{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WON7V7VSPVG5HQPEWVGZHXOSRS","short_pith_number":"pith:WON7V7VS","schema_version":"1.0","canonical_sha256":"b39bfafeb27d4dd3c1e4b54d93ddd28c8218dfb762cde02de6cc49abbaf725da","source":{"kind":"arxiv","id":"2207.00429","version":1},"attestation_state":"computed","paper":{"title":"Modular Lifelong Reinforcement Learning via Neural Composition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Eaton, Harm van Seijen, Jorge A. Mendez","submitted_at":"2022-07-01T13:48:29Z","abstract_excerpt":"Humans commonly solve complex problems by decomposing them into easier subproblems and then combining the subproblem solutions. This type of compositional reasoning permits reuse of the subproblem solutions when tackling future tasks that share part of the underlying compositional structure. In a continual or lifelong reinforcement learning (RL) setting, this ability to decompose knowledge into reusable components would enable agents to quickly learn new RL tasks by leveraging accumulated compositional structures. We explore a particular form of composition based on neural modules and present "},"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":"2207.00429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-01T13:48:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76486a74f6e9b2a210e6ee1c052282eff7ae3aae840b8b49a0db99baa1a6d6d9","abstract_canon_sha256":"1981332e9fa98c9391138ffa5cf9b239d9399a2ef4ad4a040959a99a6f6ba266"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:42.876746Z","signature_b64":"hZfsmnYrJeQV/wc+w60tB+oO4+hZW6jAXbUufZYZ3/SBvh51XAUJHE+CEiST9UF70k5dcnAgtJ5OrWJvJoT5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b39bfafeb27d4dd3c1e4b54d93ddd28c8218dfb762cde02de6cc49abbaf725da","last_reissued_at":"2026-07-05T04:36:42.876379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:42.876379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modular Lifelong Reinforcement Learning via Neural Composition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Eaton, Harm van Seijen, Jorge A. Mendez","submitted_at":"2022-07-01T13:48:29Z","abstract_excerpt":"Humans commonly solve complex problems by decomposing them into easier subproblems and then combining the subproblem solutions. This type of compositional reasoning permits reuse of the subproblem solutions when tackling future tasks that share part of the underlying compositional structure. In a continual or lifelong reinforcement learning (RL) setting, this ability to decompose knowledge into reusable components would enable agents to quickly learn new RL tasks by leveraging accumulated compositional structures. We explore a particular form of composition based on neural modules and present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00429","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/2207.00429/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":"2207.00429","created_at":"2026-07-05T04:36:42.876428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00429v1","created_at":"2026-07-05T04:36:42.876428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00429","created_at":"2026-07-05T04:36:42.876428+00:00"},{"alias_kind":"pith_short_12","alias_value":"WON7V7VSPVG5","created_at":"2026-07-05T04:36:42.876428+00:00"},{"alias_kind":"pith_short_16","alias_value":"WON7V7VSPVG5HQPE","created_at":"2026-07-05T04:36:42.876428+00:00"},{"alias_kind":"pith_short_8","alias_value":"WON7V7VS","created_at":"2026-07-05T04:36:42.876428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00188","citing_title":"LIMAO: A Framework for Lifelong Modular Learned Query Optimization","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS","json":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS.json","graph_json":"https://pith.science/api/pith-number/WON7V7VSPVG5HQPEWVGZHXOSRS/graph.json","events_json":"https://pith.science/api/pith-number/WON7V7VSPVG5HQPEWVGZHXOSRS/events.json","paper":"https://pith.science/paper/WON7V7VS"},"agent_actions":{"view_html":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS","download_json":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS.json","view_paper":"https://pith.science/paper/WON7V7VS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00429&json=true","fetch_graph":"https://pith.science/api/pith-number/WON7V7VSPVG5HQPEWVGZHXOSRS/graph.json","fetch_events":"https://pith.science/api/pith-number/WON7V7VSPVG5HQPEWVGZHXOSRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS/action/storage_attestation","attest_author":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS/action/author_attestation","sign_citation":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS/action/citation_signature","submit_replication":"https://pith.science/pith/WON7V7VSPVG5HQPEWVGZHXOSRS/action/replication_record"}},"created_at":"2026-07-05T04:36:42.876428+00:00","updated_at":"2026-07-05T04:36:42.876428+00:00"}