{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:57EVUUHIRLHZ2STUESVTGHRBNQ","short_pith_number":"pith:57EVUUHI","schema_version":"1.0","canonical_sha256":"efc95a50e88acf9d4a7424ab331e216c25ae18d31a7e191b5ad93d67b68f89cf","source":{"kind":"arxiv","id":"1908.10543","version":1},"attestation_state":"computed","paper":{"title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean Ponce, Jongmin Lee, Juhong Min, Minsu Cho","submitted_at":"2019-08-28T04:16:52Z","abstract_excerpt":"Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in computer vision. Despite its significance, however, most of the datasets for semantic correspondence are limited to a small amount of image pairs with similar viewpoints and scales. In this paper, we present a new large-scale benchmark dataset of semantically paired images, SPair-71k, which contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly "},"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":"1908.10543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-28T04:16:52Z","cross_cats_sorted":[],"title_canon_sha256":"275d3eff61d47a601443f6a0a0de3f812c5e896bdcbb2c823f196d57c5aca60c","abstract_canon_sha256":"7d0412fe8c3400a4a805cc40a20536106d57e974712533241800713bc1b8208e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:18.228569Z","signature_b64":"/IWqo04ZEEW06PlPaixdSZ4yHxCIzNbd2VEHhkDL7zt/HHFytb2XEAFtk+M3vKhKCbyjSnD0kGiDq9AlU2HdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc95a50e88acf9d4a7424ab331e216c25ae18d31a7e191b5ad93d67b68f89cf","last_reissued_at":"2026-07-05T00:00:18.228111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:18.228111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean Ponce, Jongmin Lee, Juhong Min, Minsu Cho","submitted_at":"2019-08-28T04:16:52Z","abstract_excerpt":"Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in computer vision. Despite its significance, however, most of the datasets for semantic correspondence are limited to a small amount of image pairs with similar viewpoints and scales. In this paper, we present a new large-scale benchmark dataset of semantically paired images, SPair-71k, which contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10543","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.10543/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":"1908.10543","created_at":"2026-07-05T00:00:18.228172+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10543v1","created_at":"2026-07-05T00:00:18.228172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10543","created_at":"2026-07-05T00:00:18.228172+00:00"},{"alias_kind":"pith_short_12","alias_value":"57EVUUHIRLHZ","created_at":"2026-07-05T00:00:18.228172+00:00"},{"alias_kind":"pith_short_16","alias_value":"57EVUUHIRLHZ2STU","created_at":"2026-07-05T00:00:18.228172+00:00"},{"alias_kind":"pith_short_8","alias_value":"57EVUUHI","created_at":"2026-07-05T00:00:18.228172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27354","citing_title":"Error-Conditioned Neural Solvers","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31597","citing_title":"SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31597","citing_title":"SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28257","citing_title":"Category-Level 3D Correspondence in Camera Space via Morphable Object Priors","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30093","citing_title":"Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17715","citing_title":"Normalized Matching Transformer","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17472","citing_title":"Weighted Reverse Convolution for Feature Upsampling","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17472","citing_title":"Weighted Reverse Convolution for Feature Upsampling","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14137","citing_title":"Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12390","citing_title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02486","citing_title":"VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14433","citing_title":"Zero-Ablation Overstates Register Content Dependence in DINO Vision Transformers","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18267","citing_title":"MARCO: Navigating the Unseen Space of Semantic Correspondence","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ","json":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ.json","graph_json":"https://pith.science/api/pith-number/57EVUUHIRLHZ2STUESVTGHRBNQ/graph.json","events_json":"https://pith.science/api/pith-number/57EVUUHIRLHZ2STUESVTGHRBNQ/events.json","paper":"https://pith.science/paper/57EVUUHI"},"agent_actions":{"view_html":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ","download_json":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ.json","view_paper":"https://pith.science/paper/57EVUUHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10543&json=true","fetch_graph":"https://pith.science/api/pith-number/57EVUUHIRLHZ2STUESVTGHRBNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/57EVUUHIRLHZ2STUESVTGHRBNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ/action/storage_attestation","attest_author":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ/action/author_attestation","sign_citation":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ/action/citation_signature","submit_replication":"https://pith.science/pith/57EVUUHIRLHZ2STUESVTGHRBNQ/action/replication_record"}},"created_at":"2026-07-05T00:00:18.228172+00:00","updated_at":"2026-07-05T00:00:18.228172+00:00"}