{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F55BY4HE66RAP2WMPFEZKJ3KJJ","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":"7308814134e06ce93b74f55121d7306ef7833660c7c3d3925c9b8e39e8186f8b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-04T09:52:17Z","title_canon_sha256":"c1a1805dc99884ab0ad80473a0a1a94132663cc46c79eee405c1f96ac15fba18"},"schema_version":"1.0","source":{"id":"2407.03788","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03788","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03788v4","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03788","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"F55BY4HE66RA","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"F55BY4HE66RAP2WM","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"F55BY4HE","created_at":"2026-07-05T09:18:27Z"}],"graph_snapshots":[{"event_id":"sha256:b141d21fa4570f6aefe76d766fb7dd2819805d9e7dd9416109cb1b03d4506b08","target":"graph","created_at":"2026-07-05T09:18:27Z","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/2407.03788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality stands at the forefront of deciding the effectiveness of video-language representation learning. However, video-text pairs in previous data typically do not align perfectly with each other, which might lead to video-language representations that do not accurately reflect cross-modal semantics. Moreover, previous data also possess an uneven distribution of concepts, thereby hampering the downstream performance across unpopular subjects. To address these problems, we propose MAMA, a new approach to learning video-language representations by utilizing a contrastive objective with a s","authors_text":"Cong-Duy Nguyen, Khoi Le, Luu Anh Tuan, See-kiong Ng, Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Yi Bin, Zhiyuan Hu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-04T09:52:17Z","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03788","kind":"arxiv","version":4},"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:a09cde1e21e0b8c2059b738f8f7ff5ba9d7179246f4d5ed0b457e323fdb05ead","target":"record","created_at":"2026-07-05T09:18:27Z","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":"7308814134e06ce93b74f55121d7306ef7833660c7c3d3925c9b8e39e8186f8b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-04T09:52:17Z","title_canon_sha256":"c1a1805dc99884ab0ad80473a0a1a94132663cc46c79eee405c1f96ac15fba18"},"schema_version":"1.0","source":{"id":"2407.03788","kind":"arxiv","version":4}},"canonical_sha256":"2f7a1c70e4f7a207eacc794995276a4a6ad7264b901fe3f60f370a231e16ceb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f7a1c70e4f7a207eacc794995276a4a6ad7264b901fe3f60f370a231e16ceb9","first_computed_at":"2026-07-05T09:18:27.904400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:27.904400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HnPBJmbj0HwfxMxFwYfMhw+UJ2LEnWyL20n4f34gHRoBsqrjnfZFiK4CdqURw2tJPJuin1lZEooHi9iEL230AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:27.904851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03788","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a09cde1e21e0b8c2059b738f8f7ff5ba9d7179246f4d5ed0b457e323fdb05ead","sha256:b141d21fa4570f6aefe76d766fb7dd2819805d9e7dd9416109cb1b03d4506b08"],"state_sha256":"bb6b0f74901d878dae40192fc4fc30c958df23b09d5f06b81ca24eccaa9b737e"}