{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DPRYJOYM6IIE6PA3YL4JT5HH6I","short_pith_number":"pith:DPRYJOYM","schema_version":"1.0","canonical_sha256":"1be384bb0cf2104f3c1bc2f899f4e7f2130b14ced29dfff83dda8152dee3321d","source":{"kind":"arxiv","id":"2507.00534","version":1},"attestation_state":"computed","paper":{"title":"NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaushal Bhogale, Mitesh M. Khapra, Tahir Javed","submitted_at":"2025-07-01T07:53:39Z","abstract_excerpt":"We introduce Nirantar, a comprehensive framework for evaluating continual learning (CL) in multilingual and multi-domain ASR. Designed to reflect real-world CL challenges, Nirantar leverages data collected incrementally across 22 languages and 208 districts in India through natural episodes. This enables evaluation across Language-Incremental (LIL), Domain-Incremental (DIL), and the novel Language-Incremental Domain-Incremental Learning (LIDIL) scenarios. Unlike prior work that relies on simulated episodes, Nirantar presents dynamic, non-uniform language and domain shifts, making it an ideal t"},"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":"2507.00534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T07:53:39Z","cross_cats_sorted":[],"title_canon_sha256":"c8e59e460f31e7a251c9ec95fccb2ec26e70be82dfaf77ec2d4f78e0141301a5","abstract_canon_sha256":"f1346270ae2456e953840468ccaad266f7029966a101713927c579772cadff28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:10.494516Z","signature_b64":"kJuXpZVzRIRuX/wmoD07s3X9B6coEJbp7jf8TvJgGTjsaQfeNwEBbF1Mnj7YsXMWfBaC6ih/fvwXeUhW1OatDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1be384bb0cf2104f3c1bc2f899f4e7f2130b14ced29dfff83dda8152dee3321d","last_reissued_at":"2026-07-05T11:30:10.494035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:10.494035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaushal Bhogale, Mitesh M. Khapra, Tahir Javed","submitted_at":"2025-07-01T07:53:39Z","abstract_excerpt":"We introduce Nirantar, a comprehensive framework for evaluating continual learning (CL) in multilingual and multi-domain ASR. Designed to reflect real-world CL challenges, Nirantar leverages data collected incrementally across 22 languages and 208 districts in India through natural episodes. This enables evaluation across Language-Incremental (LIL), Domain-Incremental (DIL), and the novel Language-Incremental Domain-Incremental Learning (LIDIL) scenarios. Unlike prior work that relies on simulated episodes, Nirantar presents dynamic, non-uniform language and domain shifts, making it an ideal t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00534","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/2507.00534/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":"2507.00534","created_at":"2026-07-05T11:30:10.494090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00534v1","created_at":"2026-07-05T11:30:10.494090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00534","created_at":"2026-07-05T11:30:10.494090+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPRYJOYM6IIE","created_at":"2026-07-05T11:30:10.494090+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPRYJOYM6IIE6PA3","created_at":"2026-07-05T11:30:10.494090+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPRYJOYM","created_at":"2026-07-05T11:30:10.494090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00534","citing_title":"NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I","json":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I.json","graph_json":"https://pith.science/api/pith-number/DPRYJOYM6IIE6PA3YL4JT5HH6I/graph.json","events_json":"https://pith.science/api/pith-number/DPRYJOYM6IIE6PA3YL4JT5HH6I/events.json","paper":"https://pith.science/paper/DPRYJOYM"},"agent_actions":{"view_html":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I","download_json":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I.json","view_paper":"https://pith.science/paper/DPRYJOYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00534&json=true","fetch_graph":"https://pith.science/api/pith-number/DPRYJOYM6IIE6PA3YL4JT5HH6I/graph.json","fetch_events":"https://pith.science/api/pith-number/DPRYJOYM6IIE6PA3YL4JT5HH6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I/action/storage_attestation","attest_author":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I/action/author_attestation","sign_citation":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I/action/citation_signature","submit_replication":"https://pith.science/pith/DPRYJOYM6IIE6PA3YL4JT5HH6I/action/replication_record"}},"created_at":"2026-07-05T11:30:10.494090+00:00","updated_at":"2026-07-05T11:30:10.494090+00:00"}