{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F55BY4HE66RAP2WMPFEZKJ3KJJ","short_pith_number":"pith:F55BY4HE","schema_version":"1.0","canonical_sha256":"2f7a1c70e4f7a207eacc794995276a4a6ad7264b901fe3f60f370a231e16ceb9","source":{"kind":"arxiv","id":"2407.03788","version":4},"attestation_state":"computed","paper":{"title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Cong-Duy Nguyen, Khoi Le, Luu Anh Tuan, See-kiong Ng, Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Yi Bin, Zhiyuan Hu","submitted_at":"2024-07-04T09:52:17Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.03788","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-04T09:52:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c1a1805dc99884ab0ad80473a0a1a94132663cc46c79eee405c1f96ac15fba18","abstract_canon_sha256":"7308814134e06ce93b74f55121d7306ef7833660c7c3d3925c9b8e39e8186f8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:27.904851Z","signature_b64":"HnPBJmbj0HwfxMxFwYfMhw+UJ2LEnWyL20n4f34gHRoBsqrjnfZFiK4CdqURw2tJPJuin1lZEooHi9iEL230AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f7a1c70e4f7a207eacc794995276a4a6ad7264b901fe3f60f370a231e16ceb9","last_reissued_at":"2026-07-05T09:18:27.904400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:27.904400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Cong-Duy Nguyen, Khoi Le, Luu Anh Tuan, See-kiong Ng, Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Yi Bin, Zhiyuan Hu","submitted_at":"2024-07-04T09:52:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03788","kind":"arxiv","version":4},"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/2407.03788/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.03788","created_at":"2026-07-05T09:18:27.904454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03788v4","created_at":"2026-07-05T09:18:27.904454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03788","created_at":"2026-07-05T09:18:27.904454+00:00"},{"alias_kind":"pith_short_12","alias_value":"F55BY4HE66RA","created_at":"2026-07-05T09:18:27.904454+00:00"},{"alias_kind":"pith_short_16","alias_value":"F55BY4HE66RAP2WM","created_at":"2026-07-05T09:18:27.904454+00:00"},{"alias_kind":"pith_short_8","alias_value":"F55BY4HE","created_at":"2026-07-05T09:18:27.904454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.07160","citing_title":"Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ","json":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ.json","graph_json":"https://pith.science/api/pith-number/F55BY4HE66RAP2WMPFEZKJ3KJJ/graph.json","events_json":"https://pith.science/api/pith-number/F55BY4HE66RAP2WMPFEZKJ3KJJ/events.json","paper":"https://pith.science/paper/F55BY4HE"},"agent_actions":{"view_html":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ","download_json":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ.json","view_paper":"https://pith.science/paper/F55BY4HE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03788&json=true","fetch_graph":"https://pith.science/api/pith-number/F55BY4HE66RAP2WMPFEZKJ3KJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/F55BY4HE66RAP2WMPFEZKJ3KJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ/action/storage_attestation","attest_author":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ/action/author_attestation","sign_citation":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ/action/citation_signature","submit_replication":"https://pith.science/pith/F55BY4HE66RAP2WMPFEZKJ3KJJ/action/replication_record"}},"created_at":"2026-07-05T09:18:27.904454+00:00","updated_at":"2026-07-05T09:18:27.904454+00:00"}