{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LEBNLNGEJMEVOEGUHGR27RGKHY","short_pith_number":"pith:LEBNLNGE","schema_version":"1.0","canonical_sha256":"5902d5b4c44b095710d439a3afc4ca3e107b3bb1add9007452caacf49aec47e0","source":{"kind":"arxiv","id":"2208.14201","version":1},"attestation_state":"computed","paper":{"title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David McKinnon, Hongkai Chen, Lei Zhou, Long Quan, Mingmin Zhen, Tian Fang, Yanghai Tsin, Yurun Tian, Zixin Luo","submitted_at":"2022-08-30T12:21:15Z","abstract_excerpt":"Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher that is built on hierarchical attention structure, adopting a novel attention operation which is capable of adjusting attention span in a self-adaptive manner. To achieve this goal, first, flow maps are regressed in each cross attention phase to locate the center of search region. Next, a sampling grid is generated around the center, whose size, instead of be"},"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":"2208.14201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-30T12:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"d61158ac25c248faa42df535f32bff36bc654faa1670d469a2b780727cc02fe9","abstract_canon_sha256":"37e27512c2fa1bbfcd2f1a46903b9ca95f4b34578abfde6c8c30cfe888ee643e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:09.850055Z","signature_b64":"rM43M0A7Gf+bg2fPY/dg+Y3M8Sz9GKvfNkWRdpIs1a3udtsluknqqLuqvdi1SORhUCse5aZ0EXsz+8EwVvfrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5902d5b4c44b095710d439a3afc4ca3e107b3bb1add9007452caacf49aec47e0","last_reissued_at":"2026-07-05T04:53:09.849649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:09.849649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David McKinnon, Hongkai Chen, Lei Zhou, Long Quan, Mingmin Zhen, Tian Fang, Yanghai Tsin, Yurun Tian, Zixin Luo","submitted_at":"2022-08-30T12:21:15Z","abstract_excerpt":"Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher that is built on hierarchical attention structure, adopting a novel attention operation which is capable of adjusting attention span in a self-adaptive manner. To achieve this goal, first, flow maps are regressed in each cross attention phase to locate the center of search region. Next, a sampling grid is generated around the center, whose size, instead of be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14201","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/2208.14201/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":"2208.14201","created_at":"2026-07-05T04:53:09.849706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.14201v1","created_at":"2026-07-05T04:53:09.849706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14201","created_at":"2026-07-05T04:53:09.849706+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEBNLNGEJMEV","created_at":"2026-07-05T04:53:09.849706+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEBNLNGEJMEVOEGU","created_at":"2026-07-05T04:53:09.849706+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEBNLNGE","created_at":"2026-07-05T04:53:09.849706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY","json":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY.json","graph_json":"https://pith.science/api/pith-number/LEBNLNGEJMEVOEGUHGR27RGKHY/graph.json","events_json":"https://pith.science/api/pith-number/LEBNLNGEJMEVOEGUHGR27RGKHY/events.json","paper":"https://pith.science/paper/LEBNLNGE"},"agent_actions":{"view_html":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY","download_json":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY.json","view_paper":"https://pith.science/paper/LEBNLNGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.14201&json=true","fetch_graph":"https://pith.science/api/pith-number/LEBNLNGEJMEVOEGUHGR27RGKHY/graph.json","fetch_events":"https://pith.science/api/pith-number/LEBNLNGEJMEVOEGUHGR27RGKHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY/action/storage_attestation","attest_author":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY/action/author_attestation","sign_citation":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY/action/citation_signature","submit_replication":"https://pith.science/pith/LEBNLNGEJMEVOEGUHGR27RGKHY/action/replication_record"}},"created_at":"2026-07-05T04:53:09.849706+00:00","updated_at":"2026-07-05T04:53:09.849706+00:00"}