{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B2U5NJNSUNQLCHWMCIQPWR6X4Z","short_pith_number":"pith:B2U5NJNS","schema_version":"1.0","canonical_sha256":"0ea9d6a5b2a360b11ecc1220fb47d7e67853c982197d54752f6e3bebe135cbca","source":{"kind":"arxiv","id":"2006.16225","version":5},"attestation_state":"computed","paper":{"title":"Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lamb, Anirudh Goyal, Charles Blundell, Michael Mozer, Phanideep Gampa, Philippe Beaudoin, Sergey Levine, Yoshua Bengio","submitted_at":"2020-06-29T17:45:03Z","abstract_excerpt":"Modeling a structured, dynamic environment like a video game requires keeping track of the objects and their states declarative knowledge) as well as predicting how objects behave (procedural knowledge). Black-box models with a monolithic hidden state often fail to apply procedural knowledge consistently and uniformly, i.e., they lack systematicity. For example, in a video game, correct prediction of one enemy's trajectory does not ensure correct prediction of another's. We address this issue via an architecture that factorizes declarative and procedural knowledge and that imposes modularity w"},"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":"2006.16225","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T17:45:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b332c91383b35d5ba5c313d9cddc04c886590132e9c704cf510eb5bb1c65eff0","abstract_canon_sha256":"7a7d1666345c51058c2e93bb68f269a837bd392d3581e2224801a6d84d210c71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:20.001706Z","signature_b64":"ourat5bGiD7zVm5CsWR+DYQIgFSU5OmYJe1rxAwNu3tEF8kZnjCfQg2cWdQgARTqJ671IlsRFr6eG5RU1pWUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ea9d6a5b2a360b11ecc1220fb47d7e67853c982197d54752f6e3bebe135cbca","last_reissued_at":"2026-07-05T01:51:20.001239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:20.001239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lamb, Anirudh Goyal, Charles Blundell, Michael Mozer, Phanideep Gampa, Philippe Beaudoin, Sergey Levine, Yoshua Bengio","submitted_at":"2020-06-29T17:45:03Z","abstract_excerpt":"Modeling a structured, dynamic environment like a video game requires keeping track of the objects and their states declarative knowledge) as well as predicting how objects behave (procedural knowledge). Black-box models with a monolithic hidden state often fail to apply procedural knowledge consistently and uniformly, i.e., they lack systematicity. For example, in a video game, correct prediction of one enemy's trajectory does not ensure correct prediction of another's. We address this issue via an architecture that factorizes declarative and procedural knowledge and that imposes modularity w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16225","kind":"arxiv","version":5},"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/2006.16225/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":"2006.16225","created_at":"2026-07-05T01:51:20.001293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16225v5","created_at":"2026-07-05T01:51:20.001293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16225","created_at":"2026-07-05T01:51:20.001293+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2U5NJNSUNQL","created_at":"2026-07-05T01:51:20.001293+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2U5NJNSUNQLCHWM","created_at":"2026-07-05T01:51:20.001293+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2U5NJNS","created_at":"2026-07-05T01:51:20.001293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08708","citing_title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":278,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z","json":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z.json","graph_json":"https://pith.science/api/pith-number/B2U5NJNSUNQLCHWMCIQPWR6X4Z/graph.json","events_json":"https://pith.science/api/pith-number/B2U5NJNSUNQLCHWMCIQPWR6X4Z/events.json","paper":"https://pith.science/paper/B2U5NJNS"},"agent_actions":{"view_html":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z","download_json":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z.json","view_paper":"https://pith.science/paper/B2U5NJNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16225&json=true","fetch_graph":"https://pith.science/api/pith-number/B2U5NJNSUNQLCHWMCIQPWR6X4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/B2U5NJNSUNQLCHWMCIQPWR6X4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z/action/storage_attestation","attest_author":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z/action/author_attestation","sign_citation":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z/action/citation_signature","submit_replication":"https://pith.science/pith/B2U5NJNSUNQLCHWMCIQPWR6X4Z/action/replication_record"}},"created_at":"2026-07-05T01:51:20.001293+00:00","updated_at":"2026-07-05T01:51:20.001293+00:00"}