{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MJSGKBLGK6CV55OOYLP2Q5OXFC","short_pith_number":"pith:MJSGKBLG","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"},"canonical_sha256":"626465056657855ef5cec2dfa875d728bfe448f288f17e28654cd9fe1012b120","source":{"kind":"arxiv","id":"2605.23288","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23288","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23288v1","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23288","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"MJSGKBLGK6CV","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"MJSGKBLGK6CV55OO","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"MJSGKBLG","created_at":"2026-05-25T02:01:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MJSGKBLGK6CV55OOYLP2Q5OXFC","target":"record","payload":{"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"},"canonical_sha256":"626465056657855ef5cec2dfa875d728bfe448f288f17e28654cd9fe1012b120","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"},"source_kind":"arxiv","source_id":"2605.23288","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQJSWZenoBc8pn31mlmAFrxK5izzrM7rTNqkETfXWcKUrQTD+85Ql+MKipXdxtQ9bP12Auo7Pf6eoYowUCItAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:10:06.988611Z"},"content_sha256":"1d97fb3855d76a8dfc27f048216337cc305652be6546d7cb2e2ce1fd120c89f7","schema_version":"1.0","event_id":"sha256:1d97fb3855d76a8dfc27f048216337cc305652be6546d7cb2e2ce1fd120c89f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MJSGKBLGK6CV55OOYLP2Q5OXFC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKf51+4lmJjTcXpaf2pzfkDdZGDcWI5h9c6jknOUUkxGUAYpRQ4An+eT6H8ZDQpDe/BcNWEkuQBaUaM40XZ8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:10:06.989463Z"},"content_sha256":"2984e5462cc45d73725137bf5a69f227cc84ecc9cfa1918e886f8441d2858960","schema_version":"1.0","event_id":"sha256:2984e5462cc45d73725137bf5a69f227cc84ecc9cfa1918e886f8441d2858960"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/bundle.json","state_url":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T18:10:06Z","links":{"resolver":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC","bundle":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/bundle.json","state":"https://pith.science/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJSGKBLGK6CV55OOYLP2Q5OXFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MJSGKBLGK6CV55OOYLP2Q5OXFC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"663b1cad529129c20b1bce594e96a442723afa699cfa622bfd08ff4b97a5a2fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T07:01:23Z","title_canon_sha256":"a12ba3bc55f2141e62473f1233bdc8a1ca33b0288014dbad8014e6df8b53da29"},"schema_version":"1.0","source":{"id":"2605.23288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23288","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23288v1","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23288","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"MJSGKBLGK6CV","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"MJSGKBLGK6CV55OO","created_at":"2026-05-25T02:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"MJSGKBLG","created_at":"2026-05-25T02:01:47Z"}],"graph_snapshots":[{"event_id":"sha256:2984e5462cc45d73725137bf5a69f227cc84ecc9cfa1918e886f8441d2858960","target":"graph","created_at":"2026-05-25T02:01:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.23288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongbo Min, Jiwon Yoon, Jiyeong Kim, Yerim So","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T07:01:23Z","title":"Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23288","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d97fb3855d76a8dfc27f048216337cc305652be6546d7cb2e2ce1fd120c89f7","target":"record","created_at":"2026-05-25T02:01:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"663b1cad529129c20b1bce594e96a442723afa699cfa622bfd08ff4b97a5a2fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T07:01:23Z","title_canon_sha256":"a12ba3bc55f2141e62473f1233bdc8a1ca33b0288014dbad8014e6df8b53da29"},"schema_version":"1.0","source":{"id":"2605.23288","kind":"arxiv","version":1}},"canonical_sha256":"626465056657855ef5cec2dfa875d728bfe448f288f17e28654cd9fe1012b120","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"626465056657855ef5cec2dfa875d728bfe448f288f17e28654cd9fe1012b120","first_computed_at":"2026-05-25T02:01:47.405545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:47.405545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2nSes/jUAdNgyYt3+jKHx6EQOvvFwACFdiQ43KjJDvpdlYZ8pqY7e6sRTlfSgGjZLmkOxlSUZ3/Uy4adQwXeDg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:47.406201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d97fb3855d76a8dfc27f048216337cc305652be6546d7cb2e2ce1fd120c89f7","sha256:2984e5462cc45d73725137bf5a69f227cc84ecc9cfa1918e886f8441d2858960"],"state_sha256":"b466429dddaad2aa2cb2e2f1ed66128e1dffcedec7a50cab6a0594613a185e11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dpJGRyDhP7llxspxTydlIBPXUo5fs6voU7QzX2cAG0iOPvOvq5YmxMD5OSLWPxpRNTwAwIz5SzlLMYvDLJgpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:10:06.992915Z","bundle_sha256":"7386bb821b8394e573e85ef398f200fe98dd2d3775ced45497dedbcae1a18383"}}