{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:624FZBBNCP46I3DQCNG543F65R","short_pith_number":"pith:624FZBBN","schema_version":"1.0","canonical_sha256":"f6b85c842d13f9e46c70134dde6cbeec596578cdad681718c882f7f5ed00ead2","source":{"kind":"arxiv","id":"2401.17716","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jialiang Wu, Longjun Cai, Yi Shen, Ziheng Zhang","submitted_at":"2024-01-31T10:20:01Z","abstract_excerpt":"Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Existing methods tend to overfit spurious correlations, such as positional bias in existing benchmark datasets, rather than capturing semantic features. Inspired by recent work, we explore leveraging large language model (LLM) to address ECPE task without additional training. Despite strong capabilities, LLMs suffer from uncontrollable outputs, resulting in mediocre performance. To address this, we introduce chain-of-thought to mimic human cognitive process and propose th"},"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":"2401.17716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T10:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"ce6a7f403ab30594cc05901412c8304679f35228d72ff45618f13d25e51eb22e","abstract_canon_sha256":"a63ea48f4b3a8ffd2439fce547557f6fd949498ae2e267f531791136a859464d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:41.198634Z","signature_b64":"DG/fCY4z1AG7SUwt2Yh8F6qOrbOjVWwfIH6igvC6MOJLcFUekVWEwn186Rjs5bnXrYttQtKVWSkH9vSMV13iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6b85c842d13f9e46c70134dde6cbeec596578cdad681718c882f7f5ed00ead2","last_reissued_at":"2026-07-05T07:39:41.198219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:41.198219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jialiang Wu, Longjun Cai, Yi Shen, Ziheng Zhang","submitted_at":"2024-01-31T10:20:01Z","abstract_excerpt":"Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Existing methods tend to overfit spurious correlations, such as positional bias in existing benchmark datasets, rather than capturing semantic features. Inspired by recent work, we explore leveraging large language model (LLM) to address ECPE task without additional training. Despite strong capabilities, LLMs suffer from uncontrollable outputs, resulting in mediocre performance. To address this, we introduce chain-of-thought to mimic human cognitive process and propose th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17716","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/2401.17716/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":"2401.17716","created_at":"2026-07-05T07:39:41.198273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17716v1","created_at":"2026-07-05T07:39:41.198273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17716","created_at":"2026-07-05T07:39:41.198273+00:00"},{"alias_kind":"pith_short_12","alias_value":"624FZBBNCP46","created_at":"2026-07-05T07:39:41.198273+00:00"},{"alias_kind":"pith_short_16","alias_value":"624FZBBNCP46I3DQ","created_at":"2026-07-05T07:39:41.198273+00:00"},{"alias_kind":"pith_short_8","alias_value":"624FZBBN","created_at":"2026-07-05T07:39:41.198273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14593","citing_title":"Mechanistic Decoding of Cognitive Constructs in Large Language Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R","json":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R.json","graph_json":"https://pith.science/api/pith-number/624FZBBNCP46I3DQCNG543F65R/graph.json","events_json":"https://pith.science/api/pith-number/624FZBBNCP46I3DQCNG543F65R/events.json","paper":"https://pith.science/paper/624FZBBN"},"agent_actions":{"view_html":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R","download_json":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R.json","view_paper":"https://pith.science/paper/624FZBBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17716&json=true","fetch_graph":"https://pith.science/api/pith-number/624FZBBNCP46I3DQCNG543F65R/graph.json","fetch_events":"https://pith.science/api/pith-number/624FZBBNCP46I3DQCNG543F65R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R/action/storage_attestation","attest_author":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R/action/author_attestation","sign_citation":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R/action/citation_signature","submit_replication":"https://pith.science/pith/624FZBBNCP46I3DQCNG543F65R/action/replication_record"}},"created_at":"2026-07-05T07:39:41.198273+00:00","updated_at":"2026-07-05T07:39:41.198273+00:00"}