{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OOKQ7QRP7S2ELMJYGGPDK4RDTF","short_pith_number":"pith:OOKQ7QRP","schema_version":"1.0","canonical_sha256":"73950fc22ffcb445b138319e357223997424e50979b42f885549df6dbafc7ecc","source":{"kind":"arxiv","id":"1711.02226","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Transformation Learning via Convex Relaxations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"John C. Duchi, Percy Liang, Tatsunori B. Hashimoto","submitted_at":"2017-11-06T23:56:41Z","abstract_excerpt":"Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised approach to learn such transformations by attempting to reconstruct an image from a linear combination of transformations of its nearest neighbors. On handwritten digits and celebrity portraits, we show that even with linear transformations, our method generates visually high-quality modified images. Moreover, since our method is semiparametric and does not model the data distribution, the learned transformations extr"},"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":"1711.02226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-06T23:56:41Z","cross_cats_sorted":[],"title_canon_sha256":"228e0442fe592d7de7ba75a3cc68aabbaa8988bc995c55f08ee553e1082909c4","abstract_canon_sha256":"86136cccee71eb89643bf91dc88ad4f12349b69c37a746a5640467de1255bdb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:08.506546Z","signature_b64":"HGrm2EZzk4N+OcphysMbgmj51R6TSnhmAqMGDNIhQjpznZUT1/BByPIKtSozlr/JcFxe0o62DxmHUj9UwUuxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73950fc22ffcb445b138319e357223997424e50979b42f885549df6dbafc7ecc","last_reissued_at":"2026-05-18T00:31:08.506020Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:08.506020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Transformation Learning via Convex Relaxations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"John C. Duchi, Percy Liang, Tatsunori B. Hashimoto","submitted_at":"2017-11-06T23:56:41Z","abstract_excerpt":"Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised approach to learn such transformations by attempting to reconstruct an image from a linear combination of transformations of its nearest neighbors. On handwritten digits and celebrity portraits, we show that even with linear transformations, our method generates visually high-quality modified images. Moreover, since our method is semiparametric and does not model the data distribution, the learned transformations extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02226","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.02226","created_at":"2026-05-18T00:31:08.506107+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.02226v1","created_at":"2026-05-18T00:31:08.506107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02226","created_at":"2026-05-18T00:31:08.506107+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOKQ7QRP7S2E","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOKQ7QRP7S2ELMJY","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOKQ7QRP","created_at":"2026-05-18T12:31:34.259226+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/OOKQ7QRP7S2ELMJYGGPDK4RDTF","json":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF.json","graph_json":"https://pith.science/api/pith-number/OOKQ7QRP7S2ELMJYGGPDK4RDTF/graph.json","events_json":"https://pith.science/api/pith-number/OOKQ7QRP7S2ELMJYGGPDK4RDTF/events.json","paper":"https://pith.science/paper/OOKQ7QRP"},"agent_actions":{"view_html":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF","download_json":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF.json","view_paper":"https://pith.science/paper/OOKQ7QRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.02226&json=true","fetch_graph":"https://pith.science/api/pith-number/OOKQ7QRP7S2ELMJYGGPDK4RDTF/graph.json","fetch_events":"https://pith.science/api/pith-number/OOKQ7QRP7S2ELMJYGGPDK4RDTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF/action/storage_attestation","attest_author":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF/action/author_attestation","sign_citation":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF/action/citation_signature","submit_replication":"https://pith.science/pith/OOKQ7QRP7S2ELMJYGGPDK4RDTF/action/replication_record"}},"created_at":"2026-05-18T00:31:08.506107+00:00","updated_at":"2026-05-18T00:31:08.506107+00:00"}