{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TOB27274W4V7YNAXUBJPPMVDNY","short_pith_number":"pith:TOB27274","schema_version":"1.0","canonical_sha256":"9b83afebfcb72bfc3417a052f7b2a36e3c833677c8ebb0eade66a43b1df158b7","source":{"kind":"arxiv","id":"2402.09055","version":3},"attestation_state":"computed","paper":{"title":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Guodong Zhou, Qingying Sun, Shoushan Li, Tongfei Shen, Yang Liu","submitted_at":"2024-02-14T10:05:19Z","abstract_excerpt":"The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video humor detection (SVHD), named Comment-aided Video-Language Alignment (CVLA) via data-augmented multi-modal contrastive pre-training. Notably, our CVLA not only operates on raw signals across various modal channels but also yields an appropriate multi-modal representation by aligning the video and language components within a consistent 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":"2402.09055","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-14T10:05:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9fff9d9f0322330f65c67d1468c2ef1496863344f6505cb18ee4b984c3975fb5","abstract_canon_sha256":"8bcf2f159813a30cc29ee9b62b5186c508ea83c843ca28942685016ae0d97a54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:01.806779Z","signature_b64":"9lZhvh4FBPmJDDzFxdBN/5Su+gSA5u28DwsLpq/MKF2IFPu4LevPfgrbBsJoR2cvUNywzPlm37X6+RY/iErlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b83afebfcb72bfc3417a052f7b2a36e3c833677c8ebb0eade66a43b1df158b7","last_reissued_at":"2026-07-05T08:08:01.806277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:01.806277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Guodong Zhou, Qingying Sun, Shoushan Li, Tongfei Shen, Yang Liu","submitted_at":"2024-02-14T10:05:19Z","abstract_excerpt":"The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video humor detection (SVHD), named Comment-aided Video-Language Alignment (CVLA) via data-augmented multi-modal contrastive pre-training. Notably, our CVLA not only operates on raw signals across various modal channels but also yields an appropriate multi-modal representation by aligning the video and language components within a consistent s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09055","kind":"arxiv","version":3},"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/2402.09055/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":"2402.09055","created_at":"2026-07-05T08:08:01.806349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09055v3","created_at":"2026-07-05T08:08:01.806349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09055","created_at":"2026-07-05T08:08:01.806349+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOB27274W4V7","created_at":"2026-07-05T08:08:01.806349+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOB27274W4V7YNAX","created_at":"2026-07-05T08:08:01.806349+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOB27274","created_at":"2026-07-05T08:08:01.806349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.19088","citing_title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23137","citing_title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY","json":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY.json","graph_json":"https://pith.science/api/pith-number/TOB27274W4V7YNAXUBJPPMVDNY/graph.json","events_json":"https://pith.science/api/pith-number/TOB27274W4V7YNAXUBJPPMVDNY/events.json","paper":"https://pith.science/paper/TOB27274"},"agent_actions":{"view_html":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY","download_json":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY.json","view_paper":"https://pith.science/paper/TOB27274","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09055&json=true","fetch_graph":"https://pith.science/api/pith-number/TOB27274W4V7YNAXUBJPPMVDNY/graph.json","fetch_events":"https://pith.science/api/pith-number/TOB27274W4V7YNAXUBJPPMVDNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY/action/storage_attestation","attest_author":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY/action/author_attestation","sign_citation":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY/action/citation_signature","submit_replication":"https://pith.science/pith/TOB27274W4V7YNAXUBJPPMVDNY/action/replication_record"}},"created_at":"2026-07-05T08:08:01.806349+00:00","updated_at":"2026-07-05T08:08:01.806349+00:00"}