{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M43VZBEVWYTDYBSKAVXIC627BC","short_pith_number":"pith:M43VZBEV","schema_version":"1.0","canonical_sha256":"67375c8495b6263c064a056e817b5f08b7f17dd2d4fe8f1f94a1aea2b881d4ce","source":{"kind":"arxiv","id":"2501.07556","version":1},"attestation_state":"computed","paper":{"title":"MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongli Tan, Hao Yu, Hujun Bao, Sida Peng, Xiaowei Zhou, Xingyi He, Zehong Shen","submitted_at":"2025-01-13T18:37:36Z","abstract_excerpt":"Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image matching algorithms have dramatically outperformed humans in rapidly and accurately finding large amounts of correspondences. However, when dealing with images captured under different imaging modalities that result in significant appearance changes, the performance of these algorithms often deteriorates due to the scarcity of annotated cross-modal training data. "},"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":"2501.07556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T18:37:36Z","cross_cats_sorted":[],"title_canon_sha256":"9cca1c87da406be65b173045575e8cffb7dd9bc6eefba721edd0eb17e35e41fb","abstract_canon_sha256":"3b169a7eca31c682d332cb4c89dc8d03a9cfad5517bdb82b62128f83c266139f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:30.152558Z","signature_b64":"7kmCztyev0gf8lcpnN2+Wt/ZKBcuh3g2yRy5wdCZg61jo/Iyaf4WVPKXvxqHkT/QSF+ZEnD0foDqjLe+bJs7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67375c8495b6263c064a056e817b5f08b7f17dd2d4fe8f1f94a1aea2b881d4ce","last_reissued_at":"2026-07-05T10:00:30.152023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:30.152023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongli Tan, Hao Yu, Hujun Bao, Sida Peng, Xiaowei Zhou, Xingyi He, Zehong Shen","submitted_at":"2025-01-13T18:37:36Z","abstract_excerpt":"Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image matching algorithms have dramatically outperformed humans in rapidly and accurately finding large amounts of correspondences. However, when dealing with images captured under different imaging modalities that result in significant appearance changes, the performance of these algorithms often deteriorates due to the scarcity of annotated cross-modal training data. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07556","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/2501.07556/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":"2501.07556","created_at":"2026-07-05T10:00:30.152088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07556v1","created_at":"2026-07-05T10:00:30.152088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07556","created_at":"2026-07-05T10:00:30.152088+00:00"},{"alias_kind":"pith_short_12","alias_value":"M43VZBEVWYTD","created_at":"2026-07-05T10:00:30.152088+00:00"},{"alias_kind":"pith_short_16","alias_value":"M43VZBEVWYTDYBSK","created_at":"2026-07-05T10:00:30.152088+00:00"},{"alias_kind":"pith_short_8","alias_value":"M43VZBEV","created_at":"2026-07-05T10:00:30.152088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31077","citing_title":"AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31077","citing_title":"AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30492","citing_title":"RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18744","citing_title":"Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10217","citing_title":"Are Pretrained Image Matchers Good Enough for SAR-Optical Satellite Registration?","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC","json":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC.json","graph_json":"https://pith.science/api/pith-number/M43VZBEVWYTDYBSKAVXIC627BC/graph.json","events_json":"https://pith.science/api/pith-number/M43VZBEVWYTDYBSKAVXIC627BC/events.json","paper":"https://pith.science/paper/M43VZBEV"},"agent_actions":{"view_html":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC","download_json":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC.json","view_paper":"https://pith.science/paper/M43VZBEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07556&json=true","fetch_graph":"https://pith.science/api/pith-number/M43VZBEVWYTDYBSKAVXIC627BC/graph.json","fetch_events":"https://pith.science/api/pith-number/M43VZBEVWYTDYBSKAVXIC627BC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC/action/storage_attestation","attest_author":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC/action/author_attestation","sign_citation":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC/action/citation_signature","submit_replication":"https://pith.science/pith/M43VZBEVWYTDYBSKAVXIC627BC/action/replication_record"}},"created_at":"2026-07-05T10:00:30.152088+00:00","updated_at":"2026-07-05T10:00:30.152088+00:00"}