{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2R5UMCTQAQOVLX2PM5YELGU7HY","short_pith_number":"pith:2R5UMCTQ","schema_version":"1.0","canonical_sha256":"d47b460a70041d55df4f6770459a9f3e1fba541b14f5a76d6b4f92fdf9770b36","source":{"kind":"arxiv","id":"2303.17264","version":1},"attestation_state":"computed","paper":{"title":"Multifactor Sequential Disentanglement via Structured Koopman Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilan Naiman, Nimrod Berman, Omri Azencot","submitted_at":"2023-03-30T10:01:58Z","abstract_excerpt":"Disentangling complex data to its latent factors of variation is a fundamental task in representation learning. Existing work on sequential disentanglement mostly provides two factor representations, i.e., it separates the data to time-varying and time-invariant factors. In contrast, we consider multifactor disentanglement in which multiple (more than two) semantic disentangled components are generated. Key to our approach is a strong inductive bias where we assume that the underlying dynamics can be represented linearly in the latent space. Under this assumption, it becomes natural to exploit"},"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":"2303.17264","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-30T10:01:58Z","cross_cats_sorted":[],"title_canon_sha256":"33f9ec10c3fe5c02ba720edbc9c633a729578396e7e637f3a8c48e941019cea2","abstract_canon_sha256":"c9ea816161615c518a04f5ffbf7a02ccc0608dd1f2f05a20b1d6984198baf597"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:32.184883Z","signature_b64":"P5k+CTJtKhak7OMkD/b21lImBzdu9I4btoLcu5AtWFIzHfu01lLw1nuZ9Zm5MwMLyJCpJ8HEvAG/cjmBMZzJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d47b460a70041d55df4f6770459a9f3e1fba541b14f5a76d6b4f92fdf9770b36","last_reissued_at":"2026-07-05T05:56:32.184433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:32.184433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multifactor Sequential Disentanglement via Structured Koopman Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilan Naiman, Nimrod Berman, Omri Azencot","submitted_at":"2023-03-30T10:01:58Z","abstract_excerpt":"Disentangling complex data to its latent factors of variation is a fundamental task in representation learning. Existing work on sequential disentanglement mostly provides two factor representations, i.e., it separates the data to time-varying and time-invariant factors. In contrast, we consider multifactor disentanglement in which multiple (more than two) semantic disentangled components are generated. Key to our approach is a strong inductive bias where we assume that the underlying dynamics can be represented linearly in the latent space. Under this assumption, it becomes natural to exploit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17264","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/2303.17264/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":"2303.17264","created_at":"2026-07-05T05:56:32.184492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17264v1","created_at":"2026-07-05T05:56:32.184492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17264","created_at":"2026-07-05T05:56:32.184492+00:00"},{"alias_kind":"pith_short_12","alias_value":"2R5UMCTQAQOV","created_at":"2026-07-05T05:56:32.184492+00:00"},{"alias_kind":"pith_short_16","alias_value":"2R5UMCTQAQOVLX2P","created_at":"2026-07-05T05:56:32.184492+00:00"},{"alias_kind":"pith_short_8","alias_value":"2R5UMCTQ","created_at":"2026-07-05T05:56:32.184492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08376","citing_title":"Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY","json":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY.json","graph_json":"https://pith.science/api/pith-number/2R5UMCTQAQOVLX2PM5YELGU7HY/graph.json","events_json":"https://pith.science/api/pith-number/2R5UMCTQAQOVLX2PM5YELGU7HY/events.json","paper":"https://pith.science/paper/2R5UMCTQ"},"agent_actions":{"view_html":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY","download_json":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY.json","view_paper":"https://pith.science/paper/2R5UMCTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17264&json=true","fetch_graph":"https://pith.science/api/pith-number/2R5UMCTQAQOVLX2PM5YELGU7HY/graph.json","fetch_events":"https://pith.science/api/pith-number/2R5UMCTQAQOVLX2PM5YELGU7HY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY/action/storage_attestation","attest_author":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY/action/author_attestation","sign_citation":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY/action/citation_signature","submit_replication":"https://pith.science/pith/2R5UMCTQAQOVLX2PM5YELGU7HY/action/replication_record"}},"created_at":"2026-07-05T05:56:32.184492+00:00","updated_at":"2026-07-05T05:56:32.184492+00:00"}