{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DK4C56ZBOC6CEVW2UA6BXHUHNS","short_pith_number":"pith:DK4C56ZB","canonical_record":{"source":{"id":"2302.05110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-10T08:21:42Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"cace9d0bd80507aa054d50ebfb827b1c05e9690e9cf2f76e1cf65d65d24c9ebc","abstract_canon_sha256":"e8df73f1301fc43f1c636cbf687c8e2cc2f746eaf181454f4090b81ab714ca4f"},"schema_version":"1.0"},"canonical_sha256":"1ab82efb2170bc2256daa03c1b9e876cadfc0af61b08849b5abd8e10a1f8cb69","source":{"kind":"arxiv","id":"2302.05110","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05110","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05110v1","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05110","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"DK4C56ZBOC6C","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"DK4C56ZBOC6CEVW2","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"DK4C56ZB","created_at":"2026-07-05T05:47:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DK4C56ZBOC6CEVW2UA6BXHUHNS","target":"record","payload":{"canonical_record":{"source":{"id":"2302.05110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-10T08:21:42Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"cace9d0bd80507aa054d50ebfb827b1c05e9690e9cf2f76e1cf65d65d24c9ebc","abstract_canon_sha256":"e8df73f1301fc43f1c636cbf687c8e2cc2f746eaf181454f4090b81ab714ca4f"},"schema_version":"1.0"},"canonical_sha256":"1ab82efb2170bc2256daa03c1b9e876cadfc0af61b08849b5abd8e10a1f8cb69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:05.965381Z","signature_b64":"GFmUkc8s8c0wMQkN1Cy1HBDaUJuGznXukeGm4OrXjnwfmB2iHxv9tMFVFS0CXkVVxysicf1PhfFHV3fEHX0YDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ab82efb2170bc2256daa03c1b9e876cadfc0af61b08849b5abd8e10a1f8cb69","last_reissued_at":"2026-07-05T05:47:05.964925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:05.964925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.05110","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":"2026-07-05T05:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V0yeAtKl+e6hc97R4MpZAuAHstEe4wXwScTP9fyA2i2friKpzg/W/6k7VFRFH8n58t9CzdlSDAfo4WdHGXZZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:12:16.304815Z"},"content_sha256":"bd2f9339f4c3392dd3fda6e2f3dc4324e3ebd2bb9acbe3147521ba5c1d6e5901","schema_version":"1.0","event_id":"sha256:bd2f9339f4c3392dd3fda6e2f3dc4324e3ebd2bb9acbe3147521ba5c1d6e5901"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DK4C56ZBOC6CEVW2UA6BXHUHNS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Goutam Saha, Md Sahidullah, Spandan Dey","submitted_at":"2023-02-10T08:21:42Z","abstract_excerpt":"This work addresses the cross-corpora generalization issue for the low-resourced spoken language identification (LID) problem. We have conducted the experiments in the context of Indian LID and identified strikingly poor cross-corpora generalization due to corpora-dependent non-lingual biases. Our contribution to this work is twofold. First, we propose domain diversification, which diversifies the limited training data using different audio data augmentation methods. We then propose the concept of maximally diversity-aware cascaded augmentations and optimize the augmentation fold-factor for ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05110","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/2302.05110/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":"2026-07-05T05:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLccorShtw44AFyaNKeLaTqTV9SM3bNDqzlqfmHmTH+VrBnjZJvcPa/z7DDZj6p3KuMehnikKzHKaN9psEpbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:12:16.305329Z"},"content_sha256":"3bce001fa8b06ec8fe98862fe23997da1d3b1eec4ec0ad75d1dba38615400429","schema_version":"1.0","event_id":"sha256:3bce001fa8b06ec8fe98862fe23997da1d3b1eec4ec0ad75d1dba38615400429"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DK4C56ZBOC6CEVW2UA6BXHUHNS/bundle.json","state_url":"https://pith.science