{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HUJXVHKKW2DCBNZFWMIVKMUTVN","short_pith_number":"pith:HUJXVHKK","schema_version":"1.0","canonical_sha256":"3d137a9d4ab68620b725b311553293ab70610fd245db2e02d586082874dd5fc2","source":{"kind":"arxiv","id":"2505.22548","version":2},"attestation_state":"computed","paper":{"title":"Emotion-o1: Adaptive Long Reasoning for Emotion Understanding in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhao Song, Hui Gao, Kaiyun Huang, Peng Zhang, Yazhou Zhang","submitted_at":"2025-05-28T16:32:16Z","abstract_excerpt":"Long chain-of-thought (CoT) reasoning has shown great promise in enhancing the emotion understanding performance of large language models (LLMs). However, current fixed-length CoT methods struggle to balance reasoning depth and efficiency. Simple tasks (e.g., sentiment classification) are over-reasoned, while complex tasks (e.g., sarcasm understanding) lack depth. To fill this gap, we present Emotion-o1, an adaptive CoT framework that dynamically adjusts reasoning length based on emotion-task complexity. Emotion-o1 is trained by distilling adaptive CoT patterns from a reasoning-oriented LLM, f"},"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":"2505.22548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T16:32:16Z","cross_cats_sorted":[],"title_canon_sha256":"412958054a7c722611b96137c8108432543ffcaf8d74055b9ead78f8e0277672","abstract_canon_sha256":"2e8f2ec0c8e707923e8d0c317e7849dff0eec793dbd598030f9717e20d0d6edd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:10.408743Z","signature_b64":"ITjfWfL8WyAc6G2nyr80llz0FuxgXD6zWi3t9Wn8xJ8/joSCxva/nHCaKqoS5/tL8MaYRcJhknINz1qHaLiJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d137a9d4ab68620b725b311553293ab70610fd245db2e02d586082874dd5fc2","last_reissued_at":"2026-07-05T11:49:10.408282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:10.408282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emotion-o1: Adaptive Long Reasoning for Emotion Understanding in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhao Song, Hui Gao, Kaiyun Huang, Peng Zhang, Yazhou Zhang","submitted_at":"2025-05-28T16:32:16Z","abstract_excerpt":"Long chain-of-thought (CoT) reasoning has shown great promise in enhancing the emotion understanding performance of large language models (LLMs). However, current fixed-length CoT methods struggle to balance reasoning depth and efficiency. Simple tasks (e.g., sentiment classification) are over-reasoned, while complex tasks (e.g., sarcasm understanding) lack depth. To fill this gap, we present Emotion-o1, an adaptive CoT framework that dynamically adjusts reasoning length based on emotion-task complexity. Emotion-o1 is trained by distilling adaptive CoT patterns from a reasoning-oriented LLM, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22548","kind":"arxiv","version":2},"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/2505.22548/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":"2505.22548","created_at":"2026-07-05T11:49:10.408336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22548v2","created_at":"2026-07-05T11:49:10.408336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22548","created_at":"2026-07-05T11:49:10.408336+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUJXVHKKW2DC","created_at":"2026-07-05T11:49:10.408336+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUJXVHKKW2DCBNZF","created_at":"2026-07-05T11:49:10.408336+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUJXVHKK","created_at":"2026-07-05T11:49:10.408336+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/HUJXVHKKW2DCBNZFWMIVKMUTVN","json":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN.json","graph_json":"https://pith.science/api/pith-number/HUJXVHKKW2DCBNZFWMIVKMUTVN/graph.json","events_json":"https://pith.science/api/pith-number/HUJXVHKKW2DCBNZFWMIVKMUTVN/events.json","paper":"https://pith.science/paper/HUJXVHKK"},"agent_actions":{"view_html":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN","download_json":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN.json","view_paper":"https://pith.science/paper/HUJXVHKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22548&json=true","fetch_graph":"https://pith.science/api/pith-number/HUJXVHKKW2DCBNZFWMIVKMUTVN/graph.json","fetch_events":"https://pith.science/api/pith-number/HUJXVHKKW2DCBNZFWMIVKMUTVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN/action/storage_attestation","attest_author":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN/action/author_attestation","sign_citation":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN/action/citation_signature","submit_replication":"https://pith.science/pith/HUJXVHKKW2DCBNZFWMIVKMUTVN/action/replication_record"}},"created_at":"2026-07-05T11:49:10.408336+00:00","updated_at":"2026-07-05T11:49:10.408336+00:00"}