{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TERIM45JK3MMQMTHZMRPOT25VO","short_pith_number":"pith:TERIM45J","schema_version":"1.0","canonical_sha256":"99228673a956d8c83267cb22f74f5dabb6be7fe2fcf340b24a8dc8f63bb5f46c","source":{"kind":"arxiv","id":"1703.04775","version":1},"attestation_state":"computed","paper":{"title":"Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Tacchetti, Georgios Evangelopoulos, Stephen Voinea","submitted_at":"2017-03-14T22:21:48Z","abstract_excerpt":"The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes are orthogonal to recognition and should not be reflected in the representation or feature encoding used for learning. We introduce a framework for weakly supervised learning of image embeddings that are robust to transformations and selective to the class distribution, using sets of transforming e"},"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":"1703.04775","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-14T22:21:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3097d2c2d340c98d4e24997679f045379308000c98127031f13dc0559481cb21","abstract_canon_sha256":"1a0168b3a5923961a0b4096dd47f1b30798a653c64f8a6704d775e9a1002e926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:39.280842Z","signature_b64":"ink0XEOu1HZeJo/20UHREiQHcLucLIUpZ/DjCmoZd9PZcmyjY4Rbmjzna6h/BoV4xL9CwHIK08sMmidG2ivHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99228673a956d8c83267cb22f74f5dabb6be7fe2fcf340b24a8dc8f63bb5f46c","last_reissued_at":"2026-05-18T00:48:39.280368Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:39.280368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Tacchetti, Georgios Evangelopoulos, Stephen Voinea","submitted_at":"2017-03-14T22:21:48Z","abstract_excerpt":"The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes are orthogonal to recognition and should not be reflected in the representation or feature encoding used for learning. We introduce a framework for weakly supervised learning of image embeddings that are robust to transformations and selective to the class distribution, using sets of transforming e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04775","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":"1703.04775","created_at":"2026-05-18T00:48:39.280447+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04775v1","created_at":"2026-05-18T00:48:39.280447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04775","created_at":"2026-05-18T00:48:39.280447+00:00"},{"alias_kind":"pith_short_12","alias_value":"TERIM45JK3MM","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TERIM45JK3MMQMTH","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TERIM45J","created_at":"2026-05-18T12:31:46.661854+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/TERIM45JK3MMQMTHZMRPOT25VO","json":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO.json","graph_json":"https://pith.science/api/pith-number/TERIM45JK3MMQMTHZMRPOT25VO/graph.json","events_json":"https://pith.science/api/pith-number/TERIM45JK3MMQMTHZMRPOT25VO/events.json","paper":"https://pith.science/paper/TERIM45J"},"agent_actions":{"view_html":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO","download_json":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO.json","view_paper":"https://pith.science/paper/TERIM45J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04775&json=true","fetch_graph":"https://pith.science/api/pith-number/TERIM45JK3MMQMTHZMRPOT25VO/graph.json","fetch_events":"https://pith.science/api/pith-number/TERIM45JK3MMQMTHZMRPOT25VO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO/action/storage_attestation","attest_author":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO/action/author_attestation","sign_citation":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO/action/citation_signature","submit_replication":"https://pith.science/pith/TERIM45JK3MMQMTHZMRPOT25VO/action/replication_record"}},"created_at":"2026-05-18T00:48:39.280447+00:00","updated_at":"2026-05-18T00:48:39.280447+00:00"}