{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:INDOHHM2MGOQ5J5IYNFFLOVE6S","short_pith_number":"pith:INDOHHM2","schema_version":"1.0","canonical_sha256":"4346e39d9a619d0ea7a8c34a55baa4f4a2541d5c6eb9c2b3facb31131b8f9c27","source":{"kind":"arxiv","id":"2310.15709","version":2},"attestation_state":"computed","paper":{"title":"Causal Representation Learning Made Identifiable by Grouping of Observational Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aapo Hyv\\\"arinen, Hiroshi Morioka","submitted_at":"2023-10-24T10:38:02Z","abstract_excerpt":"A topic of great current interest is Causal Representation Learning (CRL), whose goal is to learn a causal model for hidden features in a data-driven manner. Unfortunately, CRL is severely ill-posed since it is a combination of the two notoriously ill-posed problems of representation learning and causal discovery. Yet, finding practical identifiability conditions that guarantee a unique solution is crucial for its practical applicability. Most approaches so far have been based on assumptions on the latent causal mechanisms, such as temporal causality, or existence of supervision or interventio"},"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":"2310.15709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-24T10:38:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19cbb81fae18837b2bd13cdf11cc4fb6d1a0c9221cbb98ccc018e5cc3e5fea34","abstract_canon_sha256":"b25def3a4869e4e022c02b7dd6e059141abb63591c9eeb9b17d37158f7213235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:34.567205Z","signature_b64":"djWwl/MMb/chKV6zdhniR/GYJ1yHvsx7oLEYpbAiwBGasm2QiEC2X8m0SXUdAyIaU0wWY4w+GQkE5hWCd6YOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4346e39d9a619d0ea7a8c34a55baa4f4a2541d5c6eb9c2b3facb31131b8f9c27","last_reissued_at":"2026-07-05T08:28:34.566797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:34.566797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Representation Learning Made Identifiable by Grouping of Observational Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aapo Hyv\\\"arinen, Hiroshi Morioka","submitted_at":"2023-10-24T10:38:02Z","abstract_excerpt":"A topic of great current interest is Causal Representation Learning (CRL), whose goal is to learn a causal model for hidden features in a data-driven manner. Unfortunately, CRL is severely ill-posed since it is a combination of the two notoriously ill-posed problems of representation learning and causal discovery. Yet, finding practical identifiability conditions that guarantee a unique solution is crucial for its practical applicability. Most approaches so far have been based on assumptions on the latent causal mechanisms, such as temporal causality, or existence of supervision or interventio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15709","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/2310.15709/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":"2310.15709","created_at":"2026-07-05T08:28:34.566852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15709v2","created_at":"2026-07-05T08:28:34.566852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15709","created_at":"2026-07-05T08:28:34.566852+00:00"},{"alias_kind":"pith_short_12","alias_value":"INDOHHM2MGOQ","created_at":"2026-07-05T08:28:34.566852+00:00"},{"alias_kind":"pith_short_16","alias_value":"INDOHHM2MGOQ5J5I","created_at":"2026-07-05T08:28:34.566852+00:00"},{"alias_kind":"pith_short_8","alias_value":"INDOHHM2","created_at":"2026-07-05T08:28:34.566852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00267","citing_title":"Validating Causal Abstraction Metrics on Simulated Complex Systems","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00858","citing_title":"MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S","json":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S.json","graph_json":"https://pith.science/api/pith-number/INDOHHM2MGOQ5J5IYNFFLOVE6S/graph.json","events_json":"https://pith.science/api/pith-number/INDOHHM2MGOQ5J5IYNFFLOVE6S/events.json","paper":"https://pith.science/paper/INDOHHM2"},"agent_actions":{"view_html":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S","download_json":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S.json","view_paper":"https://pith.science/paper/INDOHHM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15709&json=true","fetch_graph":"https://pith.science/api/pith-number/INDOHHM2MGOQ5J5IYNFFLOVE6S/graph.json","fetch_events":"https://pith.science/api/pith-number/INDOHHM2MGOQ5J5IYNFFLOVE6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S/action/storage_attestation","attest_author":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S/action/author_attestation","sign_citation":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S/action/citation_signature","submit_replication":"https://pith.science/pith/INDOHHM2MGOQ5J5IYNFFLOVE6S/action/replication_record"}},"created_at":"2026-07-05T08:28:34.566852+00:00","updated_at":"2026-07-05T08:28:34.566852+00:00"}