{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZQNVGO4REU2VRS7CISZ72BTZMB","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":"4f414e43282130fdf8c2feb77ecb6bf79581d003365fdb0840f9ff88240c129e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T09:33:54Z","title_canon_sha256":"d370bc22c13dc733f38e8558b90ea723f2e47629288c9301855b6611b53227f6"},"schema_version":"1.0","source":{"id":"2201.04850","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04850","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04850v2","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04850","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZQNVGO4REU2V","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"ZQNVGO4REU2VRS7C","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"ZQNVGO4R","created_at":"2026-07-05T04:06:01Z"}],"graph_snapshots":[{"event_id":"sha256:a5fe4316aa586bcd00113f09ca0fd48b7cf64b259bd7a33ac64dc63c0d2edc3d","target":"graph","created_at":"2026-07-05T04:06:01Z","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/2201.04850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Q","authors_text":"Dian Li, Ping Luo, Xiaohu Qie, Xihui Liu, Ying Shan, Yixiao Ge, Yuying Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T09:33:54Z","title":"Bridging Video-text Retrieval with Multiple Choice Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04850","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":"sha256:22aafefaa18c90bd95fb47e2eda33eb306752648d4b7fa585d1260683b1d28bf","target":"record","created_at":"2026-07-05T04:06:01Z","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":"4f414e43282130fdf8c2feb77ecb6bf79581d003365fdb0840f9ff88240c129e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T09:33:54Z","title_canon_sha256":"d370bc22c13dc733f38e8558b90ea723f2e47629288c9301855b6611b53227f6"},"schema_version":"1.0","source":{"id":"2201.04850","kind":"arxiv","version":2}},"canonical_sha256":"cc1b533b91253558cbe244b3fd0679605b4794e065d1fce37127b25de84f9179","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc1b533b91253558cbe244b3fd0679605b4794e065d1fce37127b25de84f9179","first_computed_at":"2026-07-05T04:06:01.721875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:01.721875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B9QvSrS/7WrV4GBw/pkG9KhkKrrLkJMFKq/TFBhzl8ub7G5tLwbfTFmLzOgHpvvZ9y9SVLO+3hCz8jtDKlVqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:01.722384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.04850","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22aafefaa18c90bd95fb47e2eda33eb306752648d4b7fa585d1260683b1d28bf","sha256:a5fe4316aa586bcd00113f09ca0fd48b7cf64b259bd7a33ac64dc63c0d2edc3d"],"state_sha256":"22df5530d4ad3a546393ab32f50929d076ff9ebaf59a211c3d9659f77b4dcd68"}