{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GA7D3C5BYGQUSEA7YQAN2LJLRP","short_pith_number":"pith:GA7D3C5B","schema_version":"1.0","canonical_sha256":"303e3d8ba1c1a149101fc400dd2d2b8bf57216cd86176cdfc1c9c0047a609955","source":{"kind":"arxiv","id":"2403.08335","version":2},"attestation_state":"computed","paper":{"title":"A Sparsity Principle for Partially Observable Causal Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Danru Xu, Dingling Yao, Francesco Locatello, Julius von K\\\"ugelgen, Perouz Taslakian, Sara Magliacane, S\\'ebastien Lachapelle","submitted_at":"2024-03-13T08:40:49Z","abstract_excerpt":"Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all latent causal variables are captured in the high-dimensional observations. We instead consider a partially observed setting, in which each measurement only provides information about a subset of the underlying causal state. Prior work has studied this setting with multiple domains or views, each depending on a fixed subset of latents. Here, we focus on learning from unpaired observations from a dataset with an instance-dependent partial observability pattern. Our ma"},"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":"2403.08335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-13T08:40:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"72b8185ccb167bc749874d302877501c986f8735a46c0d0fe67bbc6fdd1397fe","abstract_canon_sha256":"bf74b995df7b56efda32c4134f31cb0e9378aaf02d165ebe98ad309aca3ddfd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:11.928370Z","signature_b64":"eag/5YJIcxRMqiDsNF9BMarHH/4CRXeQQEtgYcUydsyHAt0N+uoa2kvjUkzGgX55iNALXWrs5ifsOM0TGr/jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"303e3d8ba1c1a149101fc400dd2d2b8bf57216cd86176cdfc1c9c0047a609955","last_reissued_at":"2026-07-05T08:32:11.927887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:11.927887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sparsity Principle for Partially Observable Causal Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Danru Xu, Dingling Yao, Francesco Locatello, Julius von K\\\"ugelgen, Perouz Taslakian, Sara Magliacane, S\\'ebastien Lachapelle","submitted_at":"2024-03-13T08:40:49Z","abstract_excerpt":"Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all latent causal variables are captured in the high-dimensional observations. We instead consider a partially observed setting, in which each measurement only provides information about a subset of the underlying causal state. Prior work has studied this setting with multiple domains or views, each depending on a fixed subset of latents. Here, we focus on learning from unpaired observations from a dataset with an instance-dependent partial observability pattern. Our ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08335","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/2403.08335/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":"2403.08335","created_at":"2026-07-05T08:32:11.927938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08335v2","created_at":"2026-07-05T08:32:11.927938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08335","created_at":"2026-07-05T08:32:11.927938+00:00"},{"alias_kind":"pith_short_12","alias_value":"GA7D3C5BYGQU","created_at":"2026-07-05T08:32:11.927938+00:00"},{"alias_kind":"pith_short_16","alias_value":"GA7D3C5BYGQUSEA7","created_at":"2026-07-05T08:32:11.927938+00:00"},{"alias_kind":"pith_short_8","alias_value":"GA7D3C5B","created_at":"2026-07-05T08:32:11.927938+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21385","citing_title":"Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00858","citing_title":"MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP","json":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP.json","graph_json":"https://pith.science/api/pith-number/GA7D3C5BYGQUSEA7YQAN2LJLRP/graph.json","events_json":"https://pith.science/api/pith-number/GA7D3C5BYGQUSEA7YQAN2LJLRP/events.json","paper":"https://pith.science/paper/GA7D3C5B"},"agent_actions":{"view_html":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP","download_json":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP.json","view_paper":"https://pith.science/paper/GA7D3C5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08335&json=true","fetch_graph":"https://pith.science/api/pith-number/GA7D3C5BYGQUSEA7YQAN2LJLRP/graph.json","fetch_events":"https://pith.science/api/pith-number/GA7D3C5BYGQUSEA7YQAN2LJLRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP/action/storage_attestation","attest_author":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP/action/author_attestation","sign_citation":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP/action/citation_signature","submit_replication":"https://pith.science/pith/GA7D3C5BYGQUSEA7YQAN2LJLRP/action/replication_record"}},"created_at":"2026-07-05T08:32:11.927938+00:00","updated_at":"2026-07-05T08:32:11.927938+00:00"}