{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E35GCWFTE3KMI6S7GEPZDKS4JC","short_pith_number":"pith:E35GCWFT","schema_version":"1.0","canonical_sha256":"26fa6158b326d4c47a5f311f91aa5c489875afb7992059a84ea64eddbb37a075","source":{"kind":"arxiv","id":"2312.04642","version":1},"attestation_state":"computed","paper":{"title":"On Sarcasm Detection with OpenAI GPT-based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andriy Miranskyy, Montgomery Gole, Williams-Paul Nwadiugwu","submitted_at":"2023-12-07T19:00:56Z","abstract_excerpt":"Sarcasm is a form of irony that requires readers or listeners to interpret its intended meaning by considering context and social cues. Machine learning classification models have long had difficulty detecting sarcasm due to its social complexity and contradictory nature.\n  This paper explores the applications of the Generative Pretrained Transformer (GPT) models, including GPT-3, InstructGPT, GPT-3.5, and GPT-4, in detecting sarcasm in natural language. It tests fine-tuned and zero-shot models of different sizes and releases.\n  The GPT models were tested on the political and balanced (pol-bal"},"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":"2312.04642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T19:00:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ade097d5e19d1b7614da0cb09f2675533b0629c9b2c8d965f47f9b452f404bd","abstract_canon_sha256":"c5ae9dbdcb5d154d6ae6fc3bf0e8dec4d8b3548b86de1ce34ebbd1e5b496f8e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:08.268350Z","signature_b64":"pmZJH1jITI+MkiAc0rh8fO0nzQIQg2UKRWGEgjnXcX8DA7c3rz0W4lWdmxRPKNssj+JpAZkfUhYvcd2K0aLTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26fa6158b326d4c47a5f311f91aa5c489875afb7992059a84ea64eddbb37a075","last_reissued_at":"2026-07-05T10:05:08.267876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:08.267876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Sarcasm Detection with OpenAI GPT-based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andriy Miranskyy, Montgomery Gole, Williams-Paul Nwadiugwu","submitted_at":"2023-12-07T19:00:56Z","abstract_excerpt":"Sarcasm is a form of irony that requires readers or listeners to interpret its intended meaning by considering context and social cues. Machine learning classification models have long had difficulty detecting sarcasm due to its social complexity and contradictory nature.\n  This paper explores the applications of the Generative Pretrained Transformer (GPT) models, including GPT-3, InstructGPT, GPT-3.5, and GPT-4, in detecting sarcasm in natural language. It tests fine-tuned and zero-shot models of different sizes and releases.\n  The GPT models were tested on the political and balanced (pol-bal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04642","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/2312.04642/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":"2312.04642","created_at":"2026-07-05T10:05:08.267936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04642v1","created_at":"2026-07-05T10:05:08.267936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04642","created_at":"2026-07-05T10:05:08.267936+00:00"},{"alias_kind":"pith_short_12","alias_value":"E35GCWFTE3KM","created_at":"2026-07-05T10:05:08.267936+00:00"},{"alias_kind":"pith_short_16","alias_value":"E35GCWFTE3KMI6S7","created_at":"2026-07-05T10:05:08.267936+00:00"},{"alias_kind":"pith_short_8","alias_value":"E35GCWFT","created_at":"2026-07-05T10:05:08.267936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16884","citing_title":"Irony Detection, Reasoning and Understanding in Zero-shot Learning","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC","json":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC.json","graph_json":"https://pith.science/api/pith-number/E35GCWFTE3KMI6S7GEPZDKS4JC/graph.json","events_json":"https://pith.science/api/pith-number/E35GCWFTE3KMI6S7GEPZDKS4JC/events.json","paper":"https://pith.science/paper/E35GCWFT"},"agent_actions":{"view_html":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC","download_json":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC.json","view_paper":"https://pith.science/paper/E35GCWFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04642&json=true","fetch_graph":"https://pith.science/api/pith-number/E35GCWFTE3KMI6S7GEPZDKS4JC/graph.json","fetch_events":"https://pith.science/api/pith-number/E35GCWFTE3KMI6S7GEPZDKS4JC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC/action/storage_attestation","attest_author":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC/action/author_attestation","sign_citation":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC/action/citation_signature","submit_replication":"https://pith.science/pith/E35GCWFTE3KMI6S7GEPZDKS4JC/action/replication_record"}},"created_at":"2026-07-05T10:05:08.267936+00:00","updated_at":"2026-07-05T10:05:08.267936+00:00"}