{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KIIFJAEZL2NW4MIPXI2YV7PI4C","short_pith_number":"pith:KIIFJAEZ","schema_version":"1.0","canonical_sha256":"52105480995e9b6e310fba358afde8e08b3bcad0a3066011057105ca0313626e","source":{"kind":"arxiv","id":"2606.19940","version":1},"attestation_state":"computed","paper":{"title":"Analyzing Language and Geographical Variation in Speech Representations Across 60 Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Agneedh Basu, Nihar Desai, Pavan Kumar J, Pranav Bhat, Prasanta Kumar Ghosh, Sujith Pulikodan, Visruth Sanka","submitted_at":"2026-06-18T08:39:03Z","abstract_excerpt":"Self-supervised speech encoders are often fine-tuned with language supervision, which can overlook geographical variation. To understand the learned representations under joint supervision of language and district compared to language-only supervision, we fine-tune Whisper-base and Wav2Vec2.0-base for classification tasks with joint language-district (386 classes) and language-only classification (60 languages). The language-district supervision improves district discrimination conditioned on language in the embedding space while strong marginal language classification. We analyze the structur"},"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":"2606.19940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T08:39:03Z","cross_cats_sorted":[],"title_canon_sha256":"9796d173864b7507faa38094e04b72c42719ab07251a4c91f02466cec50158a4","abstract_canon_sha256":"6f93a688456338555af6b77db9b3bc72a6047403dbfb6db5aeff42402d0a2183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:58.752614Z","signature_b64":"G/4bOmI2+xD6Xjw3rl0YFqFNp1F4q8HYmdhvy+UXhd16zg/r7RMUPzo3Ed7iLVY+67cI95www/HzfDCw/yE3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52105480995e9b6e310fba358afde8e08b3bcad0a3066011057105ca0313626e","last_reissued_at":"2026-06-19T16:12:58.752258Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:58.752258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing Language and Geographical Variation in Speech Representations Across 60 Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Agneedh Basu, Nihar Desai, Pavan Kumar J, Pranav Bhat, Prasanta Kumar Ghosh, Sujith Pulikodan, Visruth Sanka","submitted_at":"2026-06-18T08:39:03Z","abstract_excerpt":"Self-supervised speech encoders are often fine-tuned with language supervision, which can overlook geographical variation. To understand the learned representations under joint supervision of language and district compared to language-only supervision, we fine-tune Whisper-base and Wav2Vec2.0-base for classification tasks with joint language-district (386 classes) and language-only classification (60 languages). The language-district supervision improves district discrimination conditioned on language in the embedding space while strong marginal language classification. We analyze the structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19940","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/2606.19940/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":"2606.19940","created_at":"2026-06-19T16:12:58.752325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19940v1","created_at":"2026-06-19T16:12:58.752325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19940","created_at":"2026-06-19T16:12:58.752325+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIIFJAEZL2NW","created_at":"2026-06-19T16:12:58.752325+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIIFJAEZL2NW4MIP","created_at":"2026-06-19T16:12:58.752325+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIIFJAEZ","created_at":"2026-06-19T16:12:58.752325+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/KIIFJAEZL2NW4MIPXI2YV7PI4C","json":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C.json","graph_json":"https://pith.science/api/pith-number/KIIFJAEZL2NW4MIPXI2YV7PI4C/graph.json","events_json":"https://pith.science/api/pith-number/KIIFJAEZL2NW4MIPXI2YV7PI4C/events.json","paper":"https://pith.science/paper/KIIFJAEZ"},"agent_actions":{"view_html":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C","download_json":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C.json","view_paper":"https://pith.science/paper/KIIFJAEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19940&json=true","fetch_graph":"https://pith.science/api/pith-number/KIIFJAEZL2NW4MIPXI2YV7PI4C/graph.json","fetch_events":"https://pith.science/api/pith-number/KIIFJAEZL2NW4MIPXI2YV7PI4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C/action/storage_attestation","attest_author":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C/action/author_attestation","sign_citation":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C/action/citation_signature","submit_replication":"https://pith.science/pith/KIIFJAEZL2NW4MIPXI2YV7PI4C/action/replication_record"}},"created_at":"2026-06-19T16:12:58.752325+00:00","updated_at":"2026-06-19T16:12:58.752325+00:00"}