{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IAFEBHQ52EK4A4ZD45J3KMGLXM","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":"73cbd9fc9459d6e4e50e76970cf945379bc6abafee548e5b241ebcd1965c7615","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T14:52:47Z","title_canon_sha256":"661e3a653afd183c9a1bd45cfeecdc150eb89d785a2f20510026f0d39e527d21"},"schema_version":"1.0","source":{"id":"2405.10832","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10832","created_at":"2026-07-05T08:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10832v1","created_at":"2026-07-05T08:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10832","created_at":"2026-07-05T08:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"IAFEBHQ52EK4","created_at":"2026-07-05T08:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"IAFEBHQ52EK4A4ZD","created_at":"2026-07-05T08:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"IAFEBHQ5","created_at":"2026-07-05T08:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:b0cbd208b003d52a3af583ec63a576e110aed985288ab787a10d68e5afb5b675","target":"graph","created_at":"2026-07-05T08:20:17Z","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/2405.10832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatio-temporal action detection (STAD) is an important fine-grained video understanding task. Current methods require box and label supervision for all action classes in advance. However, in real-world applications, it is very likely to come across new action classes not seen in training because the action category space is large and hard to enumerate. Also, the cost of data annotation and model training for new classes is extremely high for traditional methods, as we need to perform detailed box annotations and re-train the whole network from scratch. In this paper, we propose a new challeng","authors_text":"Gangshan Wu, Jie Qin, Limin Wang, Shuqiu Ge, Tao Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T14:52:47Z","title":"Open-Vocabulary Spatio-Temporal Action Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10832","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":"sha256:1690406782809014bde5681ce5e427184e8ce890670ed8c8261d201818843633","target":"record","created_at":"2026-07-05T08:20:17Z","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":"73cbd9fc9459d6e4e50e76970cf945379bc6abafee548e5b241ebcd1965c7615","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T14:52:47Z","title_canon_sha256":"661e3a653afd183c9a1bd45cfeecdc150eb89d785a2f20510026f0d39e527d21"},"schema_version":"1.0","source":{"id":"2405.10832","kind":"arxiv","version":1}},"canonical_sha256":"400a409e1dd115c07323e753b530cbbb3728bc13ef13930e11d40b300ed6ee56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"400a409e1dd115c07323e753b530cbbb3728bc13ef13930e11d40b300ed6ee56","first_computed_at":"2026-07-05T08:20:17.617177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:17.617177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YBn/ESXAumm3UmgZBVhE8CmV6f47OzB878qTkMFeS3NdLqxKotTWHMzzdfWHwlBw7JU1fdE2pVJ8iIsg9j6+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:17.617675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10832","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1690406782809014bde5681ce5e427184e8ce890670ed8c8261d201818843633","sha256:b0cbd208b003d52a3af583ec63a576e110aed985288ab787a10d68e5afb5b675"],"state_sha256":"0835fa064812b526aeea86effd18badf50c5c623e3fd9f18edc1d9317bfdc972"}