{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QSCCG5CEWKTWMZJPV3JDTHV2IH","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":"5ec84dc29eeec2f309a139819a3bf87129c9f69f604a89bb566c79bead2cfb8f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-21T13:03:49Z","title_canon_sha256":"7eea5db5149933fb9e2ab8c4a9e211fed6c143f206b29fee6653710918b2c20d"},"schema_version":"1.0","source":{"id":"2210.11929","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11929","created_at":"2026-07-05T05:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11929v1","created_at":"2026-07-05T05:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11929","created_at":"2026-07-05T05:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"QSCCG5CEWKTW","created_at":"2026-07-05T05:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"QSCCG5CEWKTWMZJP","created_at":"2026-07-05T05:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"QSCCG5CE","created_at":"2026-07-05T05:09:07Z"}],"graph_snapshots":[{"event_id":"sha256:2235d1e395d30baf2ff98c69bf391585108cc399b543a3ec711cf13f9cce6988","target":"graph","created_at":"2026-07-05T05:09:07Z","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/2210.11929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the redundant data structure of each video. To mitigate these problems, we propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks, without heavy pre-training. To enhance the temporal modeling lacking in the image-language model, we propose to add temporal attention modules in the image encoder o","authors_text":"Chaofan Tao, Dongsheng Chen, Lifeng Shang, Lu Hou, Qun Liu, Xin Jiang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-21T13:03:49Z","title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11929","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":"sha256:7303a60b5cc850487cb617109630cdc69be378dcdb0cc31bd0a13a63f247a23d","target":"record","created_at":"2026-07-05T05:09:07Z","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":"5ec84dc29eeec2f309a139819a3bf87129c9f69f604a89bb566c79bead2cfb8f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-21T13:03:49Z","title_canon_sha256":"7eea5db5149933fb9e2ab8c4a9e211fed6c143f206b29fee6653710918b2c20d"},"schema_version":"1.0","source":{"id":"2210.11929","kind":"arxiv","version":1}},"canonical_sha256":"8484237444b2a766652faed2399eba41f0f35e3ee3a375dcccff4a9b1f1702c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8484237444b2a766652faed2399eba41f0f35e3ee3a375dcccff4a9b1f1702c5","first_computed_at":"2026-07-05T05:09:07.270741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:07.270741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kchbSPReDpwr/wPgbQ5HHipTpmL9K9w8CytcUkKGLaAg7NP5CO5yIET8CACIaTTaNxArs2qRm5RPlXd5CofOCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:07.271181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11929","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7303a60b5cc850487cb617109630cdc69be378dcdb0cc31bd0a13a63f247a23d","sha256:2235d1e395d30baf2ff98c69bf391585108cc399b543a3ec711cf13f9cce6988"],"state_sha256":"5d1b705d716ff52c3f0afb9995a5cbca5098427dbe47e45f4c8f305276778f9f"}