{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:62AXTH25FIUVR7GYWW3RFYR3HG","short_pith_number":"pith:62AXTH25","canonical_record":{"source":{"id":"2607.23808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-26T19:12:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af4a132834be62bf0ef76c9bd758527037590fee29dce40fccf1c31242f3e76f","abstract_canon_sha256":"6d313796ba2f582765107b16f93498d2c7effe65acd578d080ef3f00f2b2852d"},"schema_version":"1.0"},"canonical_sha256":"f681799f5d2a2958fcd8b5b712e23b39972a8274ee805f5e5046d21ecd89fb3a","source":{"kind":"arxiv","id":"2607.23808","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23808","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23808v1","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23808","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"62AXTH25FIUV","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"62AXTH25FIUVR7GY","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"62AXTH25","created_at":"2026-07-28T01:23:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:62AXTH25FIUVR7GYWW3RFYR3HG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-26T19:12:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af4a132834be62bf0ef76c9bd758527037590fee29dce40fccf1c31242f3e76f","abstract_canon_sha256":"6d313796ba2f582765107b16f93498d2c7effe65acd578d080ef3f00f2b2852d"},"schema_version":"1.0"},"canonical_sha256":"f681799f5d2a2958fcd8b5b712e23b39972a8274ee805f5e5046d21ecd89fb3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:12.203275Z","signature_b64":"qy1dRs3CQWfPCjpTQOMYdVKDGOPOELctS+Symk3gDuxHGbgeegQ6Q/WtGhw64vZsV5FU4QSB4vKlJIEaNilaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f681799f5d2a2958fcd8b5b712e23b39972a8274ee805f5e5046d21ecd89fb3a","last_reissued_at":"2026-07-28T01:23:12.202511Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:12.202511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23808","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":"2026-07-28T01:23:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PB43Swl6uEJ0wD5FYrWobB0nS/a4suDTbligbrKauXCJEQZxcxVBDKjhuDV/hdTgZhMjidpBui7JmBnghZW2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:57:46.211992Z"},"content_sha256":"cb7ed5b7b8d390bad547ab9108111d9aca3c70440b81bee78a9a7d9090a8c9e6","schema_version":"1.0","event_id":"sha256:cb7ed5b7b8d390bad547ab9108111d9aca3c70440b81bee78a9a7d9090a8c9e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:62AXTH25FIUVR7GYWW3RFYR3HG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Mehndiratta, Deovrat Mehendale, Dhruv Rathi, Kaushal Bhogale, Mitesh M. Khapra","submitted_at":"2026-07-26T19:12:39Z","abstract_excerpt":"In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India. This corpus comprises approximately 108 hours of natural multi-speaker audio from near-field meetings, far-field recordings, and in-the-wild audios. All annotations are human-corrected with time-aligned speaker attributed transcriptions. The dataset captures conversational nuance prevalent in Indian speech, such as English code-mixing, dialectal variation, and frequent speaker overlap. To establish a baseline for joint ASR and diarization capabilities we eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23808","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/2607.23808/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":"2026-07-28T01:23:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s93IoCy5ODuRuOilPI+DiZdRAPq53e6lye9Rus5gXJzCKFWZYs5ZGnokiictKLQGZGh+6nCkAHyonFiuGqIYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:57:46.213076Z"},"content_sha256":"0d3f3126da18ad7ea9f2519f7f550270eda89fef613d03c3ce55c7d28285577a","schema_version":"1.0","event_id":"sha256:0d3f3126da18ad7ea9f2519f7f550270eda89fef613d03c3ce55c7d28285577a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/bundle.json","state_url":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62AXTH25FIUVR7GYWW3RFYR3HG/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":"2026-08-12T17:57:46Z","links":{"resolver":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG","bundle":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/bundle.json","state":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62AXTH25FIUVR7GYWW3RFYR3HG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:62AXTH25FIUVR7GYWW3RFYR3HG","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":"6d313796ba2f582765107b16f93498d2c7effe65acd578d080ef3f00f2b2852d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-26T19:12:39Z","title_canon_sha256":"af4a132834be62bf0ef76c9bd758527037590fee29dce40fccf1c31242f3e76f"},"schema_version":"1.0","source":{"id":"2607.23808","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23808","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23808v1","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23808","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"62AXTH25FIUV","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"62AXTH25FIUVR7GY","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"62AXTH25","created_at":"2026-07-28T01:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:0d3f3126da18ad7ea9f2519f7f550270eda89fef613d03c3ce55c7d28285577a","target":"graph","created_at":"2026-07-28T01:23:12Z","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/2607.23808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India. This corpus comprises approximately 108 hours of natural multi-speaker audio from near-field meetings, far-field recordings, and in-the-wild audios. All annotations are human-corrected with time-aligned speaker attributed transcriptions. The dataset captures conversational nuance prevalent in Indian speech, such as English code-mixing, dialectal variation, and frequent speaker overlap. To establish a baseline for joint ASR and diarization capabilities we eva","authors_text":"Aditya Mehndiratta, Deovrat Mehendale, Dhruv Rathi, Kaushal Bhogale, Mitesh M. Khapra","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-26T19:12:39Z","title":"Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23808","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:cb7ed5b7b8d390bad547ab9108111d9aca3c70440b81bee78a9a7d9090a8c9e6","target":"record","created_at":"2026-07-28T01:23:12Z","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":"6d313796ba2f582765107b16f93498d2c7effe65acd578d080ef3f00f2b2852d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-26T19:12:39Z","title_canon_sha256":"af4a132834be62bf0ef76c9bd758527037590fee29dce40fccf1c31242f3e76f"},"schema_version":"1.0","source":{"id":"2607.23808","kind":"arxiv","version":1}},"canonical_sha256":"f681799f5d2a2958fcd8b5b712e23b39972a8274ee805f5e5046d21ecd89fb3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f681799f5d2a2958fcd8b5b712e23b39972a8274ee805f5e5046d21ecd89fb3a","first_computed_at":"2026-07-28T01:23:12.202511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:12.202511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qy1dRs3CQWfPCjpTQOMYdVKDGOPOELctS+Symk3gDuxHGbgeegQ6Q/WtGhw64vZsV5FU4QSB4vKlJIEaNilaBw==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:12.203275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23808","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb7ed5b7b8d390bad547ab9108111d9aca3c70440b81bee78a9a7d9090a8c9e6","sha256:0d3f3126da18ad7ea9f2519f7f550270eda89fef613d03c3ce55c7d28285577a"],"state_sha256":"99208cb3325cac2feab30b6eb235755c94387a080498a02748fb4dc30a658105"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohfvsZPVraMOooHLZSAq+qfZ+7x5IrH8hUWD9almynYxuvWdtGZlEH1DZFAo3Kco8U5fdHgeaQFDVdCfZw+kCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T17:57:46.218910Z","bundle_sha256":"9910633ef227ec74c00d8e8e0c7a9076e4ad4d37b30ff5a97f1351f39b6f208f"}}