{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:H2PD7O2GQBT6MT2UZBK6DZ7MN7","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":"14d60e39e73871deb4e14baad504e2441a22ff2dffa710b4fb1e6318b4482a17","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-02T05:44:23Z","title_canon_sha256":"7e8754d287600e4a4cab8945234fa18cdc9b416aa51cd730881d24ee3e91a6e5"},"schema_version":"1.0","source":{"id":"2212.00986","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00986","created_at":"2026-07-05T05:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00986v2","created_at":"2026-07-05T05:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00986","created_at":"2026-07-05T05:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"H2PD7O2GQBT6","created_at":"2026-07-05T05:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"H2PD7O2GQBT6MT2U","created_at":"2026-07-05T05:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"H2PD7O2G","created_at":"2026-07-05T05:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:7de0f822311f756f22f42e3d0a9435ff466030e3cea54e5a806e46055a41c28d","target":"graph","created_at":"2026-07-05T05:22:13Z","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/2212.00986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency. Comparing conventional temporal sparse sampling, we propose to randomly mask a high ratio of spatial regions and only feed visible regions into the encoder as sparse spatial sampling. Similarly, we adopt the mask sampling technique for text inputs for consisten","authors_text":"Biaolong Chen, Fangxun Shu, Jinqiao Wang, Shuwen Xiao, Si Liu, Wenyu Sun, Xiaobo Li, Yousong Zhu, Yue Liao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-02T05:44:23Z","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00986","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":"sha256:69840626320c5e269a778879d45f9b5ece065db49b88bfc396f8302666ea4020","target":"record","created_at":"2026-07-05T05:22:13Z","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":"14d60e39e73871deb4e14baad504e2441a22ff2dffa710b4fb1e6318b4482a17","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-02T05:44:23Z","title_canon_sha256":"7e8754d287600e4a4cab8945234fa18cdc9b416aa51cd730881d24ee3e91a6e5"},"schema_version":"1.0","source":{"id":"2212.00986","kind":"arxiv","version":2}},"canonical_sha256":"3e9e3fbb468067e64f54c855e1e7ec6fe490e560e34be507aa6c1f6012fe32be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e9e3fbb468067e64f54c855e1e7ec6fe490e560e34be507aa6c1f6012fe32be","first_computed_at":"2026-07-05T05:22:13.477543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:13.477543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lZTTeCFrJHrvjtd+qVi9sHDnGqukyLZF8qvbm7Ih9OwCiv/Vxj+kbIXGlwbiBXCQwAt2PfjaYnJJSdBhKDdABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:13.477892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00986","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69840626320c5e269a778879d45f9b5ece065db49b88bfc396f8302666ea4020","sha256:7de0f822311f756f22f42e3d0a9435ff466030e3cea54e5a806e46055a41c28d"],"state_sha256":"b221fc8d7a44fa17efdb4539bbf0c3174e6f455399713c9f20e4b45b5f9da2a2"}