{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7ELTZPYFN3HMYRHWB4NCGQYB4V","short_pith_number":"pith:7ELTZPYF","schema_version":"1.0","canonical_sha256":"f9173cbf056ececc44f60f1a234301e552e0be6a19032c36e9fd2cf2fe33f0d1","source":{"kind":"arxiv","id":"2106.09620","version":2},"attestation_state":"computed","paper":{"title":"Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aapo Hyvarinen, Elisabeth Gassiat, Hermanni H\\\"alv\\\"a, Jonathan So, Luc Leh\\'ericy, Sylvain Le Corff, Yongjie Zhu","submitted_at":"2021-06-17T15:56:57Z","abstract_excerpt":"We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA). Our contribution is to extend the identifiability theory of deep generative models for a very broad class of structured models. While previous works have shown identifiability for specific classes of time-series models, our theorems extend this to more general temporal structures as well as to models with more complex structures such as spatial dependencies. In particular, we establish the major result that identifiability for this framewo"},"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":"2106.09620","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-17T15:56:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f12a2a43b61161963e262fb459a28b29a703880ea1bee844d76460a3e6af9e76","abstract_canon_sha256":"668e0923e5822c3a70bce8891f26f896eeee78c9c1c39d89f2c0bf451fcf3cde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:18.522032Z","signature_b64":"THiEruLOJ5ZPUuBhkGlLktrnatvgprSADUVbhNseCSi4vWGYwqCodD59nFHuG0KXY8Gz6uSiuWKdXM3jrKSQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9173cbf056ececc44f60f1a234301e552e0be6a19032c36e9fd2cf2fe33f0d1","last_reissued_at":"2026-07-05T03:26:18.521633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:18.521633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aapo Hyvarinen, Elisabeth Gassiat, Hermanni H\\\"alv\\\"a, Jonathan So, Luc Leh\\'ericy, Sylvain Le Corff, Yongjie Zhu","submitted_at":"2021-06-17T15:56:57Z","abstract_excerpt":"We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA). Our contribution is to extend the identifiability theory of deep generative models for a very broad class of structured models. While previous works have shown identifiability for specific classes of time-series models, our theorems extend this to more general temporal structures as well as to models with more complex structures such as spatial dependencies. In particular, we establish the major result that identifiability for this framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09620","kind":"arxiv","version":2},"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/2106.09620/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":"2106.09620","created_at":"2026-07-05T03:26:18.521690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09620v2","created_at":"2026-07-05T03:26:18.521690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09620","created_at":"2026-07-05T03:26:18.521690+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ELTZPYFN3HM","created_at":"2026-07-05T03:26:18.521690+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ELTZPYFN3HMYRHW","created_at":"2026-07-05T03:26:18.521690+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ELTZPYF","created_at":"2026-07-05T03:26:18.521690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13260","citing_title":"Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V","json":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V.json","graph_json":"https://pith.science/api/pith-number/7ELTZPYFN3HMYRHWB4NCGQYB4V/graph.json","events_json":"https://pith.science/api/pith-number/7ELTZPYFN3HMYRHWB4NCGQYB4V/events.json","paper":"https://pith.science/paper/7ELTZPYF"},"agent_actions":{"view_html":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V","download_json":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V.json","view_paper":"https://pith.science/paper/7ELTZPYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09620&json=true","fetch_graph":"https://pith.science/api/pith-number/7ELTZPYFN3HMYRHWB4NCGQYB4V/graph.json","fetch_events":"https://pith.science/api/pith-number/7ELTZPYFN3HMYRHWB4NCGQYB4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V/action/storage_attestation","attest_author":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V/action/author_attestation","sign_citation":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V/action/citation_signature","submit_replication":"https://pith.science/pith/7ELTZPYFN3HMYRHWB4NCGQYB4V/action/replication_record"}},"created_at":"2026-07-05T03:26:18.521690+00:00","updated_at":"2026-07-05T03:26:18.521690+00:00"}