{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TKLMJT64Y5XURFT65JVJVQYZCW","short_pith_number":"pith:TKLMJT64","schema_version":"1.0","canonical_sha256":"9a96c4cfdcc76f48967eea6a9ac31915822506e1f0fd5c19b62d7621b189bb20","source":{"kind":"arxiv","id":"1901.08339","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Semantic Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juho Kannala, Zakaria Laskar","submitted_at":"2019-01-24T10:46:41Z","abstract_excerpt":"Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images. Due to non-availability of large training datasets, existing methods resort to self-supervised or unsupervised training paradigm. In this paper we propose a semi-supervised learning framework that imposes cyclic consistency constraint on unlabeled image pairs. Together with the supervised loss the proposed model achieves state-of-the-art on a benchmark semantic matching 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":"1901.08339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-24T10:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"b3866d99e68948b9b3b157eb92b9f77ab0ca9021498ad057cf70aeb032ecf78c","abstract_canon_sha256":"6d88bb847a0c2b5d19bc8d62d3f8219adaa8266ab7fa350cabacd0f2d8698c56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:37.283362Z","signature_b64":"nmwUlL1vMhDZCI8v2h+DUKRy7dSiIXp53IygzjPMi3jBePlC+4UMV47GO4Uz6U/vTufP12KZvaLuG5i93alPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a96c4cfdcc76f48967eea6a9ac31915822506e1f0fd5c19b62d7621b189bb20","last_reissued_at":"2026-05-17T23:55:37.282830Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:37.282830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Semantic Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juho Kannala, Zakaria Laskar","submitted_at":"2019-01-24T10:46:41Z","abstract_excerpt":"Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images. Due to non-availability of large training datasets, existing methods resort to self-supervised or unsupervised training paradigm. In this paper we propose a semi-supervised learning framework that imposes cyclic consistency constraint on unlabeled image pairs. Together with the supervised loss the proposed model achieves state-of-the-art on a benchmark semantic matching dataset."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08339","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":"1901.08339","created_at":"2026-05-17T23:55:37.282910+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08339v1","created_at":"2026-05-17T23:55:37.282910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08339","created_at":"2026-05-17T23:55:37.282910+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKLMJT64Y5XU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKLMJT64Y5XURFT6","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKLMJT64","created_at":"2026-05-18T12:33:30.264802+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/TKLMJT64Y5XURFT65JVJVQYZCW","json":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW.json","graph_json":"https://pith.science/api/pith-number/TKLMJT64Y5XURFT65JVJVQYZCW/graph.json","events_json":"https://pith.science/api/pith-number/TKLMJT64Y5XURFT65JVJVQYZCW/events.json","paper":"https://pith.science/paper/TKLMJT64"},"agent_actions":{"view_html":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW","download_json":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW.json","view_paper":"https://pith.science/paper/TKLMJT64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08339&json=true","fetch_graph":"https://pith.science/api/pith-number/TKLMJT64Y5XURFT65JVJVQYZCW/graph.json","fetch_events":"https://pith.science/api/pith-number/TKLMJT64Y5XURFT65JVJVQYZCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW/action/storage_attestation","attest_author":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW/action/author_attestation","sign_citation":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW/action/citation_signature","submit_replication":"https://pith.science/pith/TKLMJT64Y5XURFT65JVJVQYZCW/action/replication_record"}},"created_at":"2026-05-17T23:55:37.282910+00:00","updated_at":"2026-05-17T23:55:37.282910+00:00"}