{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5MHY475M6ZFYJAJFNE632Y4O2V","short_pith_number":"pith:5MHY475M","schema_version":"1.0","canonical_sha256":"eb0f8e7facf64b848125693dbd638ed54b2552dba9e0fea308ce17d18757e9d0","source":{"kind":"arxiv","id":"2507.14887","version":1},"attestation_state":"computed","paper":{"title":"MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daling Wang, Shi Feng, Shiyi Mu, Xiaocui Yang, Yifei Zhang, Yongkang Liu","submitted_at":"2025-07-20T10:11:21Z","abstract_excerpt":"Although large language models (LLMs) excel in text comprehension and generation, their performance on the Emotion-Cause Pair Extraction (ECPE) task, which requires reasoning ability, is often underperform smaller language model. The main reason is the lack of auxiliary knowledge, which limits LLMs' ability to effectively perceive emotions and reason causes. To address this issue, we propose a novel \\textbf{M}ulti-source h\\textbf{E}terogeneous \\textbf{K}nowledge \\textbf{i}njection me\\textbf{T}hod, MEKiT, which integrates heterogeneous internal emotional knowledge and external causal knowledge."},"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":"2507.14887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T10:11:21Z","cross_cats_sorted":[],"title_canon_sha256":"647d1bc58d1f0152b894e21e05f28363e0c08642ea7c271b3f26ad173af01405","abstract_canon_sha256":"acbae68d75268567cb684749be38ebd6a490e49a145705d92ab69d959ead28b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:15.151754Z","signature_b64":"j5G4RKISsKIdI/dp0SLIdLwSGCfiiVj0EmwzOCD2ikEKoQHpTj0AOe2RoBQ+DfHy8tJIqou3UQOI94KDAePDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb0f8e7facf64b848125693dbd638ed54b2552dba9e0fea308ce17d18757e9d0","last_reissued_at":"2026-07-05T11:40:15.151247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:15.151247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daling Wang, Shi Feng, Shiyi Mu, Xiaocui Yang, Yifei Zhang, Yongkang Liu","submitted_at":"2025-07-20T10:11:21Z","abstract_excerpt":"Although large language models (LLMs) excel in text comprehension and generation, their performance on the Emotion-Cause Pair Extraction (ECPE) task, which requires reasoning ability, is often underperform smaller language model. The main reason is the lack of auxiliary knowledge, which limits LLMs' ability to effectively perceive emotions and reason causes. To address this issue, we propose a novel \\textbf{M}ulti-source h\\textbf{E}terogeneous \\textbf{K}nowledge \\textbf{i}njection me\\textbf{T}hod, MEKiT, which integrates heterogeneous internal emotional knowledge and external causal knowledge."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14887","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/2507.14887/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":"2507.14887","created_at":"2026-07-05T11:40:15.151307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14887v1","created_at":"2026-07-05T11:40:15.151307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14887","created_at":"2026-07-05T11:40:15.151307+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MHY475M6ZFY","created_at":"2026-07-05T11:40:15.151307+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MHY475M6ZFYJAJF","created_at":"2026-07-05T11:40:15.151307+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MHY475M","created_at":"2026-07-05T11:40:15.151307+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/5MHY475M6ZFYJAJFNE632Y4O2V","json":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V.json","graph_json":"https://pith.science/api/pith-number/5MHY475M6ZFYJAJFNE632Y4O2V/graph.json","events_json":"https://pith.science/api/pith-number/5MHY475M6ZFYJAJFNE632Y4O2V/events.json","paper":"https://pith.science/paper/5MHY475M"},"agent_actions":{"view_html":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V","download_json":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V.json","view_paper":"https://pith.science/paper/5MHY475M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14887&json=true","fetch_graph":"https://pith.science/api/pith-number/5MHY475M6ZFYJAJFNE632Y4O2V/graph.json","fetch_events":"https://pith.science/api/pith-number/5MHY475M6ZFYJAJFNE632Y4O2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V/action/storage_attestation","attest_author":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V/action/author_attestation","sign_citation":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V/action/citation_signature","submit_replication":"https://pith.science/pith/5MHY475M6ZFYJAJFNE632Y4O2V/action/replication_record"}},"created_at":"2026-07-05T11:40:15.151307+00:00","updated_at":"2026-07-05T11:40:15.151307+00:00"}