{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SRCIGCQ2RT7GOQJACMQHKPKKPS","short_pith_number":"pith:SRCIGCQ2","schema_version":"1.0","canonical_sha256":"9444830a1a8cfe6741201320753d4a7cb98504498aa1fc5c686562844ea6dcc9","source":{"kind":"arxiv","id":"2504.10679","version":1},"attestation_state":"computed","paper":{"title":"Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"A.M.N.H. Adhikari, Dharshana Kasthurirathna, F.A. Rizvi, Lakmini Abeywardhana, T. Navojith, W.P.U. Senevirathna","submitted_at":"2025-04-14T20:01:34Z","abstract_excerpt":"Brand reputation in the banking sector is maintained through insightful analysis of customer opinion on code-mixed and multilingual content. Conventional NLP models misclassify or ignore code-mixed text, when mix with low resource languages such as Sinhala-English and fail to capture domain-specific knowledge. This study introduces a hybrid NLP method to improve keyword extraction, content filtering, and aspect-based classification of banking content. Keyword extraction in English is performed with a hybrid approach comprising a fine-tuned SpaCy NER model, FinBERT-based KeyBERT embeddings, YAK"},"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":"2504.10679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T20:01:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a091cb89a1e11e56620911272c8471cf192fd08fdd4c7a4a04fa93c6f2e8ff1","abstract_canon_sha256":"bf461831b915ccd15c64565ffeceaf96f062e9ced3dcb8c997c36bb02c6eef1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:21.616906Z","signature_b64":"M+B30q7Lz/eX4XKir4ITNhgo1ef4SBFtdUYvyv+cqBz1g57SKbvw8aWDVxJZV0SmdBs6XMYE/HdUxZzieovwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9444830a1a8cfe6741201320753d4a7cb98504498aa1fc5c686562844ea6dcc9","last_reissued_at":"2026-07-05T10:49:21.616404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:21.616404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"A.M.N.H. Adhikari, Dharshana Kasthurirathna, F.A. Rizvi, Lakmini Abeywardhana, T. Navojith, W.P.U. Senevirathna","submitted_at":"2025-04-14T20:01:34Z","abstract_excerpt":"Brand reputation in the banking sector is maintained through insightful analysis of customer opinion on code-mixed and multilingual content. Conventional NLP models misclassify or ignore code-mixed text, when mix with low resource languages such as Sinhala-English and fail to capture domain-specific knowledge. This study introduces a hybrid NLP method to improve keyword extraction, content filtering, and aspect-based classification of banking content. Keyword extraction in English is performed with a hybrid approach comprising a fine-tuned SpaCy NER model, FinBERT-based KeyBERT embeddings, YAK"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10679","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/2504.10679/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":"2504.10679","created_at":"2026-07-05T10:49:21.616474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10679v1","created_at":"2026-07-05T10:49:21.616474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10679","created_at":"2026-07-05T10:49:21.616474+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRCIGCQ2RT7G","created_at":"2026-07-05T10:49:21.616474+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRCIGCQ2RT7GOQJA","created_at":"2026-07-05T10:49:21.616474+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRCIGCQ2","created_at":"2026-07-05T10:49:21.616474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05259","citing_title":"SalAngaBhava: A Sinhala Market Dataset for Aspect-based Sentiment Analysis","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS","json":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS.json","graph_json":"https://pith.science/api/pith-number/SRCIGCQ2RT7GOQJACMQHKPKKPS/graph.json","events_json":"https://pith.science/api/pith-number/SRCIGCQ2RT7GOQJACMQHKPKKPS/events.json","paper":"https://pith.science/paper/SRCIGCQ2"},"agent_actions":{"view_html":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS","download_json":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS.json","view_paper":"https://pith.science/paper/SRCIGCQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10679&json=true","fetch_graph":"https://pith.science/api/pith-number/SRCIGCQ2RT7GOQJACMQHKPKKPS/graph.json","fetch_events":"https://pith.science/api/pith-number/SRCIGCQ2RT7GOQJACMQHKPKKPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS/action/storage_attestation","attest_author":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS/action/author_attestation","sign_citation":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS/action/citation_signature","submit_replication":"https://pith.science/pith/SRCIGCQ2RT7GOQJACMQHKPKKPS/action/replication_record"}},"created_at":"2026-07-05T10:49:21.616474+00:00","updated_at":"2026-07-05T10:49:21.616474+00:00"}