{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3XXC345LBRVEYFUHHVYLUVRT33","short_pith_number":"pith:3XXC345L","schema_version":"1.0","canonical_sha256":"ddee2df3ab0c6a4c16873d70ba5633def87b1ff243e921e64f1ec3576e7c1fee","source":{"kind":"arxiv","id":"2407.09533","version":1},"attestation_state":"computed","paper":{"title":"Video Occupancy Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Lamb, John Langford, Manan Tomar, Matthew E. Taylor, Philip Bachman, Philippe Hansen-Estruch, Sergey Levine","submitted_at":"2024-06-25T17:57:38Z","abstract_excerpt":"We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual pixels. Unlike prior latent-space world models, VOCs directly predict the discounted distribution of future states in a single step, thus avoiding the need for multistep roll-outs. We show that both properties are beneficial when building predictive models of video for use in downstream control. Code is available at \\href{https://github.com/manant"},"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":"2407.09533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:57:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d005b7a93841de36c3d88802024e8431d6f1f77e368f07fddecfa9edd2ed286","abstract_canon_sha256":"f4c38bdca35a624c297ceb5f487b181026c8a4c5a40988003f662e406a4af09a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:31.932029Z","signature_b64":"64ZgDMEONR933eLBNd+YEtq+iaDsqTLd9Z8UeZWzHpY8L+4s+nVLanr0dS+xFXwz90pqfCzU6QE2cC/AzHsVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddee2df3ab0c6a4c16873d70ba5633def87b1ff243e921e64f1ec3576e7c1fee","last_reissued_at":"2026-07-05T08:43:31.931614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:31.931614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Occupancy Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Lamb, John Langford, Manan Tomar, Matthew E. Taylor, Philip Bachman, Philippe Hansen-Estruch, Sergey Levine","submitted_at":"2024-06-25T17:57:38Z","abstract_excerpt":"We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual pixels. Unlike prior latent-space world models, VOCs directly predict the discounted distribution of future states in a single step, thus avoiding the need for multistep roll-outs. We show that both properties are beneficial when building predictive models of video for use in downstream control. Code is available at \\href{https://github.com/manant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09533","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/2407.09533/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":"2407.09533","created_at":"2026-07-05T08:43:31.931668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09533v1","created_at":"2026-07-05T08:43:31.931668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09533","created_at":"2026-07-05T08:43:31.931668+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XXC345LBRVE","created_at":"2026-07-05T08:43:31.931668+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XXC345LBRVEYFUH","created_at":"2026-07-05T08:43:31.931668+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XXC345L","created_at":"2026-07-05T08:43:31.931668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.08902","citing_title":"Intention-Conditioned Flow Occupancy Models","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09985","citing_title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33","json":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33.json","graph_json":"https://pith.science/api/pith-number/3XXC345LBRVEYFUHHVYLUVRT33/graph.json","events_json":"https://pith.science/api/pith-number/3XXC345LBRVEYFUHHVYLUVRT33/events.json","paper":"https://pith.science/paper/3XXC345L"},"agent_actions":{"view_html":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33","download_json":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33.json","view_paper":"https://pith.science/paper/3XXC345L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09533&json=true","fetch_graph":"https://pith.science/api/pith-number/3XXC345LBRVEYFUHHVYLUVRT33/graph.json","fetch_events":"https://pith.science/api/pith-number/3XXC345LBRVEYFUHHVYLUVRT33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33/action/storage_attestation","attest_author":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33/action/author_attestation","sign_citation":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33/action/citation_signature","submit_replication":"https://pith.science/pith/3XXC345LBRVEYFUHHVYLUVRT33/action/replication_record"}},"created_at":"2026-07-05T08:43:31.931668+00:00","updated_at":"2026-07-05T08:43:31.931668+00:00"}