{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CRDRVGQ4IZQCO6EJSJBW5TZCLT","short_pith_number":"pith:CRDRVGQ4","schema_version":"1.0","canonical_sha256":"14471a9a1c466027788992436ecf225ce8c24a79631b9a7e0bc69b3538685007","source":{"kind":"arxiv","id":"2110.02891","version":2},"attestation_state":"computed","paper":{"title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Ashish Shrivastava, Hema Swetha Koppula, Jen-Hao Rick Chang, Oncel Tuzel, Xiaoshuai Zhang","submitted_at":"2021-10-06T16:17:57Z","abstract_excerpt":"Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in different voices, auto-completing and auto-correcting written handwriting, and generating missing training samples for downstream recognition tasks. However, under an unsupervised-style setting, typical training algorithms for controllable sequence generative models suffer from the training-inference mismatch, where the same sample is used as content and style input during training but unpaired samples are given during i"},"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":"2110.02891","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T16:17:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6e7483ec83cdaae101ee567ff4b518fbe11112ed1b7ec13a0ad28a1bb9e0769a","abstract_canon_sha256":"945f86bd3d731120d8e989bc993a4ec1943861acaab5f831c5708d1a5eff5d3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:33.493588Z","signature_b64":"QUkSu+0SwM+SIHZpPjCL+tjpjj+FTzHKMz4nnt9PglwPjhAuqJIA9mC/D/h6u5QbC63wH0no23KG6loPscN0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14471a9a1c466027788992436ecf225ce8c24a79631b9a7e0bc69b3538685007","last_reissued_at":"2026-07-05T04:36:33.493075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:33.493075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Ashish Shrivastava, Hema Swetha Koppula, Jen-Hao Rick Chang, Oncel Tuzel, Xiaoshuai Zhang","submitted_at":"2021-10-06T16:17:57Z","abstract_excerpt":"Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in different voices, auto-completing and auto-correcting written handwriting, and generating missing training samples for downstream recognition tasks. However, under an unsupervised-style setting, typical training algorithms for controllable sequence generative models suffer from the training-inference mismatch, where the same sample is used as content and style input during training but unpaired samples are given during i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02891","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/2110.02891/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":"2110.02891","created_at":"2026-07-05T04:36:33.493146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02891v2","created_at":"2026-07-05T04:36:33.493146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02891","created_at":"2026-07-05T04:36:33.493146+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRDRVGQ4IZQC","created_at":"2026-07-05T04:36:33.493146+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRDRVGQ4IZQCO6EJ","created_at":"2026-07-05T04:36:33.493146+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRDRVGQ4","created_at":"2026-07-05T04:36:33.493146+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/CRDRVGQ4IZQCO6EJSJBW5TZCLT","json":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT.json","graph_json":"https://pith.science/api/pith-number/CRDRVGQ4IZQCO6EJSJBW5TZCLT/graph.json","events_json":"https://pith.science/api/pith-number/CRDRVGQ4IZQCO6EJSJBW5TZCLT/events.json","paper":"https://pith.science/paper/CRDRVGQ4"},"agent_actions":{"view_html":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT","download_json":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT.json","view_paper":"https://pith.science/paper/CRDRVGQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02891&json=true","fetch_graph":"https://pith.science/api/pith-number/CRDRVGQ4IZQCO6EJSJBW5TZCLT/graph.json","fetch_events":"https://pith.science/api/pith-number/CRDRVGQ4IZQCO6EJSJBW5TZCLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT/action/storage_attestation","attest_author":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT/action/author_attestation","sign_citation":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT/action/citation_signature","submit_replication":"https://pith.science/pith/CRDRVGQ4IZQCO6EJSJBW5TZCLT/action/replication_record"}},"created_at":"2026-07-05T04:36:33.493146+00:00","updated_at":"2026-07-05T04:36:33.493146+00:00"}