{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IVMHFG5NWZ2U5L326U4NS7LADE","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":"0fe52da4d5f4c8b3619507298512f946a235f095867e5b2ae630823639181404","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-16T09:38:52Z","title_canon_sha256":"9ade4a014bd4b9ec97e46048e8436e1b294a2a331a8f9978febc770b8c957260"},"schema_version":"1.0","source":{"id":"2207.07885","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07885","created_at":"2026-07-05T05:26:45Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07885v3","created_at":"2026-07-05T05:26:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07885","created_at":"2026-07-05T05:26:45Z"},{"alias_kind":"pith_short_12","alias_value":"IVMHFG5NWZ2U","created_at":"2026-07-05T05:26:45Z"},{"alias_kind":"pith_short_16","alias_value":"IVMHFG5NWZ2U5L32","created_at":"2026-07-05T05:26:45Z"},{"alias_kind":"pith_short_8","alias_value":"IVMHFG5N","created_at":"2026-07-05T05:26:45Z"}],"graph_snapshots":[{"event_id":"sha256:e162180faf5dfff9ea43882b3f5e00ac74558a77cbbde2fb8fe6e2333a514782","target":"graph","created_at":"2026-07-05T05:26:45Z","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/2207.07885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building a universal Video-Language model for solving various video understanding tasks (\\emph{e.g.}, text-video retrieval, video question answering) is an open challenge to the machine learning field. Towards this goal, most recent works build the model by stacking uni-modal and cross-modal feature encoders and train it with pair-wise contrastive pre-text tasks. Though offering attractive generality, the resulted models have to compromise between efficiency and performance. They mostly adopt different architectures to deal with different downstream tasks. We find this is because the pair-wise","authors_text":"Jiashi Feng, Jingjia Huang, Rongrong Ji, Xiaoshuai Sun, Xinglong Wu, Yinan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-16T09:38:52Z","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07885","kind":"arxiv","version":3},"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":"sha256:5a614a523047f8257e368ad8a79fe40ee78076d3a248961387224eceb1b2fd15","target":"record","created_at":"2026-07-05T05:26:45Z","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":"0fe52da4d5f4c8b3619507298512f946a235f095867e5b2ae630823639181404","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-16T09:38:52Z","title_canon_sha256":"9ade4a014bd4b9ec97e46048e8436e1b294a2a331a8f9978febc770b8c957260"},"schema_version":"1.0","source":{"id":"2207.07885","kind":"arxiv","version":3}},"canonical_sha256":"4558729badb6754eaf7af538d97d6019125aff8ac33689709b70826b3e4c1774","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4558729badb6754eaf7af538d97d6019125aff8ac33689709b70826b3e4c1774","first_computed_at":"2026-07-05T05:26:45.525127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:45.525127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kf1eSJiJOKV2v6MrRCPb9Y8N1VjH+IJubSAxuZ3vDi2GzxvliBaPSHmA2hwqah32v0kdc6EN6QUSeIOVpTgPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:45.525694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07885","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a614a523047f8257e368ad8a79fe40ee78076d3a248961387224eceb1b2fd15","sha256:e162180faf5dfff9ea43882b3f5e00ac74558a77cbbde2fb8fe6e2333a514782"],"state_sha256":"fce24abc0e1ff370cb6fe484c1ce315d012cf0125d69f1902a27a26362bdb737"}