{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XBQ73J7SZIC23HLM2BGKUCQFRK","short_pith_number":"pith:XBQ73J7S","schema_version":"1.0","canonical_sha256":"b861fda7f2ca05ad9d6cd04caa0a058a874c9e2f9c3030c4f7848e577d85f9ec","source":{"kind":"arxiv","id":"2312.08662","version":1},"attestation_state":"computed","paper":{"title":"From Centralized to Self-Supervised: Pursuing Realistic Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Jan-Philipp Fr\\\"anken, Logan Cross, Nick Haber, Violet Xiang","submitted_at":"2023-12-14T05:32:55Z","abstract_excerpt":"In real-world environments, autonomous agents rely on their egocentric observations. They must learn adaptive strategies to interact with others who possess mixed motivations, discernible only through visible cues. Several Multi-Agent Reinforcement Learning (MARL) methods adopt centralized approaches that involve either centralized training or reward-sharing, often violating the realistic ways in which living organisms, like animals or humans, process information and interact. MARL strategies deploying decentralized training with intrinsic motivation offer a self-supervised approach, enable ag"},"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":"2312.08662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-12-14T05:32:55Z","cross_cats_sorted":[],"title_canon_sha256":"62e953c62af9e12ce3837f5e8068d4d1a2b45e58baff39b8c1040e9de60e0795","abstract_canon_sha256":"8e03f3acd991f50394fbb08a8d5cd58a642ff258a6502a06f09c8c705b590b62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:07.682137Z","signature_b64":"sDJ4jE1vOxWDNAoZk6WRzzLift8ElepQU6EVtvJX2qaAkzrDZ8b+4vSm2RUODh0z+e9fJlSn7Im2sb0CwrpZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b861fda7f2ca05ad9d6cd04caa0a058a874c9e2f9c3030c4f7848e577d85f9ec","last_reissued_at":"2026-07-05T07:24:07.681789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:07.681789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Centralized to Self-Supervised: Pursuing Realistic Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Jan-Philipp Fr\\\"anken, Logan Cross, Nick Haber, Violet Xiang","submitted_at":"2023-12-14T05:32:55Z","abstract_excerpt":"In real-world environments, autonomous agents rely on their egocentric observations. They must learn adaptive strategies to interact with others who possess mixed motivations, discernible only through visible cues. Several Multi-Agent Reinforcement Learning (MARL) methods adopt centralized approaches that involve either centralized training or reward-sharing, often violating the realistic ways in which living organisms, like animals or humans, process information and interact. MARL strategies deploying decentralized training with intrinsic motivation offer a self-supervised approach, enable ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08662","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/2312.08662/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":"2312.08662","created_at":"2026-07-05T07:24:07.681844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08662v1","created_at":"2026-07-05T07:24:07.681844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08662","created_at":"2026-07-05T07:24:07.681844+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBQ73J7SZIC2","created_at":"2026-07-05T07:24:07.681844+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBQ73J7SZIC23HLM","created_at":"2026-07-05T07:24:07.681844+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBQ73J7S","created_at":"2026-07-05T07:24:07.681844+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/XBQ73J7SZIC23HLM2BGKUCQFRK","json":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK.json","graph_json":"https://pith.science/api/pith-number/XBQ73J7SZIC23HLM2BGKUCQFRK/graph.json","events_json":"https://pith.science/api/pith-number/XBQ73J7SZIC23HLM2BGKUCQFRK/events.json","paper":"https://pith.science/paper/XBQ73J7S"},"agent_actions":{"view_html":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK","download_json":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK.json","view_paper":"https://pith.science/paper/XBQ73J7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08662&json=true","fetch_graph":"https://pith.science/api/pith-number/XBQ73J7SZIC23HLM2BGKUCQFRK/graph.json","fetch_events":"https://pith.science/api/pith-number/XBQ73J7SZIC23HLM2BGKUCQFRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK/action/storage_attestation","attest_author":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK/action/author_attestation","sign_citation":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK/action/citation_signature","submit_replication":"https://pith.science/pith/XBQ73J7SZIC23HLM2BGKUCQFRK/action/replication_record"}},"created_at":"2026-07-05T07:24:07.681844+00:00","updated_at":"2026-07-05T07:24:07.681844+00:00"}