{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GTIO4RXSCKPVZIFPEZCB5A3E62","short_pith_number":"pith:GTIO4RXS","schema_version":"1.0","canonical_sha256":"34d0ee46f2129f5ca0af26441e8364f6984269d7e77efc84b0008a35b3e1109b","source":{"kind":"arxiv","id":"1906.11796","version":3},"attestation_state":"computed","paper":{"title":"Demystifying Inter-Class Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Gabbay, Yedid Hoshen","submitted_at":"2019-06-27T16:58:26Z","abstract_excerpt":"Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations of current methods. We therefore introduce LORD, a novel method based on Latent Optimization for Representation Disentanglement. We find that latent optimization, along with an asymmetric noise regularization, is superior to amortized inference for achieving disentangled representations. In extensive experiments, our method is shown to achieve better disent"},"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":"1906.11796","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-27T16:58:26Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"368ae568191045a92267c8c3298b8d6f86337aeff5625506febf9f705f5a59b9","abstract_canon_sha256":"17e74b3676b06be8df5f253a950d5d0a42a5e06771bd295353a7afdff82c22c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:30.849190Z","signature_b64":"guX9ysu8mY8YgZjEv2q4QE29dzZ4ofXhNcMp4Beeas+Y/Y03vDaOsKjhwjUunJm543NVixg1t8iczbr00oFADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34d0ee46f2129f5ca0af26441e8364f6984269d7e77efc84b0008a35b3e1109b","last_reissued_at":"2026-07-05T00:41:30.848717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:30.848717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Demystifying Inter-Class Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Gabbay, Yedid Hoshen","submitted_at":"2019-06-27T16:58:26Z","abstract_excerpt":"Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations of current methods. We therefore introduce LORD, a novel method based on Latent Optimization for Representation Disentanglement. We find that latent optimization, along with an asymmetric noise regularization, is superior to amortized inference for achieving disentangled representations. In extensive experiments, our method is shown to achieve better disent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11796","kind":"arxiv","version":3},"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/1906.11796/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":"1906.11796","created_at":"2026-07-05T00:41:30.848776+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11796v3","created_at":"2026-07-05T00:41:30.848776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11796","created_at":"2026-07-05T00:41:30.848776+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTIO4RXSCKPV","created_at":"2026-07-05T00:41:30.848776+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTIO4RXSCKPVZIFP","created_at":"2026-07-05T00:41:30.848776+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTIO4RXS","created_at":"2026-07-05T00:41:30.848776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08493","citing_title":"Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62","json":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62.json","graph_json":"https://pith.science/api/pith-number/GTIO4RXSCKPVZIFPEZCB5A3E62/graph.json","events_json":"https://pith.science/api/pith-number/GTIO4RXSCKPVZIFPEZCB5A3E62/events.json","paper":"https://pith.science/paper/GTIO4RXS"},"agent_actions":{"view_html":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62","download_json":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62.json","view_paper":"https://pith.science/paper/GTIO4RXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11796&json=true","fetch_graph":"https://pith.science/api/pith-number/GTIO4RXSCKPVZIFPEZCB5A3E62/graph.json","fetch_events":"https://pith.science/api/pith-number/GTIO4RXSCKPVZIFPEZCB5A3E62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62/action/storage_attestation","attest_author":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62/action/author_attestation","sign_citation":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62/action/citation_signature","submit_replication":"https://pith.science/pith/GTIO4RXSCKPVZIFPEZCB5A3E62/action/replication_record"}},"created_at":"2026-07-05T00:41:30.848776+00:00","updated_at":"2026-07-05T00:41:30.848776+00:00"}