{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MJSGKBLGK6CV55OOYLP2Q5OXFC","short_pith_number":"pith:MJSGKBLG","schema_version":"1.0","canonical_sha256":"626465056657855ef5cec2dfa875d728bfe448f288f17e28654cd9fe1012b120","source":{"kind":"arxiv","id":"2605.23288","version":1},"attestation_state":"computed","paper":{"title":"Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongbo Min, Jiwon Yoon, Jiyeong Kim, Yerim So","submitted_at":"2026-05-22T07:01:23Z","abstract_excerpt":"Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignment, a process that obscures local patch information and fine-grained spatio-temporal cues. We propose Similarity Volume Aggregation (SimVA), a framework that constructs a dense 4D spatio-temporal similarity volume from patch-level visual-text similarities. SimVA constructs a spatio-temporal similarity volume over local video tokens and action classes, and employs class sampling to ensure similarity aggregation scalable to large vocabularies. The"},"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":"2605.23288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T07:01:23Z","cross_cats_sorted":[],"title_canon_sha256":"a12ba3bc55f2141e62473f1233bdc8a1ca33b0288014dbad8014e6df8b53da29","abstract_canon_sha256":"663b1cad529129c20b1bce594e96a442723afa699cfa622bfd08ff4b97a5a2fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:47.406201Z","signature_b64":"2nSes/jUAdNgyYt3+jKHx6EQOvvFwACFdiQ43KjJDvpdlYZ8pqY7e6sRTlfSgGjZLmkOxlSUZ3/Uy4adQwXeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"626465056657855ef5cec2dfa875d728bfe448f288f17e28654cd9fe1012b120","last_reissued_at":"2026-05-25T02:01:47.405545Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:47.405545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongbo Min, Jiwon Yoon, Jiyeong Kim, Yerim So","submitted_at":"2026-05-22T07:01:23Z","abstract_excerpt":"Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignment, a process that obscures local patch information and fine-grained spatio-temporal cues. We propose Similarity Volume Aggregation (SimVA), a framework that constructs a dense 4D spatio-temporal similarity volume from patch-level visual-text similarities. SimVA constructs a spatio-temporal similarity volume over local video tokens and action classes, and employs class sampling to ensure similarity aggregation scalable to large vocabularies. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23288","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/2605.23288/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":"2605.23288","created_at":"2026-05-25T02:01:47.405661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23288v1","created_at":"2026-05-25T02:01:47.405661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23288","created_at":"2026-05-25T02:01:47.405661+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJSGKBLGK6CV","created_at":"2026-05-25T02:01:47.405661+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJSGKBLGK6CV55OO","created_at":"2026-05-25T02:01:47.405661+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJSGKBLG","created_at":"2026-05-25T02:01:47.405661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC","json":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC.json","graph_json":"https://pith.science/api/pith-number/MJSGKBLGK6CV55OOYLP2Q5OXFC/graph.json","events_json":"https://pith.science/api/pith-number/MJSGKBLGK6CV55OOYLP2Q5OXFC/events.json","paper":"https://pith.science/paper/MJSGKBLG"},"agent_actions":{"view_html":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC","download_json":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC.json","view_paper":"https://pith.science/paper/MJSGKBLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23288&json=true","fetch_graph":"https://pith.science/api/pith-number/MJSGKBLGK6CV55OOYLP2Q5OXFC/graph.json","fetch_events":"https://pith.science/api/pith-number/MJSGKBLGK6CV55OOYLP2Q5OXFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/action/storage_attestation","attest_author":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/action/author_attestation","sign_citation":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/action/citation_signature","submit_replication":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/action/replication_record"}},"created_at":"2026-05-25T02:01:47.405661+00:00","updated_at":"2026-05-25T02:01:47.405661+00:00"}