{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCPGLY4ASIPWIHPNHXBYFTUHQL","short_pith_number":"pith:MCPGLY4A","schema_version":"1.0","canonical_sha256":"609e65e380921f641ded3dc382ce8782e05fe99496d6f4a8b8608fe3cfb5949e","source":{"kind":"arxiv","id":"2401.08887","version":1},"attestation_state":"computed","paper":{"title":"NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alon Vinnikov, Amir Ivry, Aviv Hurvitz, Benjamin Martinez Elizalde, Eyal Krupka, Huaming Wang, Igor Abramovski, Ilya Gurvich, Min Tang, Naoyuki Kanda, Shai Pe`er, Shalev Shaer, Sharon Koubi, Stav Yagev, Sunit Sivasankaran, Xiaofei Wang, Xiong Xiao, Yifan Gong, Yossi Asher","submitted_at":"2024-01-16T23:50:26Z","abstract_excerpt":"We introduce the first Natural Office Talkers in Settings of Far-field Audio Recordings (``NOTSOFAR-1'') Challenge alongside datasets and baseline system. The challenge focuses on distant speaker diarization and automatic speech recognition (DASR) in far-field meeting scenarios, with single-channel and known-geometry multi-channel tracks, and serves as a launch platform for two new datasets: First, a benchmarking dataset of 315 meetings, averaging 6 minutes each, capturing a broad spectrum of real-world acoustic conditions and conversational dynamics. It is recorded across 30 conference rooms,"},"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":"2401.08887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T23:50:26Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"1cf589e9ddf2ef32d26604b3e1bd80d4ea48f52492bdb05584c7d3f4f221da9d","abstract_canon_sha256":"f1998bab6d7fca17930f8397826c27b7bc2fc990d0634af3eb197d0d3ad6b2e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:23.024459Z","signature_b64":"yqIyGntAB4yw/murdfiE9Q7LRiTdcYJeLq44uulyokhZVZcucXEfk0SScd7lM0wBDThCvNe5Odv191XcX4MwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"609e65e380921f641ded3dc382ce8782e05fe99496d6f4a8b8608fe3cfb5949e","last_reissued_at":"2026-07-05T07:34:23.023925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:23.023925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alon Vinnikov, Amir Ivry, Aviv Hurvitz, Benjamin Martinez Elizalde, Eyal Krupka, Huaming Wang, Igor Abramovski, Ilya Gurvich, Min Tang, Naoyuki Kanda, Shai Pe`er, Shalev Shaer, Sharon Koubi, Stav Yagev, Sunit Sivasankaran, Xiaofei Wang, Xiong Xiao, Yifan Gong, Yossi Asher","submitted_at":"2024-01-16T23:50:26Z","abstract_excerpt":"We introduce the first Natural Office Talkers in Settings of Far-field Audio Recordings (``NOTSOFAR-1'') Challenge alongside datasets and baseline system. The challenge focuses on distant speaker diarization and automatic speech recognition (DASR) in far-field meeting scenarios, with single-channel and known-geometry multi-channel tracks, and serves as a launch platform for two new datasets: First, a benchmarking dataset of 315 meetings, averaging 6 minutes each, capturing a broad spectrum of real-world acoustic conditions and conversational dynamics. It is recorded across 30 conference rooms,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08887","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/2401.08887/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":"2401.08887","created_at":"2026-07-05T07:34:23.023984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08887v1","created_at":"2026-07-05T07:34:23.023984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08887","created_at":"2026-07-05T07:34:23.023984+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCPGLY4ASIPW","created_at":"2026-07-05T07:34:23.023984+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCPGLY4ASIPWIHPN","created_at":"2026-07-05T07:34:23.023984+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCPGLY4A","created_at":"2026-07-05T07:34:23.023984+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/MCPGLY4ASIPWIHPNHXBYFTUHQL","json":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL.json","graph_json":"https://pith.science/api/pith-number/MCPGLY4ASIPWIHPNHXBYFTUHQL/graph.json","events_json":"https://pith.science/api/pith-number/MCPGLY4ASIPWIHPNHXBYFTUHQL/events.json","paper":"https://pith.science/paper/MCPGLY4A"},"agent_actions":{"view_html":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL","download_json":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL.json","view_paper":"https://pith.science/paper/MCPGLY4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08887&json=true","fetch_graph":"https://pith.science/api/pith-number/MCPGLY4ASIPWIHPNHXBYFTUHQL/graph.json","fetch_events":"https://pith.science/api/pith-number/MCPGLY4ASIPWIHPNHXBYFTUHQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL/action/storage_attestation","attest_author":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL/action/author_attestation","sign_citation":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL/action/citation_signature","submit_replication":"https://pith.science/pith/MCPGLY4ASIPWIHPNHXBYFTUHQL/action/replication_record"}},"created_at":"2026-07-05T07:34:23.023984+00:00","updated_at":"2026-07-05T07:34:23.023984+00:00"}