{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ELYAVGF34BB6C26EG6BHCMGJEB","short_pith_number":"pith:ELYAVGF3","schema_version":"1.0","canonical_sha256":"22f00a98bbe043e16bc437827130c9204c3c63389ac675469b36ab59cf15367e","source":{"kind":"arxiv","id":"2501.14945","version":1},"attestation_state":"computed","paper":{"title":"MATCHA:Towards Matching Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Xue, Laura Leal-Taix\\'e, Qunjie Zhou, Sven Elflein","submitted_at":"2025-01-24T22:10:45Z","abstract_excerpt":"Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific correspondence types, geometric, semantic, or temporal, whereas humans naturally identify alignments across these domains. Inspired by this flexibility, we propose MATCHA, a unified feature model designed to ``rule them all'', establishing robust correspondences across diverse matching tasks. Building on insights that diffusion model features can encode multiple correspo"},"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":"2501.14945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T22:10:45Z","cross_cats_sorted":[],"title_canon_sha256":"a437854824e0971acf85b75dec4f697ad4c6d59955077244e82f8912a0cf8e60","abstract_canon_sha256":"5de505e18e51e40e3f1cc2c3c042f40144529e79aa605e5d92cd5601038da27f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:21.224455Z","signature_b64":"6xJZ7s1BzX5BgV6bpCoVQyymM6dIN32n3K+/LnWnm9xW/7hrz56tvZUrTazfailKciaBbCMNXShgb9onQ9tBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22f00a98bbe043e16bc437827130c9204c3c63389ac675469b36ab59cf15367e","last_reissued_at":"2026-07-05T10:05:21.223921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:21.223921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MATCHA:Towards Matching Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Xue, Laura Leal-Taix\\'e, Qunjie Zhou, Sven Elflein","submitted_at":"2025-01-24T22:10:45Z","abstract_excerpt":"Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific correspondence types, geometric, semantic, or temporal, whereas humans naturally identify alignments across these domains. Inspired by this flexibility, we propose MATCHA, a unified feature model designed to ``rule them all'', establishing robust correspondences across diverse matching tasks. Building on insights that diffusion model features can encode multiple correspo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14945","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/2501.14945/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":"2501.14945","created_at":"2026-07-05T10:05:21.223984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14945v1","created_at":"2026-07-05T10:05:21.223984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14945","created_at":"2026-07-05T10:05:21.223984+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELYAVGF34BB6","created_at":"2026-07-05T10:05:21.223984+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELYAVGF34BB6C26E","created_at":"2026-07-05T10:05:21.223984+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELYAVGF3","created_at":"2026-07-05T10:05:21.223984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30093","citing_title":"Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB","json":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB.json","graph_json":"https://pith.science/api/pith-number/ELYAVGF34BB6C26EG6BHCMGJEB/graph.json","events_json":"https://pith.science/api/pith-number/ELYAVGF34BB6C26EG6BHCMGJEB/events.json","paper":"https://pith.science/paper/ELYAVGF3"},"agent_actions":{"view_html":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB","download_json":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB.json","view_paper":"https://pith.science/paper/ELYAVGF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14945&json=true","fetch_graph":"https://pith.science/api/pith-number/ELYAVGF34BB6C26EG6BHCMGJEB/graph.json","fetch_events":"https://pith.science/api/pith-number/ELYAVGF34BB6C26EG6BHCMGJEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB/action/storage_attestation","attest_author":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB/action/author_attestation","sign_citation":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB/action/citation_signature","submit_replication":"https://pith.science/pith/ELYAVGF34BB6C26EG6BHCMGJEB/action/replication_record"}},"created_at":"2026-07-05T10:05:21.223984+00:00","updated_at":"2026-07-05T10:05:21.223984+00:00"}