{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6GREFQ77ATUCACIRNLKZMU4JDI","short_pith_number":"pith:6GREFQ77","schema_version":"1.0","canonical_sha256":"f1a242c3ff04e82009116ad59653891a0d4e8aab2aa8f9dc8335a5d38c9fbf57","source":{"kind":"arxiv","id":"2304.04103","version":2},"attestation_state":"computed","paper":{"title":"TC-VAE: Uncovering Out-of-Distribution Data Generative Factors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Cristian Meo, Justin Dauwels","submitted_at":"2023-04-08T21:16:46Z","abstract_excerpt":"Uncovering data generative factors is the ultimate goal of disentanglement learning. Although many works proposed disentangling generative models able to uncover the underlying generative factors of a dataset, so far no one was able to uncover OOD generative factors (i.e., factors of variations that are not explicitly shown on the dataset). Moreover, the datasets used to validate these models are synthetically generated using a balanced mixture of some predefined generative factors, implicitly assuming that generative factors are uniformly distributed across the datasets. However, real dataset"},"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":"2304.04103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-08T21:16:46Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"e8c81b1039a1ef2d36e9fa0130d1791a7c21a8b02f31e6d3a0c651795a4811a2","abstract_canon_sha256":"80d30658223e87519564fcddc0b4caa5f07a0af0544ad1fcfe035534f88d3fb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:50.948246Z","signature_b64":"0R48QTAvdlRHfz7jS6xuKCMyLml30bX+YNzvhhzrLL/xRvlizxP56iRQloCkAXsnV42mw43Dt24gUV2vU8HrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1a242c3ff04e82009116ad59653891a0d4e8aab2aa8f9dc8335a5d38c9fbf57","last_reissued_at":"2026-07-05T05:59:50.947685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:50.947685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TC-VAE: Uncovering Out-of-Distribution Data Generative Factors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Cristian Meo, Justin Dauwels","submitted_at":"2023-04-08T21:16:46Z","abstract_excerpt":"Uncovering data generative factors is the ultimate goal of disentanglement learning. Although many works proposed disentangling generative models able to uncover the underlying generative factors of a dataset, so far no one was able to uncover OOD generative factors (i.e., factors of variations that are not explicitly shown on the dataset). Moreover, the datasets used to validate these models are synthetically generated using a balanced mixture of some predefined generative factors, implicitly assuming that generative factors are uniformly distributed across the datasets. However, real dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04103","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/2304.04103/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":"2304.04103","created_at":"2026-07-05T05:59:50.947751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04103v2","created_at":"2026-07-05T05:59:50.947751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04103","created_at":"2026-07-05T05:59:50.947751+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GREFQ77ATUC","created_at":"2026-07-05T05:59:50.947751+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GREFQ77ATUCACIR","created_at":"2026-07-05T05:59:50.947751+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GREFQ77","created_at":"2026-07-05T05:59:50.947751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14476","citing_title":"Enhancing Interpretability of Sparse Latent Representations with Class Information","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI","json":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI.json","graph_json":"https://pith.science/api/pith-number/6GREFQ77ATUCACIRNLKZMU4JDI/graph.json","events_json":"https://pith.science/api/pith-number/6GREFQ77ATUCACIRNLKZMU4JDI/events.json","paper":"https://pith.science/paper/6GREFQ77"},"agent_actions":{"view_html":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI","download_json":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI.json","view_paper":"https://pith.science/paper/6GREFQ77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04103&json=true","fetch_graph":"https://pith.science/api/pith-number/6GREFQ77ATUCACIRNLKZMU4JDI/graph.json","fetch_events":"https://pith.science/api/pith-number/6GREFQ77ATUCACIRNLKZMU4JDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI/action/storage_attestation","attest_author":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI/action/author_attestation","sign_citation":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI/action/citation_signature","submit_replication":"https://pith.science/pith/6GREFQ77ATUCACIRNLKZMU4JDI/action/replication_record"}},"created_at":"2026-07-05T05:59:50.947751+00:00","updated_at":"2026-07-05T05:59:50.947751+00:00"}