{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DYVSRUUJY35MHMXG33S75RT4M5","short_pith_number":"pith:DYVSRUUJ","schema_version":"1.0","canonical_sha256":"1e2b28d289c6fac3b2e6dee5fec67c6750e0eca079d18c04542e00f13f68bba5","source":{"kind":"arxiv","id":"2101.00591","version":2},"attestation_state":"computed","paper":{"title":"Progressive Correspondence Pruning by Consensus Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chen Zhao, Feng Zhu, Hongsheng Li, Mathieu Salzmann, Rui Zhao, Yixiao Ge","submitted_at":"2021-01-03T09:10:00Z","abstract_excerpt":"Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences. The selection is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the random distribution of such outliers further complicates the learning process for learning-based methods. To address this issue, we propose to progressively prune the correspondences via a local-to-global consensus learning procedure. We introduce a ``pruning'' block that lets us identify reliable candidates among the initial matches accor"},"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":"2101.00591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-03T09:10:00Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"0da7a9b7ee6d1dd9f589329b18303d71792da74e7c8e28a5917a6984239b173a","abstract_canon_sha256":"fd62ca9988d2545f9d030e692eb15af3851d721a8513f09fc5733ee1ee0f37a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:34.929818Z","signature_b64":"I4WvqHj7U25PjnMFiMztjDQkJofQx10TQ6sccpKsruJiH43DvgIvMJwMMgC09uAoN/OFZTiWSTJaNX+qTDaxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e2b28d289c6fac3b2e6dee5fec67c6750e0eca079d18c04542e00f13f68bba5","last_reissued_at":"2026-07-05T03:01:34.929305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:34.929305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Correspondence Pruning by Consensus Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chen Zhao, Feng Zhu, Hongsheng Li, Mathieu Salzmann, Rui Zhao, Yixiao Ge","submitted_at":"2021-01-03T09:10:00Z","abstract_excerpt":"Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences. The selection is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the random distribution of such outliers further complicates the learning process for learning-based methods. To address this issue, we propose to progressively prune the correspondences via a local-to-global consensus learning procedure. We introduce a ``pruning'' block that lets us identify reliable candidates among the initial matches accor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00591","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/2101.00591/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":"2101.00591","created_at":"2026-07-05T03:01:34.929387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.00591v2","created_at":"2026-07-05T03:01:34.929387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00591","created_at":"2026-07-05T03:01:34.929387+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYVSRUUJY35M","created_at":"2026-07-05T03:01:34.929387+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYVSRUUJY35MHMXG","created_at":"2026-07-05T03:01:34.929387+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYVSRUUJ","created_at":"2026-07-05T03:01:34.929387+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/DYVSRUUJY35MHMXG33S75RT4M5","json":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5.json","graph_json":"https://pith.science/api/pith-number/DYVSRUUJY35MHMXG33S75RT4M5/graph.json","events_json":"https://pith.science/api/pith-number/DYVSRUUJY35MHMXG33S75RT4M5/events.json","paper":"https://pith.science/paper/DYVSRUUJ"},"agent_actions":{"view_html":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5","download_json":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5.json","view_paper":"https://pith.science/paper/DYVSRUUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.00591&json=true","fetch_graph":"https://pith.science/api/pith-number/DYVSRUUJY35MHMXG33S75RT4M5/graph.json","fetch_events":"https://pith.science/api/pith-number/DYVSRUUJY35MHMXG33S75RT4M5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5/action/storage_attestation","attest_author":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5/action/author_attestation","sign_citation":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5/action/citation_signature","submit_replication":"https://pith.science/pith/DYVSRUUJY35MHMXG33S75RT4M5/action/replication_record"}},"created_at":"2026-07-05T03:01:34.929387+00:00","updated_at":"2026-07-05T03:01:34.929387+00:00"}