{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CS24ZATWK26EEQWIPJ3XGR5M5M","short_pith_number":"pith:CS24ZATW","schema_version":"1.0","canonical_sha256":"14b5cc827656bc4242c87a777347aceb0baadb5bfaf17034ae66e022e32fcef4","source":{"kind":"arxiv","id":"2310.00229","version":4},"attestation_state":"computed","paper":{"title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Doina Precup, Harm van Seijen, Mingde Zhao, Romain Laroche, Safa Alver, Yoshua Bengio","submitted_at":"2023-09-30T02:25:18Z","abstract_excerpt":"Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations. It automatically decomposes the given task into smaller, more manageable subtasks, and thus enables sparse decision-making and focused computation on the relevant parts of the environment. The decomposition relies on the extraction of an abstracted proxy problem represented as a directed graph, in which vertices and edges are learned end-to-end from hindsight. Our theoretical analyses provide performance guaran"},"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":"2310.00229","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-30T02:25:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d939beea97b723eba85e274f5caf07326df22833f646a54d9f910bc11a32e293","abstract_canon_sha256":"5ebb78a08ceb54af4ed4799b745465f78744adfb69e9683ba46d95ec18b3c8b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:52.896070Z","signature_b64":"nkLcCLkRD4IO6DcKnRUuApytGoOYfmWr9ggfl7FqiGcDUBefN3fV7+N+u2ypofYPAmIYRfk4MOoaVYa5enlbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14b5cc827656bc4242c87a777347aceb0baadb5bfaf17034ae66e022e32fcef4","last_reissued_at":"2026-07-05T07:56:52.895561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:52.895561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Doina Precup, Harm van Seijen, Mingde Zhao, Romain Laroche, Safa Alver, Yoshua Bengio","submitted_at":"2023-09-30T02:25:18Z","abstract_excerpt":"Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations. It automatically decomposes the given task into smaller, more manageable subtasks, and thus enables sparse decision-making and focused computation on the relevant parts of the environment. The decomposition relies on the extraction of an abstracted proxy problem represented as a directed graph, in which vertices and edges are learned end-to-end from hindsight. Our theoretical analyses provide performance guaran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00229","kind":"arxiv","version":4},"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/2310.00229/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":"2310.00229","created_at":"2026-07-05T07:56:52.895620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00229v4","created_at":"2026-07-05T07:56:52.895620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00229","created_at":"2026-07-05T07:56:52.895620+00:00"},{"alias_kind":"pith_short_12","alias_value":"CS24ZATWK26E","created_at":"2026-07-05T07:56:52.895620+00:00"},{"alias_kind":"pith_short_16","alias_value":"CS24ZATWK26EEQWI","created_at":"2026-07-05T07:56:52.895620+00:00"},{"alias_kind":"pith_short_8","alias_value":"CS24ZATW","created_at":"2026-07-05T07:56:52.895620+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/CS24ZATWK26EEQWIPJ3XGR5M5M","json":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M.json","graph_json":"https://pith.science/api/pith-number/CS24ZATWK26EEQWIPJ3XGR5M5M/graph.json","events_json":"https://pith.science/api/pith-number/CS24ZATWK26EEQWIPJ3XGR5M5M/events.json","paper":"https://pith.science/paper/CS24ZATW"},"agent_actions":{"view_html":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M","download_json":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M.json","view_paper":"https://pith.science/paper/CS24ZATW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00229&json=true","fetch_graph":"https://pith.science/api/pith-number/CS24ZATWK26EEQWIPJ3XGR5M5M/graph.json","fetch_events":"https://pith.science/api/pith-number/CS24ZATWK26EEQWIPJ3XGR5M5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M/action/storage_attestation","attest_author":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M/action/author_attestation","sign_citation":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M/action/citation_signature","submit_replication":"https://pith.science/pith/CS24ZATWK26EEQWIPJ3XGR5M5M/action/replication_record"}},"created_at":"2026-07-05T07:56:52.895620+00:00","updated_at":"2026-07-05T07:56:52.895620+00:00"}