{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WQ65JJEEXJZJKNTM6JSHQ642YD","short_pith_number":"pith:WQ65JJEE","schema_version":"1.0","canonical_sha256":"b43dd4a484ba7295366cf264787b9ac0cb0ee4729473af202a021eb8d8daf6ba","source":{"kind":"arxiv","id":"2603.14483","version":2},"attestation_state":"computed","paper":{"title":"Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anson Lei, Ingmar Posner, Joe Watson, Markus W. Baumgartner","submitted_at":"2026-03-15T17:03:34Z","abstract_excerpt":"Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a predefined library of candidate functions chosen via available domain knowledge. In contrast, deep learning can demonstrably model systems of broad complexity with high fidelity, but black-box function approximation typically fails to yield explicit descriptive or disentangled representations revealing the structure of a system. We develop a novel identifiability theorem, leveraging"},"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":"2603.14483","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-15T17:03:34Z","cross_cats_sorted":[],"title_canon_sha256":"845139495665c26802e92ba3d50d797dbe004902ac8cfbe42016d9785ea0f53c","abstract_canon_sha256":"a0f30532c88227eaee475b23619fac89df756d4eed96735b0bd382c714f2f473"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:25.072493Z","signature_b64":"LoXtHHQEj4Blm3itTGzbdNIyKLuTpEd95b8YvBoVZvYh4k41DqQPJOXnfM1aJvyycI4vr4OwlqTx8h1kzQWqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43dd4a484ba7295366cf264787b9ac0cb0ee4729473af202a021eb8d8daf6ba","last_reissued_at":"2026-06-12T01:09:25.072011Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:25.072011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anson Lei, Ingmar Posner, Joe Watson, Markus W. Baumgartner","submitted_at":"2026-03-15T17:03:34Z","abstract_excerpt":"Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a predefined library of candidate functions chosen via available domain knowledge. In contrast, deep learning can demonstrably model systems of broad complexity with high fidelity, but black-box function approximation typically fails to yield explicit descriptive or disentangled representations revealing the structure of a system. We develop a novel identifiability theorem, leveraging"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14483","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/2603.14483/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":"2603.14483","created_at":"2026-06-12T01:09:25.072066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14483v2","created_at":"2026-06-12T01:09:25.072066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14483","created_at":"2026-06-12T01:09:25.072066+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ65JJEEXJZJ","created_at":"2026-06-12T01:09:25.072066+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ65JJEEXJZJKNTM","created_at":"2026-06-12T01:09:25.072066+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ65JJEE","created_at":"2026-06-12T01:09:25.072066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.28228","citing_title":"Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22248","citing_title":"No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation","ref_index":79,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD","json":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD.json","graph_json":"https://pith.science/api/pith-number/WQ65JJEEXJZJKNTM6JSHQ642YD/graph.json","events_json":"https://pith.science/api/pith-number/WQ65JJEEXJZJKNTM6JSHQ642YD/events.json","paper":"https://pith.science/paper/WQ65JJEE"},"agent_actions":{"view_html":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD","download_json":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD.json","view_paper":"https://pith.science/paper/WQ65JJEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14483&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ65JJEEXJZJKNTM6JSHQ642YD/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ65JJEEXJZJKNTM6JSHQ642YD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD/action/storage_attestation","attest_author":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD/action/author_attestation","sign_citation":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD/action/citation_signature","submit_replication":"https://pith.science/pith/WQ65JJEEXJZJKNTM6JSHQ642YD/action/replication_record"}},"created_at":"2026-06-12T01:09:25.072066+00:00","updated_at":"2026-06-12T01:09:25.072066+00:00"}