{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZZY4LKIR5QPQ2GJRLVAI65MKEB","short_pith_number":"pith:ZZY4LKIR","canonical_record":{"source":{"id":"2508.12338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-17T11:57:34Z","cross_cats_sorted":[],"title_canon_sha256":"3f8bd5ea1561417bb6a6131f81855a69450bc30b94756236a82f592ee58666d4","abstract_canon_sha256":"9f1e67db7cef560237ad3f4decb040d4269baa8ea0bd10a584462bcdf66534ae"},"schema_version":"1.0"},"canonical_sha256":"ce71c5a911ec1f0d19315d408f758a20464797be24a0c83d85b7108f2644d5a9","source":{"kind":"arxiv","id":"2508.12338","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12338","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12338v1","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12338","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"ZZY4LKIR5QPQ","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"pith_short_16","alias_value":"ZZY4LKIR5QPQ2GJR","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"pith_short_8","alias_value":"ZZY4LKIR","created_at":"2026-07-05T11:55:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZZY4LKIR5QPQ2GJRLVAI65MKEB","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-17T11:57:34Z","cross_cats_sorted":[],"title_canon_sha256":"3f8bd5ea1561417bb6a6131f81855a69450bc30b94756236a82f592ee58666d4","abstract_canon_sha256":"9f1e67db7cef560237ad3f4decb040d4269baa8ea0bd10a584462bcdf66534ae"},"schema_version":"1.0"},"canonical_sha256":"ce71c5a911ec1f0d19315d408f758a20464797be24a0c83d85b7108f2644d5a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:03.794442Z","signature_b64":"vdZqz3Aa2C2Np8yaqmMwNEV9vS2Wpk2gARB7Jds82Ph08Z+e/O5eIHU3kniPGxD2ZRJ1ytxeagli/7CxEZ+uBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce71c5a911ec1f0d19315d408f758a20464797be24a0c83d85b7108f2644d5a9","last_reissued_at":"2026-07-05T11:55:03.793951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:03.793951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12338","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jg3B541zM8wTLwEc1X6p/+bSg31Y+KIDPe/nToLhOW5ZCyn1tK6TGrVHOQDEO+c0B8Wh5jBtRgt3109Bz7W0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:52:00.115947Z"},"content_sha256":"55086ccd3bc706dca7bb6b78af8ca9e788554d3679622a93364e117218132bdf","schema_version":"1.0","event_id":"sha256:55086ccd3bc706dca7bb6b78af8ca9e788554d3679622a93364e117218132bdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZZY4LKIR5QPQ2GJRLVAI65MKEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Zhang, Ganqu Cui, Jiacheng Ruan, Lei Bai, Peng Ye, Shengji Tang, Tao Chen, Ting Liu, Weihao Lin, Wenzhen Yuan, Yuzhuo Fu","submitted_at":"2025-08-17T11:57:34Z","abstract_excerpt":"Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex reward models severely limits scalability. While existing self-feedback methods aim to address this problem, they are constrained by the capabilities of a single model, which can lead to overconfidence in incorrect answers, reward hacking, and even training collapse. To this end, we propose Reinforcement Learning from Coevolutionary Collective Feedback (RLCCF), a novel RL framework that enables multi-model collaborative e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12338","kind":"arxiv","version":1},"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/2508.12338/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":"2026-07-05T11:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhZV2ffcaaJVV4B03muCTbEGFWMHxPTaVOUVxz8r41apG7RTBNcgS0Yku90KYTuu4H5DuSUqBehGOIq+fFOtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:52:00.116263Z"},"content_sha256":"a93ce5228e0070e12f8d2f8a8e124922f0f24031dfb987979ae36b7951834d3c","schema_version":"1.0","event_id":"sha256:a93ce5228e0070e12f8d2f8a8e124922f0f24031dfb987979ae36b7951834d3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZZY4LKIR5QPQ2GJRLVAI65MKEB/bundle.json","state_url":"https://pith.science/pith/ZZY4LKIR5QPQ2GJRLVAI65MKEