{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OOZ2RNPFW2H5I4QPR2L7ORUMC4","short_pith_number":"pith:OOZ2RNPF","schema_version":"1.0","canonical_sha256":"73b3a8b5e5b68fd4720f8e97f7468c1737370f91f3ab152acb57c4097845ee00","source":{"kind":"arxiv","id":"2506.02005","version":2},"attestation_state":"computed","paper":{"title":"Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Harshita Poojary, Kevin Zhu, Pranav Prabhu, Pranav Saran, Sean O'Brien, Timothy Do, Vasu Sharma","submitted_at":"2025-05-24T03:23:39Z","abstract_excerpt":"In this paper, we address the persistent challenges that figurative language expressions pose for natural language processing (NLP) systems, particularly in low-resource languages such as Konkani. We present a hybrid model that integrates a pre-trained Multilingual BERT (mBERT) with a bidirectional LSTM and a linear classifier. This architecture is fine-tuned on a newly introduced annotated dataset for metaphor classification, developed as part of this work. To improve the model's efficiency, we implement a gradient-based attention head pruning strategy. For metaphor classification, the pruned"},"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":"2506.02005","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T03:23:39Z","cross_cats_sorted":[],"title_canon_sha256":"e40899c8f5c5633e8c442b9ee49f0f5e7efe8cfefe57346977bbe581b9486423","abstract_canon_sha256":"f51adf52676b0486ac30cd40ae210026d1e501ccc5f5370b0a869d5aabcb678d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:06.727133Z","signature_b64":"IKcSzCc6g9Qro134elvGxxE2ilZBVP8b5WmOEoq9rkeCzsBAfvO026cUoxnVxHN57zanvMpRsDQtHHw8ZgpDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73b3a8b5e5b68fd4720f8e97f7468c1737370f91f3ab152acb57c4097845ee00","last_reissued_at":"2026-07-05T11:44:06.726633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:06.726633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Harshita Poojary, Kevin Zhu, Pranav Prabhu, Pranav Saran, Sean O'Brien, Timothy Do, Vasu Sharma","submitted_at":"2025-05-24T03:23:39Z","abstract_excerpt":"In this paper, we address the persistent challenges that figurative language expressions pose for natural language processing (NLP) systems, particularly in low-resource languages such as Konkani. We present a hybrid model that integrates a pre-trained Multilingual BERT (mBERT) with a bidirectional LSTM and a linear classifier. This architecture is fine-tuned on a newly introduced annotated dataset for metaphor classification, developed as part of this work. To improve the model's efficiency, we implement a gradient-based attention head pruning strategy. For metaphor classification, the pruned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02005","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/2506.02005/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":"2506.02005","created_at":"2026-07-05T11:44:06.726690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02005v2","created_at":"2026-07-05T11:44:06.726690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02005","created_at":"2026-07-05T11:44:06.726690+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOZ2RNPFW2H5","created_at":"2026-07-05T11:44:06.726690+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOZ2RNPFW2H5I4QP","created_at":"2026-07-05T11:44:06.726690+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOZ2RNPF","created_at":"2026-07-05T11:44:06.726690+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/OOZ2RNPFW2H5I4QPR2L7ORUMC4","json":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4.json","graph_json":"https://pith.science/api/pith-number/OOZ2RNPFW2H5I4QPR2L7ORUMC4/graph.json","events_json":"https://pith.science/api/pith-number/OOZ2RNPFW2H5I4QPR2L7ORUMC4/events.json","paper":"https://pith.science/paper/OOZ2RNPF"},"agent_actions":{"view_html":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4","download_json":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4.json","view_paper":"https://pith.science/paper/OOZ2RNPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02005&json=true","fetch_graph":"https://pith.science/api/pith-number/OOZ2RNPFW2H5I4QPR2L7ORUMC4/graph.json","fetch_events":"https://pith.science/api/pith-number/OOZ2RNPFW2H5I4QPR2L7ORUMC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4/action/storage_attestation","attest_author":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4/action/author_attestation","sign_citation":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4/action/citation_signature","submit_replication":"https://pith.science/pith/OOZ2RNPFW2H5I4QPR2L7ORUMC4/action/replication_record"}},"created_at":"2026-07-05T11:44:06.726690+00:00","updated_at":"2026-07-05T11:44:06.726690+00:00"}