{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TNNDX6WBFVC4IQBOYKWHGX4OQ4","short_pith_number":"pith:TNNDX6WB","schema_version":"1.0","canonical_sha256":"9b5a3bfac12d45c4402ec2ac735f8e871471b141bc7a2aee238d512c88c5d069","source":{"kind":"arxiv","id":"2311.18048","version":2},"attestation_state":"computed","paper":{"title":"An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.SY","eess.SY","stat.ME"],"primary_cat":"cs.LG","authors_text":"Goutham Rajendran, Patrik Reizinger, Pradeep Ravikumar, Wieland Brendel","submitted_at":"2023-11-29T19:51:35Z","abstract_excerpt":"We investigate the relationship between system identification and intervention design in dynamical systems. While previous research demonstrated how identifiable representation learning methods, such as Independent Component Analysis (ICA), can reveal cause-effect relationships, it relied on a passive perspective without considering how to collect data. Our work shows that in Gaussian Linear Time-Invariant (LTI) systems, the system parameters can be identified by introducing diverse intervention signals in a multi-environment setting. By harnessing appropriate diversity assumptions motivated b"},"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":"2311.18048","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T19:51:35Z","cross_cats_sorted":["cs.CE","cs.SY","eess.SY","stat.ME"],"title_canon_sha256":"4f97151f3dae7e47d841fe59c2a4614c9646aaa52723fb771b4c91a1f9b03168","abstract_canon_sha256":"951947f345b5ccd460bddc12e916ff0bc385a1e933d1a7fc3ea6d7ceddb29fc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:50.840303Z","signature_b64":"YzN6wuDRnpWRWwQ3JfF0m/1cPFzYdgKkM4YDFXMmfHTv4mQed+rA2+iNOsOehjDWrSaQFbst1JIyf670uMRACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b5a3bfac12d45c4402ec2ac735f8e871471b141bc7a2aee238d512c88c5d069","last_reissued_at":"2026-07-05T07:45:50.839721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:50.839721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.SY","eess.SY","stat.ME"],"primary_cat":"cs.LG","authors_text":"Goutham Rajendran, Patrik Reizinger, Pradeep Ravikumar, Wieland Brendel","submitted_at":"2023-11-29T19:51:35Z","abstract_excerpt":"We investigate the relationship between system identification and intervention design in dynamical systems. While previous research demonstrated how identifiable representation learning methods, such as Independent Component Analysis (ICA), can reveal cause-effect relationships, it relied on a passive perspective without considering how to collect data. Our work shows that in Gaussian Linear Time-Invariant (LTI) systems, the system parameters can be identified by introducing diverse intervention signals in a multi-environment setting. By harnessing appropriate diversity assumptions motivated b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18048","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/2311.18048/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":"2311.18048","created_at":"2026-07-05T07:45:50.839839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18048v2","created_at":"2026-07-05T07:45:50.839839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18048","created_at":"2026-07-05T07:45:50.839839+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNNDX6WBFVC4","created_at":"2026-07-05T07:45:50.839839+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNNDX6WBFVC4IQBO","created_at":"2026-07-05T07:45:50.839839+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNNDX6WB","created_at":"2026-07-05T07:45:50.839839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14748","citing_title":"Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4","json":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4.json","graph_json":"https://pith.science/api/pith-number/TNNDX6WBFVC4IQBOYKWHGX4OQ4/graph.json","events_json":"https://pith.science/api/pith-number/TNNDX6WBFVC4IQBOYKWHGX4OQ4/events.json","paper":"https://pith.science/paper/TNNDX6WB"},"agent_actions":{"view_html":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4","download_json":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4.json","view_paper":"https://pith.science/paper/TNNDX6WB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18048&json=true","fetch_graph":"https://pith.science/api/pith-number/TNNDX6WBFVC4IQBOYKWHGX4OQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/TNNDX6WBFVC4IQBOYKWHGX4OQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4/action/storage_attestation","attest_author":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4/action/author_attestation","sign_citation":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4/action/citation_signature","submit_replication":"https://pith.science/pith/TNNDX6WBFVC4IQBOYKWHGX4OQ4/action/replication_record"}},"created_at":"2026-07-05T07:45:50.839839+00:00","updated_at":"2026-07-05T07:45:50.839839+00:00"}