{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BDF2UYUFHVRTDMDVIZHAESCZY7","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":"f635391979e92527ec63207e97e5338483d301b69b508607f8350637d1141732","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T09:54:21Z","title_canon_sha256":"521194edb6b3e2550d7d13b239c58c108223d338bbd29e69e588ebb05c6acd30"},"schema_version":"1.0","source":{"id":"2404.06173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06173","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06173v1","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06173","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"BDF2UYUFHVRT","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"BDF2UYUFHVRTDMDV","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"BDF2UYUF","created_at":"2026-07-05T08:06:05Z"}],"graph_snapshots":[{"event_id":"sha256:0e02aaaa5150f7af4680949c833de6dacd9216f12202323092909cd9ab6f6e6a","target":"graph","created_at":"2026-07-05T08:06:05Z","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/2404.06173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small sizes of available video-text datasets and the low quality of concept banks, which results in the failures of unseen queries and the out-of-vocabulary problem. This paper addresses these two problems by constructing a new dataset and developing a multi-word concept bank. Specifically, capitalizing on a generative model, we construct a new dataset consisting of","authors_text":"Chong-Wah Ngo, Jiaxin Wu, Wing-Kwong Chan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T09:54:21Z","title":"Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06173","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":"sha256:7716f9c57f377566e0685930177043e2c6ab80e1d1bf69cdcde4055abeb16b84","target":"record","created_at":"2026-07-05T08:06:05Z","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":"f635391979e92527ec63207e97e5338483d301b69b508607f8350637d1141732","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T09:54:21Z","title_canon_sha256":"521194edb6b3e2550d7d13b239c58c108223d338bbd29e69e588ebb05c6acd30"},"schema_version":"1.0","source":{"id":"2404.06173","kind":"arxiv","version":1}},"canonical_sha256":"08cbaa62853d6331b075464e024859c7ebb199a19a22e7d8056dcd8714a56cff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08cbaa62853d6331b075464e024859c7ebb199a19a22e7d8056dcd8714a56cff","first_computed_at":"2026-07-05T08:06:05.286068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:05.286068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hv7uz0toiWT3Bz+4KAdlx/tWa63v/8h8kX3dvfmv3cWwAESMu7GcM+Zu3VSRx54YMdwmR7t0Th1oUc0pE4iQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:05.286549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7716f9c57f377566e0685930177043e2c6ab80e1d1bf69cdcde4055abeb16b84","sha256:0e02aaaa5150f7af4680949c833de6dacd9216f12202323092909cd9ab6f6e6a"],"state_sha256":"afc4b7f83a5e3a7b1f40ab6807b2f4ff2389361c3c2a3e00fd8d616dbf37bc8c"}