{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HXTO4DAQ3FVFAP74ADYB4JKNTC","short_pith_number":"pith:HXTO4DAQ","schema_version":"1.0","canonical_sha256":"3de6ee0c10d96a503ffc00f01e254d98a373bf1e44d5ef50be588f16a4ae1460","source":{"kind":"arxiv","id":"2507.02958","version":1},"attestation_state":"computed","paper":{"title":"Real-World En Call Center Transcripts Dataset with PII Redaction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caleb DeLeeuw, Gaurav Chawla, Ha Dao, Raghu Banda","submitted_at":"2025-06-30T03:41:02Z","abstract_excerpt":"We introduce CallCenterEN, a large-scale (91,706 conversations, corresponding to 10448 audio hours), real-world English call center transcript dataset designed to support research and development in customer support and sales AI systems. This is the largest release to-date of open source call center transcript data of this kind. The dataset includes inbound and outbound calls between agents and customers, with accents from India, the Philippines and the United States. The dataset includes high-quality, PII-redacted human-readable transcriptions. All personally identifiable information (PII) ha"},"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":"2507.02958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T03:41:02Z","cross_cats_sorted":[],"title_canon_sha256":"c76af9d53f897f9be5db3ca22e962b7e9e551b23aeabe206e349fe450a5967ec","abstract_canon_sha256":"3e8b3fbe4495d04e2b1e03ac8f6c5122ccd1f77a8b87a57ae32674fc3f7d5635"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:49.526092Z","signature_b64":"D7P/nqlPaDZUWew4rtEPNYusk58ihUINWgTpzrn9MoxLorKA8tqeqnK3mrn7aLbUG+upla/jsm3m6gRnrZEWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3de6ee0c10d96a503ffc00f01e254d98a373bf1e44d5ef50be588f16a4ae1460","last_reissued_at":"2026-07-05T11:31:49.525599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:49.525599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-World En Call Center Transcripts Dataset with PII Redaction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caleb DeLeeuw, Gaurav Chawla, Ha Dao, Raghu Banda","submitted_at":"2025-06-30T03:41:02Z","abstract_excerpt":"We introduce CallCenterEN, a large-scale (91,706 conversations, corresponding to 10448 audio hours), real-world English call center transcript dataset designed to support research and development in customer support and sales AI systems. This is the largest release to-date of open source call center transcript data of this kind. The dataset includes inbound and outbound calls between agents and customers, with accents from India, the Philippines and the United States. The dataset includes high-quality, PII-redacted human-readable transcriptions. All personally identifiable information (PII) ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02958","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/2507.02958/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":"2507.02958","created_at":"2026-07-05T11:31:49.525660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02958v1","created_at":"2026-07-05T11:31:49.525660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02958","created_at":"2026-07-05T11:31:49.525660+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXTO4DAQ3FVF","created_at":"2026-07-05T11:31:49.525660+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXTO4DAQ3FVFAP74","created_at":"2026-07-05T11:31:49.525660+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXTO4DAQ","created_at":"2026-07-05T11:31:49.525660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28048","citing_title":"DG^VoiC: Speaker Clustering for Fraud Investigation under Real Call-Centre Conditions","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC","json":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC.json","graph_json":"https://pith.science/api/pith-number/HXTO4DAQ3FVFAP74ADYB4JKNTC/graph.json","events_json":"https://pith.science/api/pith-number/HXTO4DAQ3FVFAP74ADYB4JKNTC/events.json","paper":"https://pith.science/paper/HXTO4DAQ"},"agent_actions":{"view_html":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC","download_json":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC.json","view_paper":"https://pith.science/paper/HXTO4DAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02958&json=true","fetch_graph":"https://pith.science/api/pith-number/HXTO4DAQ3FVFAP74ADYB4JKNTC/graph.json","fetch_events":"https://pith.science/api/pith-number/HXTO4DAQ3FVFAP74ADYB4JKNTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC/action/storage_attestation","attest_author":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC/action/author_attestation","sign_citation":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC/action/citation_signature","submit_replication":"https://pith.science/pith/HXTO4DAQ3FVFAP74ADYB4JKNTC/action/replication_record"}},"created_at":"2026-07-05T11:31:49.525660+00:00","updated_at":"2026-07-05T11:31:49.525660+00:00"}