{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IF4OBXMSMWILE6UZYK52J6DVT4","short_pith_number":"pith:IF4OBXMS","schema_version":"1.0","canonical_sha256":"4178e0dd926590b27a99c2bba4f8759f2baf0470679d383a0218615fa9d0a46e","source":{"kind":"arxiv","id":"1911.11763","version":2},"attestation_state":"computed","paper":{"title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Rabinovich, Daniel DeTone, Paul-Edouard Sarlin, Tomasz Malisiewicz","submitted_at":"2019-11-26T18:57:21Z","abstract_excerpt":"This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D wo"},"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":"1911.11763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-26T18:57:21Z","cross_cats_sorted":[],"title_canon_sha256":"a57116cb44ec6cdb5cf74e657dda9dc2df57286d75cd62fe1b2e80088e5a82dd","abstract_canon_sha256":"655a69af10786644651ea85dd8f670c636a48bf9463ebdc5215d1ad2688ba04c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:04.948205Z","signature_b64":"2gZDdkFYttGog5nU+H1+lHWc6xMiaRXfuZZ1fwh5Blchl0LE4kLq/upwzszJshayDYZssEem+0zRoU6TN4raDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4178e0dd926590b27a99c2bba4f8759f2baf0470679d383a0218615fa9d0a46e","last_reissued_at":"2026-07-05T00:51:04.947756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:04.947756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Rabinovich, Daniel DeTone, Paul-Edouard Sarlin, Tomasz Malisiewicz","submitted_at":"2019-11-26T18:57:21Z","abstract_excerpt":"This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11763","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/1911.11763/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":"1911.11763","created_at":"2026-07-05T00:51:04.947813+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.11763v2","created_at":"2026-07-05T00:51:04.947813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11763","created_at":"2026-07-05T00:51:04.947813+00:00"},{"alias_kind":"pith_short_12","alias_value":"IF4OBXMSMWIL","created_at":"2026-07-05T00:51:04.947813+00:00"},{"alias_kind":"pith_short_16","alias_value":"IF4OBXMSMWILE6UZ","created_at":"2026-07-05T00:51:04.947813+00:00"},{"alias_kind":"pith_short_8","alias_value":"IF4OBXMS","created_at":"2026-07-05T00:51:04.947813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01757","citing_title":"DL-VINS-Factory: A Modular Framework for Learned Visual Front-Ends in Visual-Inertial SLAM","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30399","citing_title":"A Novel Computer Vision Approach for Assessing Fish Responses to Intrusive Objects in Aquaculture","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17434","citing_title":"Leveraging AV1 motion vectors for Fast and Dense Feature Matching","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4","json":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4.json","graph_json":"https://pith.science/api/pith-number/IF4OBXMSMWILE6UZYK52J6DVT4/graph.json","events_json":"https://pith.science/api/pith-number/IF4OBXMSMWILE6UZYK52J6DVT4/events.json","paper":"https://pith.science/paper/IF4OBXMS"},"agent_actions":{"view_html":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4","download_json":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4.json","view_paper":"https://pith.science/paper/IF4OBXMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.11763&json=true","fetch_graph":"https://pith.science/api/pith-number/IF4OBXMSMWILE6UZYK52J6DVT4/graph.json","fetch_events":"https://pith.science/api/pith-number/IF4OBXMSMWILE6UZYK52J6DVT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4/action/storage_attestation","attest_author":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4/action/author_attestation","sign_citation":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4/action/citation_signature","submit_replication":"https://pith.science/pith/IF4OBXMSMWILE6UZYK52J6DVT4/action/replication_record"}},"created_at":"2026-07-05T00:51:04.947813+00:00","updated_at":"2026-07-05T00:51:04.947813+00:00"}