{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5NOE7AYJ7LD5ZGMZHI5Y6GDJPD","short_pith_number":"pith:5NOE7AYJ","canonical_record":{"source":{"id":"2603.21563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-23T04:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"ca5a6842de66a8dcdec4d44e344db4ba5f6ca00bfb0a4396ab441554e5b66c1b","abstract_canon_sha256":"e265e3d0c697e6a9e52ccd7d3221a0dfb2e45e90616804203003381ab2947586"},"schema_version":"1.0"},"canonical_sha256":"eb5c4f8309fac7dc99993a3b8f186978f3a8e989b2e208e246807f0f1757054f","source":{"kind":"arxiv","id":"2603.21563","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.21563","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2603.21563v2","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21563","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"5NOE7AYJ7LD5","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"5NOE7AYJ7LD5ZGMZ","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"5NOE7AYJ","created_at":"2026-05-27T01:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5NOE7AYJ7LD5ZGMZHI5Y6GDJPD","target":"record","payload":{"canonical_record":{"source":{"id":"2603.21563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-23T04:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"ca5a6842de66a8dcdec4d44e344db4ba5f6ca00bfb0a4396ab441554e5b66c1b","abstract_canon_sha256":"e265e3d0c697e6a9e52ccd7d3221a0dfb2e45e90616804203003381ab2947586"},"schema_version":"1.0"},"canonical_sha256":"eb5c4f8309fac7dc99993a3b8f186978f3a8e989b2e208e246807f0f1757054f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:47.308061Z","signature_b64":"t1UTtd3EkxXfomTVNuzSjQb55aOLexGL5NwRgCCQFxFbRN9UMRv5Pp9jaaUeNyhLz21OQVbq6Lf3FZ0zIk4NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb5c4f8309fac7dc99993a3b8f186978f3a8e989b2e208e246807f0f1757054f","last_reissued_at":"2026-05-27T01:05:47.307426Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:47.307426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.21563","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+CrlzPeB6faXPpoBO2AGI/2xuMxgnpP36XlhVin19af9VOd30+d3ImvD/1RgP/KgTqzjpwKdO3y/FLwChsO6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:02:18.212253Z"},"content_sha256":"dd2fe3c4d7765e98ebf87ee27b98890b463cff9d42cf1166c2852932fef4dbcc","schema_version":"1.0","event_id":"sha256:dd2fe3c4d7765e98ebf87ee27b98890b463cff9d42cf1166c2852932fef4dbcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5NOE7AYJ7LD5ZGMZHI5Y6GDJPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Counterfactual Credit Policy Optimization for Multi-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fuzhen Zhuang, Huiming Zhang, Jinju Chen, Wan Tian, Yang Liu, Yikun Ban, Zhongyi Li","submitted_at":"2026-03-23T04:35:02Z","abstract_excerpt":"Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce Collaborative Credit Policy Optimization (CCPO), an optimizer-agnostic credit assignment layer that converts team-level outcomes into agent-specific learning signals. CCPO provides two complementary allocators. Counterfactual credit estimates an agent's marginal contribution by comparing the realized team outc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.21563","kind":"arxiv","version":2},"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/2603.21563/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":"2026-05-27T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ts91i7rWdQjamfZwO2dNHwY3CnynMb1V000Qc8D5uIjRqqRCpyAe3OMAXHTpWABr2osTualw+4PObFm5eCj/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:02:18.212960Z"},"content_sha256":"3fdf7d38e1068ca86626e2c72bc6b08b19df8e18428cc8528e4d794de5530502","schema_version":"1.0","event_id":"sha256:3fdf7d38e1068ca86626e2c72bc6b08b19df8e18428cc8528e4d794de5530502"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NOE7AYJ7LD5ZGMZHI5Y6GDJPD/bundle.json","state_url":"https://pith.science/pith/5NOE7AYJ7LD5ZGMZHI