{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VLFN7WYSTJILT5RQXAE6FISJFY","short_pith_number":"pith:VLFN7WYS","schema_version":"1.0","canonical_sha256":"aacadfdb129a50b9f630b809e2a2492e0863e7b1c3fa20d52ac481f7265eb5e5","source":{"kind":"arxiv","id":"2401.04890","version":1},"attestation_state":"computed","paper":{"title":"Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre Lacoste, Katie Everett, Pau Rodr\\'iguez L\\'opez, R\\'emi Le Priol, S\\'ebastien Lachapelle, Simon Lacoste-Julien, Yash Sharma","submitted_at":"2024-01-10T02:38:21Z","abstract_excerpt":"This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors and the sparse causal graphical model that explains them. We develop a nonparametric identifiability theory that formalizes this principle and shows that the latent factors can be recovered by regularizing the learned causal graph to be sparse. More pre"},"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":"2401.04890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-01-10T02:38:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94395856031c7c81c5f0f3a19ef6555a240404d821be4d32f3ab41420834c774","abstract_canon_sha256":"c2968d47081bc7887558b8c4626ac0d8babe3cbd30b3bddf3259260244aec9f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:59.570699Z","signature_b64":"pyyVyLcTIdPNXDJW1bDihIcGH92l/grbaPwEfen4sN98rb8b2FINB1gYA7WUwGcG4f17s43hnt8F7kcw8L1bAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aacadfdb129a50b9f630b809e2a2492e0863e7b1c3fa20d52ac481f7265eb5e5","last_reissued_at":"2026-07-05T07:31:59.570249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:59.570249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre Lacoste, Katie Everett, Pau Rodr\\'iguez L\\'opez, R\\'emi Le Priol, S\\'ebastien Lachapelle, Simon Lacoste-Julien, Yash Sharma","submitted_at":"2024-01-10T02:38:21Z","abstract_excerpt":"This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors and the sparse causal graphical model that explains them. We develop a nonparametric identifiability theory that formalizes this principle and shows that the latent factors can be recovered by regularizing the learned causal graph to be sparse. More pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04890","kind":"arxiv","version":1},"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/2401.04890/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":"2401.04890","created_at":"2026-07-05T07:31:59.570311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04890v1","created_at":"2026-07-05T07:31:59.570311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04890","created_at":"2026-07-05T07:31:59.570311+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLFN7WYSTJIL","created_at":"2026-07-05T07:31:59.570311+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLFN7WYSTJILT5RQ","created_at":"2026-07-05T07:31:59.570311+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLFN7WYS","created_at":"2026-07-05T07:31:59.570311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.06288","citing_title":"Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applications","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19135","citing_title":"Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22196","citing_title":"Mechanistic Independence: A Principle for Identifiable Disentangled Representations","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23790","citing_title":"A General Representation-Based Approach to Multi-Source Domain Adaptation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05524","citing_title":"MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY","json":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY.json","graph_json":"https://pith.science/api/pith-number/VLFN7WYSTJILT5RQXAE6FISJFY/graph.json","events_json":"https://pith.science/api/pith-number/VLFN7WYSTJILT5RQXAE6FISJFY/events.json","paper":"https://pith.science/paper/VLFN7WYS"},"agent_actions":{"view_html":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY","download_json":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY.json","view_paper":"https://pith.science/paper/VLFN7WYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04890&json=true","fetch_graph":"https://pith.science/api/pith-number/VLFN7WYSTJILT5RQXAE6FISJFY/graph.json","fetch_events":"https://pith.science/api/pith-number/VLFN7WYSTJILT5RQXAE6FISJFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY/action/storage_attestation","attest_author":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY/action/author_attestation","sign_citation":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY/action/citation_signature","submit_replication":"https://pith.science/pith/VLFN7WYSTJILT5RQXAE6FISJFY/action/replication_record"}},"created_at":"2026-07-05T07:31:59.570311+00:00","updated_at":"2026-07-05T07:31:59.570311+00:00"}