{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UDAZMLW6CQNQTEKT473XUGESAE","short_pith_number":"pith:UDAZMLW6","schema_version":"1.0","canonical_sha256":"a0c1962ede141b099153e7f77a18920111e7a60a2da1529803c7d7a404d6f9d3","source":{"kind":"arxiv","id":"2304.07939","version":3},"attestation_state":"computed","paper":{"title":"Leveraging sparse and shared feature activations for disentangled representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Achille, Bernhard Sch\\\"olkopf, Emanuele Rodol\\`a, Florian Wenzel, Francesco Locatello, Luca Zancato, Marco Fumero, Stefano Soatto","submitted_at":"2023-04-17T01:33:24Z","abstract_excerpt":"Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for representation learning on real world data. In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. Assuming each supervised task only depends on an unknown subset of the factors of variation, we disentangle the feature space of a supervised multi-task model, with featur"},"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":"2304.07939","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T01:33:24Z","cross_cats_sorted":[],"title_canon_sha256":"287aa2649f4417fac6570642e5a0ce4678d0f4a16171586ac48c61c7d20010c4","abstract_canon_sha256":"01165b7219bf69bc9e6d2f4e186641ca0c28af49fe4a6638187cd2884ed32af1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:25.108170Z","signature_b64":"J7IQc3wMUB6UANxeX59I2GHVrzNH1Dx7Hjs4JW9Xx2k4ZkPMr7a/wLy486pnBkMTzeETrYpa1BsfpiQeb2xZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0c1962ede141b099153e7f77a18920111e7a60a2da1529803c7d7a404d6f9d3","last_reissued_at":"2026-07-05T07:23:25.107739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:25.107739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging sparse and shared feature activations for disentangled representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Achille, Bernhard Sch\\\"olkopf, Emanuele Rodol\\`a, Florian Wenzel, Francesco Locatello, Luca Zancato, Marco Fumero, Stefano Soatto","submitted_at":"2023-04-17T01:33:24Z","abstract_excerpt":"Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for representation learning on real world data. In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. Assuming each supervised task only depends on an unknown subset of the factors of variation, we disentangle the feature space of a supervised multi-task model, with featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07939","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/2304.07939/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":"2304.07939","created_at":"2026-07-05T07:23:25.107791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.07939v3","created_at":"2026-07-05T07:23:25.107791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07939","created_at":"2026-07-05T07:23:25.107791+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDAZMLW6CQNQ","created_at":"2026-07-05T07:23:25.107791+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDAZMLW6CQNQTEKT","created_at":"2026-07-05T07:23:25.107791+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDAZMLW6","created_at":"2026-07-05T07:23:25.107791+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/UDAZMLW6CQNQTEKT473XUGESAE","json":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE.json","graph_json":"https://pith.science/api/pith-number/UDAZMLW6CQNQTEKT473XUGESAE/graph.json","events_json":"https://pith.science/api/pith-number/UDAZMLW6CQNQTEKT473XUGESAE/events.json","paper":"https://pith.science/paper/UDAZMLW6"},"agent_actions":{"view_html":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE","download_json":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE.json","view_paper":"https://pith.science/paper/UDAZMLW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.07939&json=true","fetch_graph":"https://pith.science/api/pith-number/UDAZMLW6CQNQTEKT473XUGESAE/graph.json","fetch_events":"https://pith.science/api/pith-number/UDAZMLW6CQNQTEKT473XUGESAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE/action/storage_attestation","attest_author":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE/action/author_attestation","sign_citation":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE/action/citation_signature","submit_replication":"https://pith.science/pith/UDAZMLW6CQNQTEKT473XUGESAE/action/replication_record"}},"created_at":"2026-07-05T07:23:25.107791+00:00","updated_at":"2026-07-05T07:23:25.107791+00:00"}