/pith/DK4C56ZBOC6CEVW2UA6BXHUHNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DK4C56ZBOC6CEVW2UA6BXHUHNS/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":"2026-08-19T05:12:16Z","links":{"resolver":"https://pith.science/pith/DK4C56ZBOC6CEVW2UA6BXHUHNS","bundle":"https://pith.science/pith/DK4C56ZBOC6CEVW2UA6BXHUHNS/bundle.json","state":"https://pith.science/pith/DK4C56ZBOC6CEVW2UA6BXHUHNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DK4C56ZBOC6CEVW2UA6BXHUHNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DK4C56ZBOC6CEVW2UA6BXHUHNS","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":"e8df73f1301fc43f1c636cbf687c8e2cc2f746eaf181454f4090b81ab714ca4f","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-10T08:21:42Z","title_canon_sha256":"cace9d0bd80507aa054d50ebfb827b1c05e9690e9cf2f76e1cf65d65d24c9ebc"},"schema_version":"1.0","source":{"id":"2302.05110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05110","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05110v1","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05110","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"DK4C56ZBOC6C","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"DK4C56ZBOC6CEVW2","created_at":"2026-07-05T05:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"DK4C56ZB","created_at":"2026-07-05T05:47:05Z"}],"graph_snapshots":[{"event_id":"sha256:3bce001fa8b06ec8fe98862fe23997da1d3b1eec4ec0ad75d1dba38615400429","target":"graph","created_at":"2026-07-05T05:47:05Z","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/2302.05110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work addresses the cross-corpora generalization issue for the low-resourced spoken language identification (LID) problem. We have conducted the experiments in the context of Indian LID and identified strikingly poor cross-corpora generalization due to corpora-dependent non-lingual biases. Our contribution to this work is twofold. First, we propose domain diversification, which diversifies the limited training data using different audio data augmentation methods. We then propose the concept of maximally diversity-aware cascaded augmentations and optimize the augmentation fold-factor for ef","authors_text":"Goutam Saha, Md Sahidullah, Spandan Dey","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-10T08:21:42Z","title":"Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05110","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:bd2f9339f4c3392dd3fda6e2f3dc4324e3ebd2bb9acbe3147521ba5c1d6e5901","target":"record","created_at":"2026-07-05T05:47:05Z","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":"e8df73f1301fc43f1c636cbf687c8e2cc2f746eaf181454f4090b81ab714ca4f","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-10T08:21:42Z","title_canon_sha256":"cace9d0bd80507aa054d50ebfb827b1c05e9690e9cf2f76e1cf65d65d24c9ebc"},"schema_version":"1.0","source":{"id":"2302.05110","kind":"arxiv","version":1}},"canonical_sha256":"1ab82efb2170bc2256daa03c1b9e876cadfc0af61b08849b5abd8e10a1f8cb69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ab82efb2170bc2256daa03c1b9e876cadfc0af61b08849b5abd8e10a1f8cb69","first_computed_at":"2026-07-05T05:47:05.964925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:05.964925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GFmUkc8s8c0wMQkN1Cy1HBDaUJuGznXukeGm4OrXjnwfmB2iHxv9tMFVFS0CXkVVxysicf1PhfFHV3fEHX0YDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:05.965381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd2f9339f4c3392dd3fda6e2f3dc4324e3ebd2bb9acbe3147521ba5c1d6e5901","sha256:3bce001fa8b06ec8fe98862fe23997da1d3b1eec4ec0ad75d1dba38615400429"],"state_sha256":"120bb3b27192d22dc74370485b39396400c87a1dc68d5cd5afe9a16b9c15c34c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HgVDdadKjfxpkMqGMOpO7ycMP6IZjB3rTTJ2HEoU5m1tN5S2+U6ytfGJQWnUiq2Es/cjjDIycVHWJJ1SfB6sBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:12:16.310094Z","bundle_sha256":"a0515496e7e8f643f026f09baea7615f2c988cd7786fa27c0228562772bb6e0c"}}