{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B72SMFSUDPRGM57HARNUWB7XRB","short_pith_number":"pith:B72SMFSU","schema_version":"1.0","canonical_sha256":"0ff52616541be26677e7045b4b07f788701cf25cbdff296565c8d980d1579447","source":{"kind":"arxiv","id":"2004.03090","version":1},"attestation_state":"computed","paper":{"title":"Interview: A Large-Scale Open-Source Corpus of Media Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bodhisattwa Prasad Majumder, Jianmo Ni, Julian McAuley, Shuyang Li","submitted_at":"2020-04-07T02:44:50Z","abstract_excerpt":"Existing conversational datasets consist either of written proxies for dialog or small-scale transcriptions of natural speech. We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview transcripts. Compared to existing large-scale proxies for conversational data, language models trained on our dataset exhibit better zero-shot out-of-domain performance on existing spoken dialog datasets, demonstrating its usefulness in modeling real-world conversations. 'Interview' contains speaker role annotations for each turn, facilitating the development"},"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":"2004.03090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T02:44:50Z","cross_cats_sorted":[],"title_canon_sha256":"a477b50335ad7ad20f06c49225f983f99a036fec319e1d0a118281f5ca07dff9","abstract_canon_sha256":"aee880a1a705aec8c9d075f8b3d583346544f3efd1a0387f5cbd08c947d5f0de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:23.123466Z","signature_b64":"mYde1MX5OL7jJLrAETUwfRwZ98TnnboB+HyXz2tRSwLYhP0aEU2/w/gqxxR9KbD3f/AY/dsxI+2RPc7VPpi+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ff52616541be26677e7045b4b07f788701cf25cbdff296565c8d980d1579447","last_reissued_at":"2026-07-05T00:53:23.122967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:23.122967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interview: A Large-Scale Open-Source Corpus of Media Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bodhisattwa Prasad Majumder, Jianmo Ni, Julian McAuley, Shuyang Li","submitted_at":"2020-04-07T02:44:50Z","abstract_excerpt":"Existing conversational datasets consist either of written proxies for dialog or small-scale transcriptions of natural speech. We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview transcripts. Compared to existing large-scale proxies for conversational data, language models trained on our dataset exhibit better zero-shot out-of-domain performance on existing spoken dialog datasets, demonstrating its usefulness in modeling real-world conversations. 'Interview' contains speaker role annotations for each turn, facilitating the development"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03090","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/2004.03090/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":"2004.03090","created_at":"2026-07-05T00:53:23.123029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03090v1","created_at":"2026-07-05T00:53:23.123029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03090","created_at":"2026-07-05T00:53:23.123029+00:00"},{"alias_kind":"pith_short_12","alias_value":"B72SMFSUDPRG","created_at":"2026-07-05T00:53:23.123029+00:00"},{"alias_kind":"pith_short_16","alias_value":"B72SMFSUDPRGM57H","created_at":"2026-07-05T00:53:23.123029+00:00"},{"alias_kind":"pith_short_8","alias_value":"B72SMFSU","created_at":"2026-07-05T00:53:23.123029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04564","citing_title":"My LLM might Mimic AAE -- But When Should it?","ref_index":2019,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB","json":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB.json","graph_json":"https://pith.science/api/pith-number/B72SMFSUDPRGM57HARNUWB7XRB/graph.json","events_json":"https://pith.science/api/pith-number/B72SMFSUDPRGM57HARNUWB7XRB/events.json","paper":"https://pith.science/paper/B72SMFSU"},"agent_actions":{"view_html":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB","download_json":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB.json","view_paper":"https://pith.science/paper/B72SMFSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03090&json=true","fetch_graph":"https://pith.science/api/pith-number/B72SMFSUDPRGM57HARNUWB7XRB/graph.json","fetch_events":"https://pith.science/api/pith-number/B72SMFSUDPRGM57HARNUWB7XRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/action/storage_attestation","attest_author":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/action/author_attestation","sign_citation":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/action/citation_signature","submit_replication":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/action/replication_record"}},"created_at":"2026-07-05T00:53:23.123029+00:00","updated_at":"2026-07-05T00:53:23.123029+00:00"}