{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3526D6TCLWPFLTJXZBAHX4BZIQ","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":"e30b673a4ced53ca8774d6d6ee09f93e85480aaf17339842fa26439e12363da4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T04:54:39Z","title_canon_sha256":"7cd46eb489df05471387bec8c9083725d65cd663f4b5eb6cd85eab68e0f29a57"},"schema_version":"1.0","source":{"id":"2407.05610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05610","created_at":"2026-07-05T08:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05610v1","created_at":"2026-07-05T08:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05610","created_at":"2026-07-05T08:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"3526D6TCLWPF","created_at":"2026-07-05T08:41:16Z"},{"alias_kind":"pith_short_16","alias_value":"3526D6TCLWPFLTJX","created_at":"2026-07-05T08:41:16Z"},{"alias_kind":"pith_short_8","alias_value":"3526D6TC","created_at":"2026-07-05T08:41:16Z"}],"graph_snapshots":[{"event_id":"sha256:a77e7cbb2d1a8c540cfb145f14e3565bc9d6d99db320a0d1a9152fa9f6d9441e","target":"graph","created_at":"2026-07-05T08:41:16Z","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/2407.05610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting visual content on language expression has become an emerging topic in the community. However, in the video domain, the existing setting, i.e., spatial-temporal video grounding (STVG), is formulated to only detect one pre-existing object in each frame, ignoring the fact that language descriptions can involve none or multiple entities within a video. In this work, we advance the STVG to a more practical setting called described spatial-temporal video detection (DSTVD) by overcoming the above limitation. To facilitate the exploration of DSTVD, we first introduce a new benchmark, namely ","authors_text":"Ammar Nuwanna, Jiajun Deng, Lina Wei, Mengyao Qiu, Roger Zimmermann, Wei Ji, Xiangyan Liu, Yingfei Sun, You Qin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T04:54:39Z","title":"Described Spatial-Temporal Video Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05610","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":"sha256:7c5343b0eb1599f7a0378489c62e7b2b4f1e54e2e2f82d92bb5b56dba849ceb5","target":"record","created_at":"2026-07-05T08:41:16Z","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":"e30b673a4ced53ca8774d6d6ee09f93e85480aaf17339842fa26439e12363da4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T04:54:39Z","title_canon_sha256":"7cd46eb489df05471387bec8c9083725d65cd663f4b5eb6cd85eab68e0f29a57"},"schema_version":"1.0","source":{"id":"2407.05610","kind":"arxiv","version":1}},"canonical_sha256":"df75e1fa625d9e55cd37c8407bf039440fb5611ff9b0227753f9e56a4aca6569","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df75e1fa625d9e55cd37c8407bf039440fb5611ff9b0227753f9e56a4aca6569","first_computed_at":"2026-07-05T08:41:16.150462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:16.150462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S3cu06TZ9btGlqw9gJHDYqagsy3NaS6buBwWwUWswWqn3HpNhoGb5NZt3SRnPhHVE+/XC+l4oS69eIDPAUGoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:16.150956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c5343b0eb1599f7a0378489c62e7b2b4f1e54e2e2f82d92bb5b56dba849ceb5","sha256:a77e7cbb2d1a8c540cfb145f14e3565bc9d6d99db320a0d1a9152fa9f6d9441e"],"state_sha256":"9886e0fa2cb9f1dc44cedad8f49c91ec8c97a9d968134cd7771aaf7ccc6ede56"}