{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:OGXYVVEWPVXVUVALJC4BO3XAG5","short_pith_number":"pith:OGXYVVEW","schema_version":"1.0","canonical_sha256":"71af8ad4967d6f5a540b48b8176ee0376770e796aaf8cfd605cc1c99113c75be","source":{"kind":"arxiv","id":"1510.05970","version":2},"attestation_state":"computed","paper":{"title":"Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jure \\v{Z}bontar, Yann LeCun","submitted_at":"2015-10-20T17:15:05Z","abstract_excerpt":"We present a method for extracting depth information from a rectified image pair. Our approach focuses on the first stage of many stereo algorithms: the matching cost computation. We approach the problem by learning a similarity measure on small image patches using a convolutional neural network. Training is carried out in a supervised manner by constructing a binary classification data set with examples of similar and dissimilar pairs of patches. We examine two network architectures for this task: one tuned for speed, the other for accuracy. The output of the convolutional neural network is u"},"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":"1510.05970","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-10-20T17:15:05Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"3b1385789760198c8c4a0fbef009c6c0b0d1489b0420580caf8cd56e6f5600db","abstract_canon_sha256":"07e97e16c0ba9df9c8104af7d4575ed103a460b5baa20f8baa969a2ba5e45048"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:35.824650Z","signature_b64":"7mKMBhDdl4VSQAEjUFO7yPTuscqWAM71T/MM2GVygdr5Lw+60KsKX+gZWd7nSOgeF5/07Lckq5z6zlPMbqkxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71af8ad4967d6f5a540b48b8176ee0376770e796aaf8cfd605cc1c99113c75be","last_reissued_at":"2026-05-18T01:14:35.823898Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:35.823898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jure \\v{Z}bontar, Yann LeCun","submitted_at":"2015-10-20T17:15:05Z","abstract_excerpt":"We present a method for extracting depth information from a rectified image pair. Our approach focuses on the first stage of many stereo algorithms: the matching cost computation. We approach the problem by learning a similarity measure on small image patches using a convolutional neural network. Training is carried out in a supervised manner by constructing a binary classification data set with examples of similar and dissimilar pairs of patches. We examine two network architectures for this task: one tuned for speed, the other for accuracy. The output of the convolutional neural network is u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.05970","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":""},"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":"1510.05970","created_at":"2026-05-18T01:14:35.824028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.05970v2","created_at":"2026-05-18T01:14:35.824028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.05970","created_at":"2026-05-18T01:14:35.824028+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGXYVVEWPVXV","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGXYVVEWPVXVUVAL","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGXYVVEW","created_at":"2026-05-18T12:29:34.919912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19926","citing_title":"A Fast Parallel Median Filtering Algorithm Using Hierarchical Tiling","ref_index":2016,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5","json":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5.json","graph_json":"https://pith.science/api/pith-number/OGXYVVEWPVXVUVALJC4BO3XAG5/graph.json","events_json":"https://pith.science/api/pith-number/OGXYVVEWPVXVUVALJC4BO3XAG5/events.json","paper":"https://pith.science/paper/OGXYVVEW"},"agent_actions":{"view_html":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5","download_json":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5.json","view_paper":"https://pith.science/paper/OGXYVVEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.05970&json=true","fetch_graph":"https://pith.science/api/pith-number/OGXYVVEWPVXVUVALJC4BO3XAG5/graph.json","fetch_events":"https://pith.science/api/pith-number/OGXYVVEWPVXVUVALJC4BO3XAG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5/action/storage_attestation","attest_author":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5/action/author_attestation","sign_citation":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5/action/citation_signature","submit_replication":"https://pith.science/pith/OGXYVVEWPVXVUVALJC4BO3XAG5/action/replication_record"}},"created_at":"2026-05-18T01:14:35.824028+00:00","updated_at":"2026-05-18T01:14:35.824028+00:00"}