{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PVRCCZYZXYDWUZWJN7NPT2SGI6","short_pith_number":"pith:PVRCCZYZ","schema_version":"1.0","canonical_sha256":"7d62216719be076a66c96fdaf9ea46478bee3bfbec9e8a42c6d67041e7468607","source":{"kind":"arxiv","id":"2501.14174","version":5},"attestation_state":"computed","paper":{"title":"Dreamweaver: Learning Compositional World Models from Pixels","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gautam Singh, Junyeob Baek, Sungjin Ahn, Yi-Fu Wu","submitted_at":"2025-01-24T01:50:19Z","abstract_excerpt":"Humans have an innate ability to decompose their perceptions of the world into objects and their attributes, such as colors, shapes, and movement patterns. This cognitive process enables us to imagine novel futures by recombining familiar concepts. However, replicating this ability in artificial intelligence systems has proven challenging, particularly when it comes to modeling videos into compositional concepts and generating unseen, recomposed futures without relying on auxiliary data, such as text, masks, or bounding boxes. In this paper, we propose Dreamweaver, a neural architecture design"},"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":"2501.14174","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T01:50:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"515b112635cad53a424adc96e3c402e39c756c335636f2698479bd75c408e37b","abstract_canon_sha256":"80467aed0b575a8d4fc6eab3d07242ce13a6b0469dcf2363359a82b52b8bb5d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:00.043884Z","signature_b64":"mCzbwRRZviYx+6/LApJ5TWTKNa51eG/vZdEoKeK5j51RK3SPn1Dk/uVCYRLu6ZfaoXZa5uuSqtxXpT4b1x4gBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d62216719be076a66c96fdaf9ea46478bee3bfbec9e8a42c6d67041e7468607","last_reissued_at":"2026-07-05T10:47:00.043398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:00.043398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dreamweaver: Learning Compositional World Models from Pixels","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gautam Singh, Junyeob Baek, Sungjin Ahn, Yi-Fu Wu","submitted_at":"2025-01-24T01:50:19Z","abstract_excerpt":"Humans have an innate ability to decompose their perceptions of the world into objects and their attributes, such as colors, shapes, and movement patterns. This cognitive process enables us to imagine novel futures by recombining familiar concepts. However, replicating this ability in artificial intelligence systems has proven challenging, particularly when it comes to modeling videos into compositional concepts and generating unseen, recomposed futures without relying on auxiliary data, such as text, masks, or bounding boxes. In this paper, we propose Dreamweaver, a neural architecture design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14174","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/2501.14174/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":"2501.14174","created_at":"2026-07-05T10:47:00.043455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14174v5","created_at":"2026-07-05T10:47:00.043455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14174","created_at":"2026-07-05T10:47:00.043455+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVRCCZYZXYDW","created_at":"2026-07-05T10:47:00.043455+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVRCCZYZXYDWUZWJ","created_at":"2026-07-05T10:47:00.043455+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVRCCZYZ","created_at":"2026-07-05T10:47:00.043455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.02193","citing_title":"From monoliths to modules: Decomposing transducers for efficient world modelling","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6","json":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6.json","graph_json":"https://pith.science/api/pith-number/PVRCCZYZXYDWUZWJN7NPT2SGI6/graph.json","events_json":"https://pith.science/api/pith-number/PVRCCZYZXYDWUZWJN7NPT2SGI6/events.json","paper":"https://pith.science/paper/PVRCCZYZ"},"agent_actions":{"view_html":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6","download_json":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6.json","view_paper":"https://pith.science/paper/PVRCCZYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14174&json=true","fetch_graph":"https://pith.science/api/pith-number/PVRCCZYZXYDWUZWJN7NPT2SGI6/graph.json","fetch_events":"https://pith.science/api/pith-number/PVRCCZYZXYDWUZWJN7NPT2SGI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6/action/storage_attestation","attest_author":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6/action/author_attestation","sign_citation":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6/action/citation_signature","submit_replication":"https://pith.science/pith/PVRCCZYZXYDWUZWJN7NPT2SGI6/action/replication_record"}},"created_at":"2026-07-05T10:47:00.043455+00:00","updated_at":"2026-07-05T10:47:00.043455+00:00"}