{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LRCX72Z3SRRLDNWHUHI3OJZMGR","short_pith_number":"pith:LRCX72Z3","schema_version":"1.0","canonical_sha256":"5c457feb3b9462b1b6c7a1d1b7272c3456f6ab9cc1ca484b0dee494082a740d8","source":{"kind":"arxiv","id":"2505.21985","version":1},"attestation_state":"computed","paper":{"title":"Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Naoto Yoshida, Tadahiro Taniguchi","submitted_at":"2025-05-28T05:23:47Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), effective communication improves agent performance, particularly under partial observability. We propose MARL-CPC, a framework that enables communication among fully decentralized, independent agents without parameter sharing. MARL-CPC incorporates a message learning model based on collective predictive coding (CPC) from emergent communication research. Unlike conventional methods that treat messages as part of the action space and assume cooperation, MARL-CPC links messages to state inference, supporting communication in non-cooperative, reward-in"},"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":"2505.21985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-28T05:23:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c0c2ee1b2526bc4d858d5e209f1c64aaf3b0d5b1546fb353996865b0b1e75d8","abstract_canon_sha256":"b11dc4b7a9000ae143233fb1b15ca4e20f1178440d6cf11c722ab69a4e2940f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:07.394810Z","signature_b64":"+hm10uYpS2mnzdgk4yRVuLwRGpGjbS2pH87PDB1AkHnYuMmRFG+/ud1AwKniu6ateBkCFJZNOxuX2kgggLReBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c457feb3b9462b1b6c7a1d1b7272c3456f6ab9cc1ca484b0dee494082a740d8","last_reissued_at":"2026-07-05T11:11:07.394230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:07.394230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Naoto Yoshida, Tadahiro Taniguchi","submitted_at":"2025-05-28T05:23:47Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), effective communication improves agent performance, particularly under partial observability. We propose MARL-CPC, a framework that enables communication among fully decentralized, independent agents without parameter sharing. MARL-CPC incorporates a message learning model based on collective predictive coding (CPC) from emergent communication research. Unlike conventional methods that treat messages as part of the action space and assume cooperation, MARL-CPC links messages to state inference, supporting communication in non-cooperative, reward-in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21985","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/2505.21985/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":"2505.21985","created_at":"2026-07-05T11:11:07.394309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21985v1","created_at":"2026-07-05T11:11:07.394309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21985","created_at":"2026-07-05T11:11:07.394309+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRCX72Z3SRRL","created_at":"2026-07-05T11:11:07.394309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRCX72Z3SRRLDNWH","created_at":"2026-07-05T11:11:07.394309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRCX72Z3","created_at":"2026-07-05T11:11:07.394309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27532","citing_title":"SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR","json":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR.json","graph_json":"https://pith.science/api/pith-number/LRCX72Z3SRRLDNWHUHI3OJZMGR/graph.json","events_json":"https://pith.science/api/pith-number/LRCX72Z3SRRLDNWHUHI3OJZMGR/events.json","paper":"https://pith.science/paper/LRCX72Z3"},"agent_actions":{"view_html":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR","download_json":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR.json","view_paper":"https://pith.science/paper/LRCX72Z3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21985&json=true","fetch_graph":"https://pith.science/api/pith-number/LRCX72Z3SRRLDNWHUHI3OJZMGR/graph.json","fetch_events":"https://pith.science/api/pith-number/LRCX72Z3SRRLDNWHUHI3OJZMGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR/action/storage_attestation","attest_author":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR/action/author_attestation","sign_citation":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR/action/citation_signature","submit_replication":"https://pith.science/pith/LRCX72Z3SRRLDNWHUHI3OJZMGR/action/replication_record"}},"created_at":"2026-07-05T11:11:07.394309+00:00","updated_at":"2026-07-05T11:11:07.394309+00:00"}