{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KQCGEEF3QLV2UF4YXAW5WCHJ4X","short_pith_number":"pith:KQCGEEF3","schema_version":"1.0","canonical_sha256":"54046210bb82ebaa1798b82ddb08e9e5df030c34f0f6e94333ebb2f727cc34c3","source":{"kind":"arxiv","id":"2607.00968","version":1},"attestation_state":"computed","paper":{"title":"Quantifying the Affective Gap: A Zero-Shot Evaluation of LLMs on Fine-Grained Emotion Taxonomies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Jessica M. Johnson, Krzysztof J. Rechowicz, Lawrence Obiuwevwi, Sachin Shetty, Sampath Jayarathna, Vikas Ashok","submitted_at":"2026-07-01T14:04:48Z","abstract_excerpt":"Emotion recognition in natural language is a foundational challenge in affective computing, with critical implications for human-computer interaction, mental health support, and conversational AI. This paper presents a rigorous, unified zero-shot evaluation of three leading commercial large language models: Claude (claude-sonnet-4-6), ChatGPT (GPT-5.4), and Gemini (gemini-2.5-flash). The models were queried through their respective production APIs as of April 2026 on a fine-grained 13-class emotion classification task. Using a stratified 1,000-sentence sample from the boltuix/emotions dataset,"},"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":"2607.00968","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T14:04:48Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"55d4f03dce0f71c704eeec1cda101bcf44f67f12075803e60f00259b7817e75b","abstract_canon_sha256":"475c6cbe4ba50a73c6228f4699630b1711bd5082eb409e547c060f4c6da5dafd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:24.738026Z","signature_b64":"Oh3HOtKbVT26tMlHsfKMPpvXMnJ3xlcmHhigkbu+Kryvy5sVo6LVvjvIeQONeRZdvnfAKXYhpsaOoZ+AnZ2BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54046210bb82ebaa1798b82ddb08e9e5df030c34f0f6e94333ebb2f727cc34c3","last_reissued_at":"2026-07-02T01:18:24.737666Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:24.737666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying the Affective Gap: A Zero-Shot Evaluation of LLMs on Fine-Grained Emotion Taxonomies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Jessica M. Johnson, Krzysztof J. Rechowicz, Lawrence Obiuwevwi, Sachin Shetty, Sampath Jayarathna, Vikas Ashok","submitted_at":"2026-07-01T14:04:48Z","abstract_excerpt":"Emotion recognition in natural language is a foundational challenge in affective computing, with critical implications for human-computer interaction, mental health support, and conversational AI. This paper presents a rigorous, unified zero-shot evaluation of three leading commercial large language models: Claude (claude-sonnet-4-6), ChatGPT (GPT-5.4), and Gemini (gemini-2.5-flash). The models were queried through their respective production APIs as of April 2026 on a fine-grained 13-class emotion classification task. Using a stratified 1,000-sentence sample from the boltuix/emotions dataset,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00968","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/2607.00968/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":"2607.00968","created_at":"2026-07-02T01:18:24.737732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00968v1","created_at":"2026-07-02T01:18:24.737732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00968","created_at":"2026-07-02T01:18:24.737732+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQCGEEF3QLV2","created_at":"2026-07-02T01:18:24.737732+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQCGEEF3QLV2UF4Y","created_at":"2026-07-02T01:18:24.737732+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQCGEEF3","created_at":"2026-07-02T01:18:24.737732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X","json":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X.json","graph_json":"https://pith.science/api/pith-number/KQCGEEF3QLV2UF4YXAW5WCHJ4X/graph.json","events_json":"https://pith.science/api/pith-number/KQCGEEF3QLV2UF4YXAW5WCHJ4X/events.json","paper":"https://pith.science/paper/KQCGEEF3"},"agent_actions":{"view_html":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X","download_json":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X.json","view_paper":"https://pith.science/paper/KQCGEEF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00968&json=true","fetch_graph":"https://pith.science/api/pith-number/KQCGEEF3QLV2UF4YXAW5WCHJ4X/graph.json","fetch_events":"https://pith.science/api/pith-number/KQCGEEF3QLV2UF4YXAW5WCHJ4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X/action/storage_attestation","attest_author":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X/action/author_attestation","sign_citation":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X/action/citation_signature","submit_replication":"https://pith.science/pith/KQCGEEF3QLV2UF4YXAW5WCHJ4X/action/replication_record"}},"created_at":"2026-07-02T01:18:24.737732+00:00","updated_at":"2026-07-02T01:18:24.737732+00:00"}