf","sha256:af550d7704c9a4e6e5f6301df7381b9db462a0c898e04eac602f6d887e989979"],"state_sha256":"b689b123d57fb8367fdc03db3ebb748e2fd8623ae8c6dae12bc93aa2c29a1835"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WwGZ739wevsaLqAC7HqpNZ1nEIi5+7RnLpo8S5wUgGfFIfthXol0u8PxPoDzJK8Axo5tZc/FcGl6ODve/gXiBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:50:45.162422Z","bundle_sha256":"4d0390521868c972d24abe3fdaf600bdfb5a6458e118eff763b98b9ee2b66d6d"}}