{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7UIGDDVQFSB5WBIB6IC3DEJAVH","short_pith_number":"pith:7UIGDDVQ","schema_version":"1.0","canonical_sha256":"fd10618eb02c83db0501f205b19120a9ef6deb3a542e2af14005e4a93d60b5eb","source":{"kind":"arxiv","id":"1611.10229","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Training of Hybrid CNN-CRF Models for Stereo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Shekhovtsov, Christian Reinbacher, Patrick Kn\\\"obelreiter, Thomas Pock","submitted_at":"2016-11-30T15:45:02Z","abstract_excerpt":"We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expressive features for matching and distinctive color edges, which in turn are used to compute the unary and binary costs of the CRF. For inference, we apply a recently proposed highly parallel dual block descent algorithm which only needs a small fixed number of iterations to compute a high-quality approximate minimizer. As the main contribution of th"},"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":"1611.10229","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-30T15:45:02Z","cross_cats_sorted":[],"title_canon_sha256":"166738f53cd4696bef9005a6b2b44ba680d2c38fa6c9a62e011c0a52d0dc5b47","abstract_canon_sha256":"3e6b24787b812e39de2f343dd9763ad7d4752fe47c0db315fba0c1443d523fd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:06.315132Z","signature_b64":"jSGh36AWVF9w4B8HPeZJbkYqI70TQoua47br9dx3MX5ckK029ik+rW3d53/ePaWs//gNYsh0aPvWD8CJtjnwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd10618eb02c83db0501f205b19120a9ef6deb3a542e2af14005e4a93d60b5eb","last_reissued_at":"2026-05-18T00:45:06.314752Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:06.314752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Training of Hybrid CNN-CRF Models for Stereo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Shekhovtsov, Christian Reinbacher, Patrick Kn\\\"obelreiter, Thomas Pock","submitted_at":"2016-11-30T15:45:02Z","abstract_excerpt":"We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expressive features for matching and distinctive color edges, which in turn are used to compute the unary and binary costs of the CRF. For inference, we apply a recently proposed highly parallel dual block descent algorithm which only needs a small fixed number of iterations to compute a high-quality approximate minimizer. As the main contribution of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.10229","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":"1611.10229","created_at":"2026-05-18T00:45:06.314814+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.10229v2","created_at":"2026-05-18T00:45:06.314814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.10229","created_at":"2026-05-18T00:45:06.314814+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UIGDDVQFSB5","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UIGDDVQFSB5WBIB","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UIGDDVQ","created_at":"2026-05-18T12:30:04.600751+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/7UIGDDVQFSB5WBIB6IC3DEJAVH","json":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH.json","graph_json":"https://pith.science/api/pith-number/7UIGDDVQFSB5WBIB6IC3DEJAVH/graph.json","events_json":"https://pith.science/api/pith-number/7UIGDDVQFSB5WBIB6IC3DEJAVH/events.json","paper":"https://pith.science/paper/7UIGDDVQ"},"agent_actions":{"view_html":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH","download_json":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH.json","view_paper":"https://pith.science/paper/7UIGDDVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.10229&json=true","fetch_graph":"https://pith.science/api/pith-number/7UIGDDVQFSB5WBIB6IC3DEJAVH/graph.json","fetch_events":"https://pith.science/api/pith-number/7UIGDDVQFSB5WBIB6IC3DEJAVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH/action/storage_attestation","attest_author":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH/action/author_attestation","sign_citation":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH/action/citation_signature","submit_replication":"https://pith.science/pith/7UIGDDVQFSB5WBIB6IC3DEJAVH/action/replication_record"}},"created_at":"2026-05-18T00:45:06.314814+00:00","updated_at":"2026-05-18T00:45:06.314814+00:00"}