{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VDRAEGVVAOIIHNTM2ATLRN6MZ4","short_pith_number":"pith:VDRAEGVV","schema_version":"1.0","canonical_sha256":"a8e2021ab5039083b66cd026b8b7cccf245eac13121c4fcea900596c2bcf888a","source":{"kind":"arxiv","id":"2607.19809","version":1},"attestation_state":"computed","paper":{"title":"Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Naoto Yoshida, Tadahiro Taniguchi, Taisuke Takayama","submitted_at":"2026-07-22T06:42:03Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches enable decentralized agents to learn messages grounded in their own observations, but they rely only on current observations and cannot convey information accumulated over time. We propose Dreamer-CPC, a decentralized model-based MARL method that integrates message learning based on Collective Predictive Coding (CPC) into the world model of DreamerV3. Each agent independently maintains a world model and a message mo"},"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":"2607.19809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-07-22T06:42:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"72eb2e34ff54236f94bdd16cf1b3cdd7f8646bb465a9f285743bc449544f8ecd","abstract_canon_sha256":"8e61c60d7d8304dc0b3fb8cced40b6f87a5423e44c259b99dec7937eb31fd023"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:00.412529Z","signature_b64":"PPGpo44w3+HgjLQIi2tSp5vv8oA5c9SK0JahMzfu7WT06Q2+nvaxEKq72P7SQ20+OSRoV3dVpUSRzEii70iGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8e2021ab5039083b66cd026b8b7cccf245eac13121c4fcea900596c2bcf888a","last_reissued_at":"2026-07-23T01:24:00.411632Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:00.411632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Naoto Yoshida, Tadahiro Taniguchi, Taisuke Takayama","submitted_at":"2026-07-22T06:42:03Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches enable decentralized agents to learn messages grounded in their own observations, but they rely only on current observations and cannot convey information accumulated over time. We propose Dreamer-CPC, a decentralized model-based MARL method that integrates message learning based on Collective Predictive Coding (CPC) into the world model of DreamerV3. Each agent independently maintains a world model and a message mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19809","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/2607.19809/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":"2607.19809","created_at":"2026-07-23T01:24:00.412096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19809v1","created_at":"2026-07-23T01:24:00.412096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19809","created_at":"2026-07-23T01:24:00.412096+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDRAEGVVAOII","created_at":"2026-07-23T01:24:00.412096+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDRAEGVVAOIIHNTM","created_at":"2026-07-23T01:24:00.412096+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDRAEGVV","created_at":"2026-07-23T01:24:00.412096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4","json":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4.json","graph_json":"https://pith.science/api/pith-number/VDRAEGVVAOIIHNTM2ATLRN6MZ4/graph.json","events_json":"https://pith.science/api/pith-number/VDRAEGVVAOIIHNTM2ATLRN6MZ4/events.json","paper":"https://pith.science/paper/VDRAEGVV"},"agent_actions":{"view_html":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4","download_json":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4.json","view_paper":"https://pith.science/paper/VDRAEGVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19809&json=true","fetch_graph":"https://pith.science/api/pith-number/VDRAEGVVAOIIHNTM2ATLRN6MZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/VDRAEGVVAOIIHNTM2ATLRN6MZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4/action/storage_attestation","attest_author":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4/action/author_attestation","sign_citation":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4/action/citation_signature","submit_replication":"https://pith.science/pith/VDRAEGVVAOIIHNTM2ATLRN6MZ4/action/replication_record"}},"created_at":"2026-07-23T01:24:00.412096+00:00","updated_at":"2026-07-23T01:24:00.412096+00:00"}