5Y6GDJPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NOE7AYJ7LD5ZGMZHI5Y6GDJPD/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":"2026-06-12T06:02:18Z","links":{"resolver":"https://pith.science/pith/5NOE7AYJ7LD5ZGMZHI5Y6GDJPD","bundle":"https://pith.science/pith/5NOE7AYJ7LD5ZGMZHI5Y6GDJPD/bundle.json","state":"https://pith.science/pith/5NOE7AYJ7LD5ZGMZHI5Y6GDJPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NOE7AYJ7LD5ZGMZHI5Y6GDJPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5NOE7AYJ7LD5ZGMZHI5Y6GDJPD","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":"e265e3d0c697e6a9e52ccd7d3221a0dfb2e45e90616804203003381ab2947586","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-23T04:35:02Z","title_canon_sha256":"ca5a6842de66a8dcdec4d44e344db4ba5f6ca00bfb0a4396ab441554e5b66c1b"},"schema_version":"1.0","source":{"id":"2603.21563","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.21563","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2603.21563v2","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21563","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"5NOE7AYJ7LD5","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"5NOE7AYJ7LD5ZGMZ","created_at":"2026-05-27T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"5NOE7AYJ","created_at":"2026-05-27T01:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:3fdf7d38e1068ca86626e2c72bc6b08b19df8e18428cc8528e4d794de5530502","target":"graph","created_at":"2026-05-27T01:05:47Z","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/2603.21563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce Collaborative Credit Policy Optimization (CCPO), an optimizer-agnostic credit assignment layer that converts team-level outcomes into agent-specific learning signals. CCPO provides two complementary allocators. Counterfactual credit estimates an agent's marginal contribution by comparing the realized team outc","authors_text":"Fuzhen Zhuang, Huiming Zhang, Jinju Chen, Wan Tian, Yang Liu, Yikun Ban, Zhongyi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-23T04:35:02Z","title":"Counterfactual Credit Policy Optimization for Multi-Agent Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.21563","kind":"arxiv","version":2},"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:dd2fe3c4d7765e98ebf87ee27b98890b463cff9d42cf1166c2852932fef4dbcc","target":"record","created_at":"2026-05-27T01:05:47Z","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":"e265e3d0c697e6a9e52ccd7d3221a0dfb2e45e90616804203003381ab2947586","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-23T04:35:02Z","title_canon_sha256":"ca5a6842de66a8dcdec4d44e344db4ba5f6ca00bfb0a4396ab441554e5b66c1b"},"schema_version":"1.0","source":{"id":"2603.21563","kind":"arxiv","version":2}},"canonical_sha256":"eb5c4f8309fac7dc99993a3b8f186978f3a8e989b2e208e246807f0f1757054f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb5c4f8309fac7dc99993a3b8f186978f3a8e989b2e208e246807f0f1757054f","first_computed_at":"2026-05-27T01:05:47.307426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:47.307426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t1UTtd3EkxXfomTVNuzSjQb55aOLexGL5NwRgCCQFxFbRN9UMRv5Pp9jaaUeNyhLz21OQVbq6Lf3FZ0zIk4NAw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:47.308061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.21563","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd2fe3c4d7765e98ebf87ee27b98890b463cff9d42cf1166c2852932fef4dbcc","sha256:3fdf7d38e1068ca86626e2c72bc6b08b19df8e18428cc8528e4d794de5530502"],"state_sha256":"5138c5ea47a90063d4975b80d4d5e7dfa198ae8e7cac91bb81547c1142ef54a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gl9u3K1TUMnRbc/0WwLvP62lhtkJ/MJ+S9MOeUrma382GMlpc8OQgmGWoxqoxFLioy8UTq/f5zuGATF2W/NuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T06:02:18.216102Z","bundle_sha256":"4fe5f472227911ee6aba7d5430d43cc7eaac481ecd77c2fabded6e435383fae1"}}