{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7DP36N5A4UJWDCRBUAEY2KKZ6X","short_pith_number":"pith:7DP36N5A","schema_version":"1.0","canonical_sha256":"f8dfbf37a0e513618a21a0098d2959f5d52ccb5716162d0e8cc1d7b930d3c673","source":{"kind":"arxiv","id":"2502.16863","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"Dayi Dong, Jean-Baptiste Bouvier, Kartik Nagpal, Negar Mehr","submitted_at":"2025-02-24T05:56:47Z","abstract_excerpt":"Recent work, spanning from autonomous vehicle coordination to in-space assembly, has shown the importance of learning collaborative behavior for enabling robots to achieve shared goals. A common approach for learning this cooperative behavior is to utilize the centralized-training decentralized-execution paradigm. However, this approach also introduces a new challenge: how do we evaluate the contributions of each agent's actions to the overall success or failure of the team. This credit assignment problem has remained open, and has been extensively studied in the Multi-Agent Reinforcement Lear"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.16863","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MA","submitted_at":"2025-02-24T05:56:47Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"b38ebd3e4afcc4c235788ba807c9563c13e64cc34e26bdaf5e0aa5bb81ad18ef","abstract_canon_sha256":"b553e9b5a546589674e5f2d7deb1cfa68a4336f90b11328d54152c09017b5ed2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:01.171260Z","signature_b64":"dA8/CPBYNB4g1rgqt4rjG2O/y+5fIc1MUqcUKsIVmJE/N8O8ZqQtm3LsFDuildfcr2X5sIuvIGlFo6lAzi7/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8dfbf37a0e513618a21a0098d2959f5d52ccb5716162d0e8cc1d7b930d3c673","last_reissued_at":"2026-07-05T10:19:01.170775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:01.170775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"Dayi Dong, Jean-Baptiste Bouvier, Kartik Nagpal, Negar Mehr","submitted_at":"2025-02-24T05:56:47Z","abstract_excerpt":"Recent work, spanning from autonomous vehicle coordination to in-space assembly, has shown the importance of learning collaborative behavior for enabling robots to achieve shared goals. A common approach for learning this cooperative behavior is to utilize the centralized-training decentralized-execution paradigm. However, this approach also introduces a new challenge: how do we evaluate the contributions of each agent's actions to the overall success or failure of the team. This credit assignment problem has remained open, and has been extensively studied in the Multi-Agent Reinforcement Lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16863","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/2502.16863/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.16863","created_at":"2026-07-05T10:19:01.170835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16863v1","created_at":"2026-07-05T10:19:01.170835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16863","created_at":"2026-07-05T10:19:01.170835+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DP36N5A4UJW","created_at":"2026-07-05T10:19:01.170835+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DP36N5A4UJWDCRB","created_at":"2026-07-05T10:19:01.170835+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DP36N5A","created_at":"2026-07-05T10:19:01.170835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27922","citing_title":"Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27922","citing_title":"Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27922","citing_title":"Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30246","citing_title":"Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09459","citing_title":"From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X","json":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X.json","graph_json":"https://pith.science/api/pith-number/7DP36N5A4UJWDCRBUAEY2KKZ6X/graph.json","events_json":"https://pith.science/api/pith-number/7DP36N5A4UJWDCRBUAEY2KKZ6X/events.json","paper":"https://pith.science/paper/7DP36N5A"},"agent_actions":{"view_html":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X","download_json":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X.json","view_paper":"https://pith.science/paper/7DP36N5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16863&json=true","fetch_graph":"https://pith.science/api/pith-number/7DP36N5A4UJWDCRBUAEY2KKZ6X/graph.json","fetch_events":"https://pith.science/api/pith-number/7DP36N5A4UJWDCRBUAEY2KKZ6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X/action/storage_attestation","attest_author":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X/action/author_attestation","sign_citation":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X/action/citation_signature","submit_replication":"https://pith.science/pith/7DP36N5A4UJWDCRBUAEY2KKZ6X/action/replication_record"}},"created_at":"2026-07-05T10:19:01.170835+00:00","updated_at":"2026-07-05T10:19:01.170835+00:00"}