{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UVF7AF2JP6C3IHV2ALTC76G7UO","short_pith_number":"pith:UVF7AF2J","schema_version":"1.0","canonical_sha256":"a54bf017497f85b41eba02e62ff8dfa38886c5db200c7fb46ebc536c57877f50","source":{"kind":"arxiv","id":"2606.30914","version":1},"attestation_state":"computed","paper":{"title":"Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Md. Musfique Anwar, Nayeemul Islam, S. M Golam Rifat, Tanvir Ahmed Sijan","submitted_at":"2026-06-29T21:03:32Z","abstract_excerpt":"Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particularly for low-resource languages such as Bangla. We introduce a generalized Bangla news event ontology and a benchmark comprising 9,979 annotated sentences across 40 event subtypes, spanning clean news text, real-world Automatic Speech Recognition (ASR) transcripts, and orthographically corrupted text. We systematically evaluate fine-tuned encoder-only models (BanglaBERT and XLM-R) alongside instruction-tuned decoder-only large language models (Ll"},"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":"2606.30914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T21:03:32Z","cross_cats_sorted":[],"title_canon_sha256":"5b601691862fc17b3f84b379fa9a1a3321084ca4c74627e4d7d6827276dc3a73","abstract_canon_sha256":"d65af55db22c7e56a524f7c2c44da1531b8c9862a180bc8efce17a9bfcd795bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:21.523374Z","signature_b64":"fF2jI/NRG1b3gTlh7v+bdDCSrkz3UxO9Fw3lzdybwJs/XZjsR9hPB5BqbNQHXs8nFjoZXTKcmn/5SxNGUrcoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a54bf017497f85b41eba02e62ff8dfa38886c5db200c7fb46ebc536c57877f50","last_reissued_at":"2026-07-01T00:17:21.522946Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:21.522946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Md. Musfique Anwar, Nayeemul Islam, S. M Golam Rifat, Tanvir Ahmed Sijan","submitted_at":"2026-06-29T21:03:32Z","abstract_excerpt":"Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particularly for low-resource languages such as Bangla. We introduce a generalized Bangla news event ontology and a benchmark comprising 9,979 annotated sentences across 40 event subtypes, spanning clean news text, real-world Automatic Speech Recognition (ASR) transcripts, and orthographically corrupted text. We systematically evaluate fine-tuned encoder-only models (BanglaBERT and XLM-R) alongside instruction-tuned decoder-only large language models (Ll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30914","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/2606.30914/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":"2606.30914","created_at":"2026-07-01T00:17:21.523005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30914v1","created_at":"2026-07-01T00:17:21.523005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30914","created_at":"2026-07-01T00:17:21.523005+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVF7AF2JP6C3","created_at":"2026-07-01T00:17:21.523005+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVF7AF2JP6C3IHV2","created_at":"2026-07-01T00:17:21.523005+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVF7AF2J","created_at":"2026-07-01T00:17:21.523005+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/UVF7AF2JP6C3IHV2ALTC76G7UO","json":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO.json","graph_json":"https://pith.science/api/pith-number/UVF7AF2JP6C3IHV2ALTC76G7UO/graph.json","events_json":"https://pith.science/api/pith-number/UVF7AF2JP6C3IHV2ALTC76G7UO/events.json","paper":"https://pith.science/paper/UVF7AF2J"},"agent_actions":{"view_html":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO","download_json":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO.json","view_paper":"https://pith.science/paper/UVF7AF2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30914&json=true","fetch_graph":"https://pith.science/api/pith-number/UVF7AF2JP6C3IHV2ALTC76G7UO/graph.json","fetch_events":"https://pith.science/api/pith-number/UVF7AF2JP6C3IHV2ALTC76G7UO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO/action/storage_attestation","attest_author":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO/action/author_attestation","sign_citation":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO/action/citation_signature","submit_replication":"https://pith.science/pith/UVF7AF2JP6C3IHV2ALTC76G7UO/action/replication_record"}},"created_at":"2026-07-01T00:17:21.523005+00:00","updated_at":"2026-07-01T00:17:21.523005+00:00"}