{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VRXT74NT2RNAZAPT6MMM237HFH","short_pith_number":"pith:VRXT74NT","schema_version":"1.0","canonical_sha256":"ac6f3ff1b3d45a0c81f3f318cd6fe729f2145862b192c5518763a4ae2ecc9535","source":{"kind":"arxiv","id":"1905.04132","version":2},"attestation_state":"computed","paper":{"title":"Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carsten Rother, Eric Brachmann","submitted_at":"2019-05-10T12:50:27Z","abstract_excerpt":"We present Neural-Guided RANSAC (NG-RANSAC), an extension to the classic RANSAC algorithm from robust optimization. NG-RANSAC uses prior information to improve model hypothesis search, increasing the chance of finding outlier-free minimal sets. Previous works use heuristic side-information like hand-crafted descriptor distance to guide hypothesis search. In contrast, we learn hypothesis search in a principled fashion that lets us optimize an arbitrary task loss during training, leading to large improvements on classic computer vision tasks. We present two further extensions to NG-RANSAC. First"},"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":"1905.04132","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-10T12:50:27Z","cross_cats_sorted":[],"title_canon_sha256":"26bcf2dee54354514e5e9c6abbc831679f51e3fc5e094551256a65e62fb36534","abstract_canon_sha256":"81426437fe2749245c49b182b2fb1f556920d2406c7d946f701154cfc15a6b45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:50:45.499729Z","signature_b64":"kusqSOeeZBy/tIanMsIfaMtkgadY563yFj2Wbj1jrDuOJIpBJxaP4syYYwsJIZ71I2b8fSHBv5SEMtH6FB/fAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac6f3ff1b3d45a0c81f3f318cd6fe729f2145862b192c5518763a4ae2ecc9535","last_reissued_at":"2026-07-04T23:50:45.499282Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:50:45.499282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carsten Rother, Eric Brachmann","submitted_at":"2019-05-10T12:50:27Z","abstract_excerpt":"We present Neural-Guided RANSAC (NG-RANSAC), an extension to the classic RANSAC algorithm from robust optimization. NG-RANSAC uses prior information to improve model hypothesis search, increasing the chance of finding outlier-free minimal sets. Previous works use heuristic side-information like hand-crafted descriptor distance to guide hypothesis search. In contrast, we learn hypothesis search in a principled fashion that lets us optimize an arbitrary task loss during training, leading to large improvements on classic computer vision tasks. We present two further extensions to NG-RANSAC. First"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04132","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.04132/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":"1905.04132","created_at":"2026-07-04T23:50:45.499346+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04132v2","created_at":"2026-07-04T23:50:45.499346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04132","created_at":"2026-07-04T23:50:45.499346+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRXT74NT2RNA","created_at":"2026-07-04T23:50:45.499346+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRXT74NT2RNAZAPT","created_at":"2026-07-04T23:50:45.499346+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRXT74NT","created_at":"2026-07-04T23:50:45.499346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.08744","citing_title":"Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH","json":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH.json","graph_json":"https://pith.science/api/pith-number/VRXT74NT2RNAZAPT6MMM237HFH/graph.json","events_json":"https://pith.science/api/pith-number/VRXT74NT2RNAZAPT6MMM237HFH/events.json","paper":"https://pith.science/paper/VRXT74NT"},"agent_actions":{"view_html":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH","download_json":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH.json","view_paper":"https://pith.science/paper/VRXT74NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04132&json=true","fetch_graph":"https://pith.science/api/pith-number/VRXT74NT2RNAZAPT6MMM237HFH/graph.json","fetch_events":"https://pith.science/api/pith-number/VRXT74NT2RNAZAPT6MMM237HFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH/action/storage_attestation","attest_author":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH/action/author_attestation","sign_citation":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH/action/citation_signature","submit_replication":"https://pith.science/pith/VRXT74NT2RNAZAPT6MMM237HFH/action/replication_record"}},"created_at":"2026-07-04T23:50:45.499346+00:00","updated_at":"2026-07-04T23:50:45.499346+00:00"}