{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YCAELD2S5GA3BDH4QSDSWIZ4PU","short_pith_number":"pith:YCAELD2S","schema_version":"1.0","canonical_sha256":"c080458f52e981b08cfc84872b233c7d0343c873cc38a5e9ffabb45249441e08","source":{"kind":"arxiv","id":"2312.06699","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Dabouei, Bishmoy Paul, Min Xu, Najibul Haque Sarker, Rahul Pratap Singh, Zaber Ibn Abdul Hakim","submitted_at":"2023-12-10T02:03:51Z","abstract_excerpt":"A thorough comprehension of textual data is a fundamental element in multi-modal video analysis tasks. However, recent works have shown that the current models do not achieve a comprehensive understanding of the textual data during the training for the target downstream tasks. Orthogonal to the previous approaches to this limitation, we postulate that understanding the significance of the sentence components according to the target task can potentially enhance the performance of the models. Hence, we utilize the knowledge of a pre-trained large language model (LLM) to generate text samples fro"},"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":"2312.06699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-10T02:03:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c93fa7cf66f2041c912728f296f39e7afdb0dac1a3132c95c6b55e3379f0a45","abstract_canon_sha256":"67a34d6bbe3b20e561cef48aa2ed11b4e10e6e9c0e0811a8e01e6f46ebcd7279"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:51.728956Z","signature_b64":"0vKPN0ykjozFjlQrXzVFx9si/T6Dqp4rWdh/MqZejfeCzgcb1DM7MsJ/hU+Bp8L+DBIt0qYtwvBTbYCbWPa5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c080458f52e981b08cfc84872b233c7d0343c873cc38a5e9ffabb45249441e08","last_reissued_at":"2026-07-05T07:22:51.728483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:51.728483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Dabouei, Bishmoy Paul, Min Xu, Najibul Haque Sarker, Rahul Pratap Singh, Zaber Ibn Abdul Hakim","submitted_at":"2023-12-10T02:03:51Z","abstract_excerpt":"A thorough comprehension of textual data is a fundamental element in multi-modal video analysis tasks. However, recent works have shown that the current models do not achieve a comprehensive understanding of the textual data during the training for the target downstream tasks. Orthogonal to the previous approaches to this limitation, we postulate that understanding the significance of the sentence components according to the target task can potentially enhance the performance of the models. Hence, we utilize the knowledge of a pre-trained large language model (LLM) to generate text samples fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06699","kind":"arxiv","version":1},"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/2312.06699/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":"2312.06699","created_at":"2026-07-05T07:22:51.728543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06699v1","created_at":"2026-07-05T07:22:51.728543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06699","created_at":"2026-07-05T07:22:51.728543+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCAELD2S5GA3","created_at":"2026-07-05T07:22:51.728543+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCAELD2S5GA3BDH4","created_at":"2026-07-05T07:22:51.728543+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCAELD2S","created_at":"2026-07-05T07:22:51.728543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19234","citing_title":"Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU","json":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU.json","graph_json":"https://pith.science/api/pith-number/YCAELD2S5GA3BDH4QSDSWIZ4PU/graph.json","events_json":"https://pith.science/api/pith-number/YCAELD2S5GA3BDH4QSDSWIZ4PU/events.json","paper":"https://pith.science/paper/YCAELD2S"},"agent_actions":{"view_html":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU","download_json":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU.json","view_paper":"https://pith.science/paper/YCAELD2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06699&json=true","fetch_graph":"https://pith.science/api/pith-number/YCAELD2S5GA3BDH4QSDSWIZ4PU/graph.json","fetch_events":"https://pith.science/api/pith-number/YCAELD2S5GA3BDH4QSDSWIZ4PU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU/action/storage_attestation","attest_author":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU/action/author_attestation","sign_citation":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU/action/citation_signature","submit_replication":"https://pith.science/pith/YCAELD2S5GA3BDH4QSDSWIZ4PU/action/replication_record"}},"created_at":"2026-07-05T07:22:51.728543+00:00","updated_at":"2026-07-05T07:22:51.728543+00:00"}