{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VUM2TF64ETA5X2TPNNMFN3IRSV","short_pith_number":"pith:VUM2TF64","schema_version":"1.0","canonical_sha256":"ad19a997dc24c1dbea6f6b5856ed119567a1ba82e057466652744823049e542b","source":{"kind":"arxiv","id":"2606.09317","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Study of Pre-trained Speech Encoders and Training Objectives for Large-Scale Indic Spoken Language Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Agneedh Basu, Nihar Desai, Pavan Kumar J, Prasanta Kumar Ghosh, Sujith P, Visruth Sanka","submitted_at":"2026-06-08T10:27:33Z","abstract_excerpt":"Spoken language identification (LID) for Indian languages is a challenging problem due to the large number of languages, significant phonetic overlap among related varieties, and the scarcity of labeled data for many low-resource languages. In this work, we present a systematic comparative study of two pre-trained speech encoders -- Whisper and FastConformer -- combined with a linear classifier for large-scale Indic LID spanning 42 languages across four linguistic families. We evaluate both encoders in frozen (linear probing) and fine-tuned settings, and compare three training objectives: cros"},"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":"2606.09317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T10:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"dbd5284efe73917faaa4c8159032785c273af9dd3a68701444737d79b496646d","abstract_canon_sha256":"d22e19954d31bdfab0eed7664e586de2fad880a908f33bc3f8e1eb4358d8ce63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:14.649134Z","signature_b64":"WYTTXiN/fqa+Kw79r5TThlvnHYXvYjQVwzcYMGPX3F0QOJW03T2xXP7H1S/XZiUPDEo412k2GVVKH2nwHsLoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad19a997dc24c1dbea6f6b5856ed119567a1ba82e057466652744823049e542b","last_reissued_at":"2026-06-09T02:08:14.647852Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:14.647852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of Pre-trained Speech Encoders and Training Objectives for Large-Scale Indic Spoken Language Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Agneedh Basu, Nihar Desai, Pavan Kumar J, Prasanta Kumar Ghosh, Sujith P, Visruth Sanka","submitted_at":"2026-06-08T10:27:33Z","abstract_excerpt":"Spoken language identification (LID) for Indian languages is a challenging problem due to the large number of languages, significant phonetic overlap among related varieties, and the scarcity of labeled data for many low-resource languages. In this work, we present a systematic comparative study of two pre-trained speech encoders -- Whisper and FastConformer -- combined with a linear classifier for large-scale Indic LID spanning 42 languages across four linguistic families. We evaluate both encoders in frozen (linear probing) and fine-tuned settings, and compare three training objectives: cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09317","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/2606.09317/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":"2606.09317","created_at":"2026-06-09T02:08:14.647990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09317v1","created_at":"2026-06-09T02:08:14.647990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09317","created_at":"2026-06-09T02:08:14.647990+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUM2TF64ETA5","created_at":"2026-06-09T02:08:14.647990+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUM2TF64ETA5X2TP","created_at":"2026-06-09T02:08:14.647990+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUM2TF64","created_at":"2026-06-09T02:08:14.647990+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/VUM2TF64ETA5X2TPNNMFN3IRSV","json":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV.json","graph_json":"https://pith.science/api/pith-number/VUM2TF64ETA5X2TPNNMFN3IRSV/graph.json","events_json":"https://pith.science/api/pith-number/VUM2TF64ETA5X2TPNNMFN3IRSV/events.json","paper":"https://pith.science/paper/VUM2TF64"},"agent_actions":{"view_html":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV","download_json":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV.json","view_paper":"https://pith.science/paper/VUM2TF64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09317&json=true","fetch_graph":"https://pith.science/api/pith-number/VUM2TF64ETA5X2TPNNMFN3IRSV/graph.json","fetch_events":"https://pith.science/api/pith-number/VUM2TF64ETA5X2TPNNMFN3IRSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/action/storage_attestation","attest_author":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/action/author_attestation","sign_citation":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/action/citation_signature","submit_replication":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/action/replication_record"}},"created_at":"2026-06-09T02:08:14.647990+00:00","updated_at":"2026-06-09T02:08:14.647990+00:00"}