{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AK7LKO57JTFXIKJ6MOVGQSYNAB","short_pith_number":"pith:AK7LKO57","schema_version":"1.0","canonical_sha256":"02beb53bbf4ccb74293e63aa684b0d0076968d686c6bb8da8e44be56fb3684ed","source":{"kind":"arxiv","id":"1812.03253","version":2},"attestation_state":"computed","paper":{"title":"Counterfactuals uncover the modular structure of deep generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Mehrjou, Bernhard Sch\\\"olkopf, Michel Besserve, R\\'emy Sun","submitted_at":"2018-12-08T01:57:27Z","abstract_excerpt":"Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the data space remains challenging without some form of supervision. While previous work has focused on exploiting statistical independence to disentangle latent factors, we argue that such requirement is too restrictive and propose instead a non-statistical framework that relies on counterfactual manipulations to uncover a modular structure of the network compos"},"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":"1812.03253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-08T01:57:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94340624127e896adca98540356562971e2dac40ae301d894a0d918b2e73a4fc","abstract_canon_sha256":"c6c31aa356e5e00231f874f6f6caa24dd33cafa90c903b31b90ff08861b8ac1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:38.081429Z","signature_b64":"N1xK/9rGawq7wH4sZeV9cYvpGlSfFs2NUP7lUbqoJEc++OudBqMAkoYobASXCyV2I6tK2Dzomt7QTklZrTOyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02beb53bbf4ccb74293e63aa684b0d0076968d686c6bb8da8e44be56fb3684ed","last_reissued_at":"2026-07-05T00:25:38.081002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:38.081002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactuals uncover the modular structure of deep generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Mehrjou, Bernhard Sch\\\"olkopf, Michel Besserve, R\\'emy Sun","submitted_at":"2018-12-08T01:57:27Z","abstract_excerpt":"Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the data space remains challenging without some form of supervision. While previous work has focused on exploiting statistical independence to disentangle latent factors, we argue that such requirement is too restrictive and propose instead a non-statistical framework that relies on counterfactual manipulations to uncover a modular structure of the network compos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03253","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/1812.03253/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":"1812.03253","created_at":"2026-07-05T00:25:38.081066+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03253v2","created_at":"2026-07-05T00:25:38.081066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03253","created_at":"2026-07-05T00:25:38.081066+00:00"},{"alias_kind":"pith_short_12","alias_value":"AK7LKO57JTFX","created_at":"2026-07-05T00:25:38.081066+00:00"},{"alias_kind":"pith_short_16","alias_value":"AK7LKO57JTFXIKJ6","created_at":"2026-07-05T00:25:38.081066+00:00"},{"alias_kind":"pith_short_8","alias_value":"AK7LKO57","created_at":"2026-07-05T00:25:38.081066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB","json":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB.json","graph_json":"https://pith.science/api/pith-number/AK7LKO57JTFXIKJ6MOVGQSYNAB/graph.json","events_json":"https://pith.science/api/pith-number/AK7LKO57JTFXIKJ6MOVGQSYNAB/events.json","paper":"https://pith.science/paper/AK7LKO57"},"agent_actions":{"view_html":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB","download_json":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB.json","view_paper":"https://pith.science/paper/AK7LKO57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03253&json=true","fetch_graph":"https://pith.science/api/pith-number/AK7LKO57JTFXIKJ6MOVGQSYNAB/graph.json","fetch_events":"https://pith.science/api/pith-number/AK7LKO57JTFXIKJ6MOVGQSYNAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB/action/storage_attestation","attest_author":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB/action/author_attestation","sign_citation":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB/action/citation_signature","submit_replication":"https://pith.science/pith/AK7LKO57JTFXIKJ6MOVGQSYNAB/action/replication_record"}},"created_at":"2026-07-05T00:25:38.081066+00:00","updated_at":"2026-07-05T00:25:38.081066+00:00"}