{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VUM2TF64ETA5X2TPNNMFN3IRSV","short_pith_number":"pith:VUM2TF64","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"},"canonical_sha256":"ad19a997dc24c1dbea6f6b5856ed119567a1ba82e057466652744823049e542b","source":{"kind":"arxiv","id":"2606.09317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09317","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09317v1","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09317","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"VUM2TF64ETA5","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"VUM2TF64ETA5X2TP","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"VUM2TF64","created_at":"2026-06-09T02:08:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VUM2TF64ETA5X2TPNNMFN3IRSV","target":"record","payload":{"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"},"canonical_sha256":"ad19a997dc24c1dbea6f6b5856ed119567a1ba82e057466652744823049e542b","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"},"source_kind":"arxiv","source_id":"2606.09317","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mI3hdM8R4eiXGgJbQqhq2trskcaZUZS5c/Vm1SiCn7uI5VQKZub5xDO2g0BhbZ0UUm0d1K7mFDlEM74duksrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T07:03:50.216746Z"},"content_sha256":"cafc96ae0299ae61d05a7efe8d48c55017a84aa0b82c3e53a4b9a11df17d8542","schema_version":"1.0","event_id":"sha256:cafc96ae0299ae61d05a7efe8d48c55017a84aa0b82c3e53a4b9a11df17d8542"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VUM2TF64ETA5X2TPNNMFN3IRSV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2XSE1lVNbeZx/2VokwPOn9wlmy84FsWexqClP5D9OaikcwBgLXoIZh4KlJlH3XDJUSgv3b0yI1ViqojCznwmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T07:03:50.217121Z"},"content_sha256":"d34acf175bbb197f78987feb49ae5cba2dee5e444f805a5390ba80f56ee19496","schema_version":"1.0","event_id":"sha256:d34acf175bbb197f78987feb49ae5cba2dee5e444f805a5390ba80f56ee19496"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/bundle.json","state_url":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-26T07:03:50Z","links":{"resolver":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV","bundle":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/bundle.json","state":"https://pith.science/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUM2TF64ETA5X2TPNNMFN3IRSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VUM2TF64ETA5X2TPNNMFN3IRSV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d22e19954d31bdfab0eed7664e586de2fad880a908f33bc3f8e1eb4358d8ce63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T10:27:33Z","title_canon_sha256":"dbd5284efe73917faaa4c8159032785c273af9dd3a68701444737d79b496646d"},"schema_version":"1.0","source":{"id":"2606.09317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09317","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09317v1","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09317","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"VUM2TF64ETA5","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"VUM2TF64ETA5X2TP","created_at":"2026-06-09T02:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"VUM2TF64","created_at":"2026-06-09T02:08:14Z"}],"graph_snapshots":[{"event_id":"sha256:d34acf175bbb197f78987feb49ae5cba2dee5e444f805a5390ba80f56ee19496","target":"graph","created_at":"2026-06-09T02:08:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.09317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Agneedh Basu, Nihar Desai, Pavan Kumar J, Prasanta Kumar Ghosh, Sujith P, Visruth Sanka","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T10:27:33Z","title":"A Comparative Study of Pre-trained Speech Encoders and Training Objectives for Large-Scale Indic Spoken Language Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09317","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cafc96ae0299ae61d05a7efe8d48c55017a84aa0b82c3e53a4b9a11df17d8542","target":"record","created_at":"2026-06-09T02:08:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d22e19954d31bdfab0eed7664e586de2fad880a908f33bc3f8e1eb4358d8ce63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T10:27:33Z","title_canon_sha256":"dbd5284efe73917faaa4c8159032785c273af9dd3a68701444737d79b496646d"},"schema_version":"1.0","source":{"id":"2606.09317","kind":"arxiv","version":1}},"canonical_sha256":"ad19a997dc24c1dbea6f6b5856ed119567a1ba82e057466652744823049e542b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad19a997dc24c1dbea6f6b5856ed119567a1ba82e057466652744823049e542b","first_computed_at":"2026-06-09T02:08:14.647852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:14.647852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WYTTXiN/fqa+Kw79r5TThlvnHYXvYjQVwzcYMGPX3F0QOJW03T2xXP7H1S/XZiUPDEo412k2GVVKH2nwHsLoAw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:14.649134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cafc96ae0299ae61d05a7efe8d48c55017a84aa0b82c3e53a4b9a11df17d8542","sha256:d34acf175bbb197f78987feb49ae5cba2dee5e444f805a5390ba80f56ee19496"],"state_sha256":"abd60f0fd27b407c2bf377e50ed815a265f2e384c7ee39daae4d2bde93b838ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2xngVHkY21M+1YCUWANh162TTggbeljMNJuVer9nNylhb9YQM7EyIF4aUMteTqHf7KpQwmHHjbUirozT3ivCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T07:03:50.219132Z","bundle_sha256":"c1516ba41c9a175a7e19846d826da749224cfe6dc8655ecc0f06b6d1cf2ad85b"}}