{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZQNVGO4REU2VRS7CISZ72BTZMB","short_pith_number":"pith:ZQNVGO4R","canonical_record":{"source":{"id":"2201.04850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T09:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"d370bc22c13dc733f38e8558b90ea723f2e47629288c9301855b6611b53227f6","abstract_canon_sha256":"4f414e43282130fdf8c2feb77ecb6bf79581d003365fdb0840f9ff88240c129e"},"schema_version":"1.0"},"canonical_sha256":"cc1b533b91253558cbe244b3fd0679605b4794e065d1fce37127b25de84f9179","source":{"kind":"arxiv","id":"2201.04850","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZQNVGO4REU2VRS7CISZ72BTZMB","target":"record","payload":{"canonical_record":{"source":{"id":"2201.04850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T09:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"d370bc22c13dc733f38e8558b90ea723f2e47629288c9301855b6611b53227f6","abstract_canon_sha256":"4f414e43282130fdf8c2feb77ecb6bf79581d003365fdb0840f9ff88240c129e"},"schema_version":"1.0"},"canonical_sha256":"cc1b533b91253558cbe244b3fd0679605b4794e065d1fce37127b25de84f9179","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:01.722384Z","signature_b64":"B9QvSrS/7WrV4GBw/pkG9KhkKrrLkJMFKq/TFBhzl8ub7G5tLwbfTFmLzOgHpvvZ9y9SVLO+3hCz8jtDKlVqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc1b533b91253558cbe244b3fd0679605b4794e065d1fce37127b25de84f9179","last_reissued_at":"2026-07-05T04:06:01.721875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:01.721875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.04850","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7BPEFdqRFJIZ+PtZcQTq+Bh7z8R8fl1gbhwhO3zkW//O+VMEbWeOTj3IT2KLkfSsIQ3Gb+vYuIA513rufXsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:54:02.645447Z"},"content_sha256":"22aafefaa18c90bd95fb47e2eda33eb306752648d4b7fa585d1260683b1d28bf","schema_version":"1.0","event_id":"sha256:22aafefaa18c90bd95fb47e2eda33eb306752648d4b7fa585d1260683b1d28bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZQNVGO4REU2VRS7CISZ72BTZMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Video-text Retrieval with Multiple Choice Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Li, Ping Luo, Xiaohu Qie, Xihui Liu, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2022-01-13T09:33:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04850","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.04850/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oLRnV1ZZMsuXnlsTeUWAsJ4QKwFSTSMiBUoF6rNR1vRoVfRsakWG/yC6WGRQBzAPBqX11PCYPIIDLK7uatl5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:54:02.645980Z"},"content_sha256":"a5fe4316aa586bcd00113f09ca0fd48b7cf64b259bd7a33ac64dc63c0d2edc3d","schema_version":"1.0","event_id":"sha256:a5fe4316aa586bcd00113f09ca0fd48b7cf64b259bd7a33ac64dc63c0d2edc3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/bundle.json","state_url":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T19:54:02Z","links":{"resolver":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB","bundle":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/bundle.json","state":"https://pith.science/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQNVGO4REU2VRS7CISZ72BTZMB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vEMw1QGiyPj14l/Qtx1AMI/qPESm2y9Hqv+5h6hn0t+qszHrcFee31aNYA1hRsvQJzvbKNEzfgAi/q3rZpAuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:54:02.651512Z","bundle_sha256":"0b8be89ff91a92f7bfa0d697add9f0ee92c57904724cfdb9f4035dc5575cd0b2"}}