{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RNMJZEHONJ4TVWGZ5SEAL4RCMB","short_pith_number":"pith:RNMJZEHO","schema_version":"1.0","canonical_sha256":"8b589c90ee6a793ad8d9ec8805f222604fa687538e5c49fec7ac986dc5520ad9","source":{"kind":"arxiv","id":"2006.14613","version":2},"attestation_state":"computed","paper":{"title":"Space-Time Correspondence as a Contrastive Random Walk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Allan Jabri, Andrew Owens","submitted_at":"2020-06-25T17:56:05Z","abstract_excerpt":"This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a space-time graph constructed from video. In this graph, the nodes are patches sampled from each frame, and nodes adjacent in time can share a directed edge. We learn a representation in which pairwise similarity defines transition probability of a random walk, so that long-range correspondence is computed as a walk along the graph. We optimize the representation to place high probability along paths of similarity. Targe"},"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":"2006.14613","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-25T17:56:05Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"3900fa94b3e03ffa7667c34e390bdb950704a56ecbbe3649265debca978678b7","abstract_canon_sha256":"3c71b4b12d3afb49f599a343bf898689019a3b3d6f57fbe72bf14fbbe96f4a2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:42.789717Z","signature_b64":"JfejHWRFjfTo4XrkgfBw1vEegxc4OWAFcaf4KHjAvCKHxEK6KyAIbgXHjfc1yaCD6I/3SBmmIEEfzTc8c5j/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b589c90ee6a793ad8d9ec8805f222604fa687538e5c49fec7ac986dc5520ad9","last_reissued_at":"2026-07-05T01:56:42.789281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:42.789281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Space-Time Correspondence as a Contrastive Random Walk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Allan Jabri, Andrew Owens","submitted_at":"2020-06-25T17:56:05Z","abstract_excerpt":"This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a space-time graph constructed from video. In this graph, the nodes are patches sampled from each frame, and nodes adjacent in time can share a directed edge. We learn a representation in which pairwise similarity defines transition probability of a random walk, so that long-range correspondence is computed as a walk along the graph. We optimize the representation to place high probability along paths of similarity. Targe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14613","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/2006.14613/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":"2006.14613","created_at":"2026-07-05T01:56:42.789341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14613v2","created_at":"2026-07-05T01:56:42.789341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14613","created_at":"2026-07-05T01:56:42.789341+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNMJZEHONJ4T","created_at":"2026-07-05T01:56:42.789341+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNMJZEHONJ4TVWGZ","created_at":"2026-07-05T01:56:42.789341+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNMJZEHO","created_at":"2026-07-05T01:56:42.789341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2203.12601","citing_title":"R3M: A Universal Visual Representation for Robot Manipulation","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB","json":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB.json","graph_json":"https://pith.science/api/pith-number/RNMJZEHONJ4TVWGZ5SEAL4RCMB/graph.json","events_json":"https://pith.science/api/pith-number/RNMJZEHONJ4TVWGZ5SEAL4RCMB/events.json","paper":"https://pith.science/paper/RNMJZEHO"},"agent_actions":{"view_html":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB","download_json":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB.json","view_paper":"https://pith.science/paper/RNMJZEHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14613&json=true","fetch_graph":"https://pith.science/api/pith-number/RNMJZEHONJ4TVWGZ5SEAL4RCMB/graph.json","fetch_events":"https://pith.science/api/pith-number/RNMJZEHONJ4TVWGZ5SEAL4RCMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB/action/storage_attestation","attest_author":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB/action/author_attestation","sign_citation":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB/action/citation_signature","submit_replication":"https://pith.science/pith/RNMJZEHONJ4TVWGZ5SEAL4RCMB/action/replication_record"}},"created_at":"2026-07-05T01:56:42.789341+00:00","updated_at":"2026-07-05T01:56:42.789341+00:00"}