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZZY4LKIR5QPQ2GJRLVAI65MKEB/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":"2026-08-06T17:52:00Z","links":{"resolver":"https://pith.science/pith/ZZY4LKIR5QPQ2GJRLVAI65MKEB","bundle":"https://pith.science/pith/ZZY4LKIR5QPQ2GJRLVAI65MKEB/bundle.json","state":"https://pith.science/pith/ZZY4LKIR5QPQ2GJRLVAI65MKEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZZY4LKIR5QPQ2GJRLVAI65MKEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZZY4LKIR5QPQ2GJRLVAI65MKEB","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":"9f1e67db7cef560237ad3f4decb040d4269baa8ea0bd10a584462bcdf66534ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-17T11:57:34Z","title_canon_sha256":"3f8bd5ea1561417bb6a6131f81855a69450bc30b94756236a82f592ee58666d4"},"schema_version":"1.0","source":{"id":"2508.12338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12338","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12338v1","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12338","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"ZZY4LKIR5QPQ","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"pith_short_16","alias_value":"ZZY4LKIR5QPQ2GJR","created_at":"2026-07-05T11:55:03Z"},{"alias_kind":"pith_short_8","alias_value":"ZZY4LKIR","created_at":"2026-07-05T11:55:03Z"}],"graph_snapshots":[{"event_id":"sha256:a93ce5228e0070e12f8d2f8a8e124922f0f24031dfb987979ae36b7951834d3c","target":"graph","created_at":"2026-07-05T11:55:03Z","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/2508.12338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex reward models severely limits scalability. While existing self-feedback methods aim to address this problem, they are constrained by the capabilities of a single model, which can lead to overconfidence in incorrect answers, reward hacking, and even training collapse. To this end, we propose Reinforcement Learning from Coevolutionary Collective Feedback (RLCCF), a novel RL framework that enables multi-model collaborative e","authors_text":"Bo Zhang, Ganqu Cui, Jiacheng Ruan, Lei Bai, Peng Ye, Shengji Tang, Tao Chen, Ting Liu, Weihao Lin, Wenzhen Yuan, Yuzhuo Fu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-17T11:57:34Z","title":"Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12338","kind":"arxiv","version":1},"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":"sha256:55086ccd3bc706dca7bb6b78af8ca9e788554d3679622a93364e117218132bdf","target":"record","created_at":"2026-07-05T11:55:03Z","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":"9f1e67db7cef560237ad3f4decb040d4269baa8ea0bd10a584462bcdf66534ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-17T11:57:34Z","title_canon_sha256":"3f8bd5ea1561417bb6a6131f81855a69450bc30b94756236a82f592ee58666d4"},"schema_version":"1.0","source":{"id":"2508.12338","kind":"arxiv","version":1}},"canonical_sha256":"ce71c5a911ec1f0d19315d408f758a20464797be24a0c83d85b7108f2644d5a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce71c5a911ec1f0d19315d408f758a20464797be24a0c83d85b7108f2644d5a9","first_computed_at":"2026-07-05T11:55:03.793951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:03.793951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vdZqz3Aa2C2Np8yaqmMwNEV9vS2Wpk2gARB7Jds82Ph08Z+e/O5eIHU3kniPGxD2ZRJ1ytxeagli/7CxEZ+uBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:03.794442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55086ccd3bc706dca7bb6b78af8ca9e788554d3679622a93364e117218132bdf","sha256:a93ce5228e0070e12f8d2f8a8e124922f0f24031dfb987979ae36b7951834d3c"],"state_sha256":"5a844120f8e3ee4ae48870b8cf9bf817003a999a963c0d231a139db9721cb9bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cBuSjyclHedqHKvzFWTzi05m5mfL9VMjc6rfrbA5M0Y8zsdSV5qEcWdWysmazrDYPrFQarjMdWfKP24+ht0uBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:52:00.119738Z","bundle_sha256":"c4f516924e164249660512bf5f81c2b1d11ed4d0d208c96a7e76b187d5cf2955"}}