{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TGY7PCWWMRP3CURAGVRI4UWBNT","short_pith_number":"pith:TGY7PCWW","schema_version":"1.0","canonical_sha256":"99b1f78ad6645fb1522035628e52c16cfb5ec8f1f21b4de441d0237ba6b83955","source":{"kind":"arxiv","id":"2501.09512","version":2},"attestation_state":"computed","paper":{"title":"PIER: A Novel Metric for Evaluating What Matters in Code-Switching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Waibel, Enes Yavuz Ugan, Leonard B\\\"armann, Ngoc-Quan Pham","submitted_at":"2025-01-16T12:57:33Z","abstract_excerpt":"Code-switching, the alternation of languages within a single discourse, presents a significant challenge for Automatic Speech Recognition. Despite the unique nature of the task, performance is commonly measured with established metrics such as Word-Error-Rate (WER). However, in this paper, we question whether these general metrics accurately assess performance on code-switching. Specifically, using both Connectionist-Temporal-Classification and Encoder-Decoder models, we show fine-tuning on non-code-switched data from both matrix and embedded language improves classical metrics on code-switchi"},"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":"2501.09512","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T12:57:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5d14263c174dde3d612b5db369e5a8da4b0a4b0c44e6171c5cde56e35e15a6cf","abstract_canon_sha256":"603d9c4806834d72628b3e13aeceac5f460b0d09c6363e9fc0d84a141c1b44ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:30.359789Z","signature_b64":"5ICp+mm6kSptzYZxr6PWGCiu47BPvNT53XMEnpCU9UfFtMRKHUhCJnxPpz/RwcLBOBJrikPh4QCIAw+dqDjDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99b1f78ad6645fb1522035628e52c16cfb5ec8f1f21b4de441d0237ba6b83955","last_reissued_at":"2026-07-05T10:03:30.359246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:30.359246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIER: A Novel Metric for Evaluating What Matters in Code-Switching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Waibel, Enes Yavuz Ugan, Leonard B\\\"armann, Ngoc-Quan Pham","submitted_at":"2025-01-16T12:57:33Z","abstract_excerpt":"Code-switching, the alternation of languages within a single discourse, presents a significant challenge for Automatic Speech Recognition. Despite the unique nature of the task, performance is commonly measured with established metrics such as Word-Error-Rate (WER). However, in this paper, we question whether these general metrics accurately assess performance on code-switching. Specifically, using both Connectionist-Temporal-Classification and Encoder-Decoder models, we show fine-tuning on non-code-switched data from both matrix and embedded language improves classical metrics on code-switchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09512","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/2501.09512/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":"2501.09512","created_at":"2026-07-05T10:03:30.359326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09512v2","created_at":"2026-07-05T10:03:30.359326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09512","created_at":"2026-07-05T10:03:30.359326+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGY7PCWWMRP3","created_at":"2026-07-05T10:03:30.359326+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGY7PCWWMRP3CURA","created_at":"2026-07-05T10:03:30.359326+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGY7PCWW","created_at":"2026-07-05T10:03:30.359326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.07037","citing_title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT","json":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT.json","graph_json":"https://pith.science/api/pith-number/TGY7PCWWMRP3CURAGVRI4UWBNT/graph.json","events_json":"https://pith.science/api/pith-number/TGY7PCWWMRP3CURAGVRI4UWBNT/events.json","paper":"https://pith.science/paper/TGY7PCWW"},"agent_actions":{"view_html":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT","download_json":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT.json","view_paper":"https://pith.science/paper/TGY7PCWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09512&json=true","fetch_graph":"https://pith.science/api/pith-number/TGY7PCWWMRP3CURAGVRI4UWBNT/graph.json","fetch_events":"https://pith.science/api/pith-number/TGY7PCWWMRP3CURAGVRI4UWBNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT/action/storage_attestation","attest_author":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT/action/author_attestation","sign_citation":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT/action/citation_signature","submit_replication":"https://pith.science/pith/TGY7PCWWMRP3CURAGVRI4UWBNT/action/replication_record"}},"created_at":"2026-07-05T10:03:30.359326+00:00","updated_at":"2026-07-05T10:03:30.359326+00:00"}