{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NWB7OV24C35KUNU6URVIYLD25V","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":"ec0ee129032c8574617c97f507472b78ae653d5a5f473c7b1e724a68907f6268","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","title_canon_sha256":"e6717314382ed0299b0b593fb3d5d402db8c373cda5cd83fed0aa5ce6d86f2b5"},"schema_version":"1.0","source":{"id":"2208.04215","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.04215","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"2208.04215v2","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04215","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"NWB7OV24C35K","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_16","alias_value":"NWB7OV24C35KUNU6","created_at":"2026-07-05T04:46:55Z"},{"alias_kind":"pith_short_8","alias_value":"NWB7OV24","created_at":"2026-07-05T04:46:55Z"}],"graph_snapshots":[{"event_id":"sha256:6290e716c8f6fd634bffb0adc5cc1c850af9b12a8bcccdd6f28435eedae856e6","target":"graph","created_at":"2026-07-05T04:46:55Z","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/2208.04215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual information to align video and text, whilst lacking the awareness of homogeneous high-level semantic information residing in both modalities. To fill this gap, in this work, we propose a novel visual-linguistic aligning model named HiSE for VTR, which improves the cross-modal representation by incorporating explicit high-level semantics. First, we explore th","authors_text":"Di Xu, Dongliang He, Errui Ding, Fu Li, Haoran Wang, Jungong Han, Zhong Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04215","kind":"arxiv","version":2},"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":"sha256:55c38111c0c4fe271f79f7e25752423a8583d3e48306583da4e5c19eb50be417","target":"record","created_at":"2026-07-05T04:46:55Z","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":"ec0ee129032c8574617c97f507472b78ae653d5a5f473c7b1e724a68907f6268","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T15:39:54Z","title_canon_sha256":"e6717314382ed0299b0b593fb3d5d402db8c373cda5cd83fed0aa5ce6d86f2b5"},"schema_version":"1.0","source":{"id":"2208.04215","kind":"arxiv","version":2}},"canonical_sha256":"6d83f7575c16faaa369ea46a8c2c7aed62fb98fcb889466564d886003f7d9694","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d83f7575c16faaa369ea46a8c2c7aed62fb98fcb889466564d886003f7d9694","first_computed_at":"2026-07-05T04:46:55.457326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:55.457326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ScOf55gwTKSpNKWCXancr3A0z0icXIm+Zn+SjYOs3n3+w6DWBtUBrCcgHq47La+8++P1Oj08RSX1xQJQ52gWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:55.457669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.04215","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55c38111c0c4fe271f79f7e25752423a8583d3e48306583da4e5c19eb50be417","sha256:6290e716c8f6fd634bffb0adc5cc1c850af9b12a8bcccdd6f28435eedae856e6"],"state_sha256":"c41a6ed9c12d709c26bdf08a039343e665d92fc88143a802827176b40328f405"}