{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IV5ZE7HCG5GHTMAEEFCKPMUBPU","short_pith_number":"pith:IV5ZE7HC","schema_version":"1.0","canonical_sha256":"457b927ce2374c79b0042144a7b2817d25d44bad7137402abcbcac9943546842","source":{"kind":"arxiv","id":"2408.02595","version":1},"attestation_state":"computed","paper":{"title":"Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ananya Pandey, Dinesh Kumar Vishwakarma, Sajal Aggarwal","submitted_at":"2024-08-05T16:07:31Z","abstract_excerpt":"Sarcasm is a type of irony, characterized by an inherent mismatch between the literal interpretation and the intended connotation. Though sarcasm detection in text has been extensively studied, there are situations in which textual input alone might be insufficient to perceive sarcasm. The inclusion of additional contextual cues, such as images, is essential to recognize sarcasm in social media data effectively. This study presents a novel framework for multimodal sarcasm detection that can process input triplets. Two components of these triplets comprise the input text and its associated imag"},"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":"2408.02595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T16:07:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e16f42466fd34b7fea6565bb527e54b7c9e7763304cf961e7a04b2001743bffd","abstract_canon_sha256":"0a3f8aa357e4a9041262bcee1e19ba52f3872ac8ee35b83ef218b0601b19fde1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:15.014098Z","signature_b64":"WFi8nlZQOoNj3N4SLkTueoEQHCITbwsCw99A77RWzPWMQxOYM5GsPAJETLKNg9UW+0BbmOrHPfHoSD20DoTLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457b927ce2374c79b0042144a7b2817d25d44bad7137402abcbcac9943546842","last_reissued_at":"2026-07-05T08:52:15.013646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:15.013646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ananya Pandey, Dinesh Kumar Vishwakarma, Sajal Aggarwal","submitted_at":"2024-08-05T16:07:31Z","abstract_excerpt":"Sarcasm is a type of irony, characterized by an inherent mismatch between the literal interpretation and the intended connotation. Though sarcasm detection in text has been extensively studied, there are situations in which textual input alone might be insufficient to perceive sarcasm. The inclusion of additional contextual cues, such as images, is essential to recognize sarcasm in social media data effectively. This study presents a novel framework for multimodal sarcasm detection that can process input triplets. Two components of these triplets comprise the input text and its associated imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02595","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/2408.02595/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":"2408.02595","created_at":"2026-07-05T08:52:15.013705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02595v1","created_at":"2026-07-05T08:52:15.013705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02595","created_at":"2026-07-05T08:52:15.013705+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV5ZE7HCG5GH","created_at":"2026-07-05T08:52:15.013705+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV5ZE7HCG5GHTMAE","created_at":"2026-07-05T08:52:15.013705+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV5ZE7HC","created_at":"2026-07-05T08:52:15.013705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19420","citing_title":"Commander-GPT: Dividing and Routing for Multimodal Sarcasm Detection","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU","json":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU.json","graph_json":"https://pith.science/api/pith-number/IV5ZE7HCG5GHTMAEEFCKPMUBPU/graph.json","events_json":"https://pith.science/api/pith-number/IV5ZE7HCG5GHTMAEEFCKPMUBPU/events.json","paper":"https://pith.science/paper/IV5ZE7HC"},"agent_actions":{"view_html":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU","download_json":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU.json","view_paper":"https://pith.science/paper/IV5ZE7HC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02595&json=true","fetch_graph":"https://pith.science/api/pith-number/IV5ZE7HCG5GHTMAEEFCKPMUBPU/graph.json","fetch_events":"https://pith.science/api/pith-number/IV5ZE7HCG5GHTMAEEFCKPMUBPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU/action/storage_attestation","attest_author":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU/action/author_attestation","sign_citation":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU/action/citation_signature","submit_replication":"https://pith.science/pith/IV5ZE7HCG5GHTMAEEFCKPMUBPU/action/replication_record"}},"created_at":"2026-07-05T08:52:15.013705+00:00","updated_at":"2026-07-05T08:52:15.013705+00:00"}