{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y6TZH5KS5HRU6SFZZT5OBCJNM4","short_pith_number":"pith:Y6TZH5KS","canonical_record":{"source":{"id":"2601.21523","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:38:19Z","cross_cats_sorted":[],"title_canon_sha256":"45a82b410bd0a0820d886dae9dddcd8bb2aeb01ddd16b50dc85e69ae683dc770","abstract_canon_sha256":"e35faad395d51cd82694439b6b3ee6cc0a1094fd19f3b1831fac5d598137ffd2"},"schema_version":"1.0"},"canonical_sha256":"c7a793f552e9e34f48b9ccfae0892d673083c3415ccd2ad333b8b06f48ab7f1d","source":{"kind":"arxiv","id":"2601.21523","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21523","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21523v2","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21523","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"Y6TZH5KS5HRU","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"Y6TZH5KS5HRU6SFZ","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"Y6TZH5KS","created_at":"2026-07-07T02:18:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y6TZH5KS5HRU6SFZZT5OBCJNM4","target":"record","payload":{"canonical_record":{"source":{"id":"2601.21523","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:38:19Z","cross_cats_sorted":[],"title_canon_sha256":"45a82b410bd0a0820d886dae9dddcd8bb2aeb01ddd16b50dc85e69ae683dc770","abstract_canon_sha256":"e35faad395d51cd82694439b6b3ee6cc0a1094fd19f3b1831fac5d598137ffd2"},"schema_version":"1.0"},"canonical_sha256":"c7a793f552e9e34f48b9ccfae0892d673083c3415ccd2ad333b8b06f48ab7f1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:33.756568Z","signature_b64":"KWr7vXOtniORWDNBDqaDXYEbLR0gZFqMTa6+BKzu1YOUNZxO3Lub33tCaLa9KOh6Tt78ZUsUERlH2gaCoviNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a793f552e9e34f48b9ccfae0892d673083c3415ccd2ad333b8b06f48ab7f1d","last_reissued_at":"2026-07-07T02:18:33.755637Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:33.755637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.21523","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":"2026-07-07T02:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PE4SrN8AnKIdIinUGSy0V1zE/QyKp7xTStuL5Ox6Qj45ie4e+oKgXChhnQGTGeJrpeoTRgYMuUc9NXzEMdhcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:16:45.650499Z"},"content_sha256":"8771c6da3effea987902866c7d4e7877230e5e17bbc9764d798d9bb82219043e","schema_version":"1.0","event_id":"sha256:8771c6da3effea987902866c7d4e7877230e5e17bbc9764d798d9bb82219043e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y6TZH5KS5HRU6SFZZT5OBCJNM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bang Giang Le, Viet Cuong Ta","submitted_at":"2026-01-29T10:38:19Z","abstract_excerpt":"To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting. However, global rewards are usually noisy because they contain the contributions of all agents, which have to be resolved in the credit assignment process. On the other hand, using local reward benefits from faster learning due to the separation of agents' contributions, but can be suboptimal as agents myopically optimize their own reward while disregarding the global optimality. In this work,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21523","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/2601.21523/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":"2026-07-07T02:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Duynm52bCt7744RxI4BCDljs/3tei+566/MWptbLAa+3xdKOjqymO+OUcKAuq31aN9mN787NVX/Qtexb5bI2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:16:45.650831Z"},"content_sha256":"9aeb5e6918112ed4705779216aad209e9a7981c0226b9ae2a157d1cd4e8e26fc","schema_version":"1.0","event_id":"sha256:9aeb5e6918112ed4705779216aad209e9a7981c0226b9ae2a157d1cd4e8e26fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y6TZH5KS5HRU6SFZZT5OBCJNM4/bundle.json","state_url":"https://pith.science/pith/Y6TZH5KS5HRU6SFZZT5OBCJNM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y6TZH5KS5HRU6SFZZT5OBCJNM4/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":"2026-08-22T09:16:45Z","links":{"resolver":"https://pith.science/pith/Y6TZH5KS5HRU6SFZZT5OBCJNM4","bundle":"https://pith.science/pith/Y6TZH5KS5HRU6SFZZT5OBCJNM4/bundle.json","state":"https://pith.science/pith/Y6TZH5KS5HRU6SFZZT5OBCJNM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y6TZH5KS5HRU6SFZZT5OBCJNM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y6TZH5KS5HRU6SFZZT5OBCJNM4","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":"e35faad395d51cd82694439b6b3ee6cc0a1094fd19f3b1831fac5d598137ffd2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:38:19Z","title_canon_sha256":"45a82b410bd0a0820d886dae9dddcd8bb2aeb01ddd16b50dc85e69ae683dc770"},"schema_version":"1.0","source":{"id":"2601.21523","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21523","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21523v2","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21523","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"Y6TZH5KS5HRU","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"Y6TZH5KS5HRU6SFZ","created_at":"2026-07-07T02:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"Y6TZH5KS","created_at":"2026-07-07T02:18:33Z"}],"graph_snapshots":[{"event_id":"sha256:9aeb5e6918112ed4705779216aad209e9a7981c0226b9ae2a157d1cd4e8e26fc","target":"graph","created_at":"2026-07-07T02:18:33Z","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/2601.21523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting. However, global rewards are usually noisy because they contain the contributions of all agents, which have to be resolved in the credit assignment process. On the other hand, using local reward benefits from faster learning due to the separation of agents' contributions, but can be suboptimal as agents myopically optimize their own reward while disregarding the global optimality. In this work,","authors_text":"Bang Giang Le, Viet Cuong Ta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:38:19Z","title":"Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21523","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":"sha256:8771c6da3effea987902866c7d4e7877230e5e17bbc9764d798d9bb82219043e","target":"record","created_at":"2026-07-07T02:18:33Z","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":"e35faad395d51cd82694439b6b3ee6cc0a1094fd19f3b1831fac5d598137ffd2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:38:19Z","title_canon_sha256":"45a82b410bd0a0820d886dae9dddcd8bb2aeb01ddd16b50dc85e69ae683dc770"},"schema_version":"1.0","source":{"id":"2601.21523","kind":"arxiv","version":2}},"canonical_sha256":"c7a793f552e9e34f48b9ccfae0892d673083c3415ccd2ad333b8b06f48ab7f1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7a793f552e9e34f48b9ccfae0892d673083c3415ccd2ad333b8b06f48ab7f1d","first_computed_at":"2026-07-07T02:18:33.755637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:33.755637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KWr7vXOtniORWDNBDqaDXYEbLR0gZFqMTa6+BKzu1YOUNZxO3Lub33tCaLa9KOh6Tt78ZUsUERlH2gaCoviNDg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:33.756568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21523","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8771c6da3effea987902866c7d4e7877230e5e17bbc9764d798d9bb82219043e","sha256:9aeb5e6918112ed4705779216aad209e9a7981c0226b9ae2a157d1cd4e8e26fc"],"state_sha256":"90996afb7f4a986752702d89292b9be6b7a11332055403fb5e2530aa93eac8ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqN2uPy0R4/RpP3cBSN5fK8ytXvLDQghrm1jlX8Gmy0K2mzL1BH4z6+qL9Vu0nMR/aK+pelVV+hrACQZ3nfzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:16:45.653899Z","bundle_sha256":"fef6e4f3e4cebf561bd1f64eb3f4294608c9b669511bf298649663e01bb5b2a9"}}