{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:B72SMFSUDPRGM57HARNUWB7XRB","short_pith_number":"pith:B72SMFSU","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"},"canonical_sha256":"0ff52616541be26677e7045b4b07f788701cf25cbdff296565c8d980d1579447","source":{"kind":"arxiv","id":"2004.03090","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03090","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03090v1","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03090","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"pith_short_12","alias_value":"B72SMFSUDPRG","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"pith_short_16","alias_value":"B72SMFSUDPRGM57H","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"pith_short_8","alias_value":"B72SMFSU","created_at":"2026-07-05T00:53:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:B72SMFSUDPRGM57HARNUWB7XRB","target":"record","payload":{"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"},"canonical_sha256":"0ff52616541be26677e7045b4b07f788701cf25cbdff296565c8d980d1579447","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"},"source_kind":"arxiv","source_id":"2004.03090","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":"2026-07-05T00:53:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbN4EzxpEzUoj2IYV0WtoXm5jeKub/mwsYXWpPXyz6zEOxl/8KVs7eRfHcFgXReMSQ+WAAgf2kECFZxFVvBSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:42:49.660285Z"},"content_sha256":"49bb6a5c8277172aa6658f71aa28c8333f81d5dc46b2b15e88816d07c3cf7d50","schema_version":"1.0","event_id":"sha256:49bb6a5c8277172aa6658f71aa28c8333f81d5dc46b2b15e88816d07c3cf7d50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:B72SMFSUDPRGM57HARNUWB7XRB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:53:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTf+s40ZiW0ifcRp63c9dPKzEWK176ieRwSBfFYlefDLhLx7kOzQqYGPzeiE5ww1vQpjeQRg9uu3Uzd5tyyuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:42:49.661349Z"},"content_sha256":"2d820b20f0b3fc505a0438cd7b9978f7f2a703e2cfeb707ffebcafadb15fee5c","schema_version":"1.0","event_id":"sha256:2d820b20f0b3fc505a0438cd7b9978f7f2a703e2cfeb707ffebcafadb15fee5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/bundle.json","state_url":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B72SMFSUDPRGM57HARNUWB7XRB/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":"2026-08-09T23:42:49Z","links":{"resolver":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB","bundle":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/bundle.json","state":"https://pith.science/pith/B72SMFSUDPRGM57HARNUWB7XRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B72SMFSUDPRGM57HARNUWB7XRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:B72SMFSUDPRGM57HARNUWB7XRB","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":"aee880a1a705aec8c9d075f8b3d583346544f3efd1a0387f5cbd08c947d5f0de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T02:44:50Z","title_canon_sha256":"a477b50335ad7ad20f06c49225f983f99a036fec319e1d0a118281f5ca07dff9"},"schema_version":"1.0","source":{"id":"2004.03090","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03090","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03090v1","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03090","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"pith_short_12","alias_value":"B72SMFSUDPRG","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"pith_short_16","alias_value":"B72SMFSUDPRGM57H","created_at":"2026-07-05T00:53:23Z"},{"alias_kind":"pith_short_8","alias_value":"B72SMFSU","created_at":"2026-07-05T00:53:23Z"}],"graph_snapshots":[{"event_id":"sha256:2d820b20f0b3fc505a0438cd7b9978f7f2a703e2cfeb707ffebcafadb15fee5c","target":"graph","created_at":"2026-07-05T00:53:23Z","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/2004.03090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bodhisattwa Prasad Majumder, Jianmo Ni, Julian McAuley, Shuyang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T02:44:50Z","title":"Interview: A Large-Scale Open-Source Corpus of Media Dialog"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03090","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":"sha256:49bb6a5c8277172aa6658f71aa28c8333f81d5dc46b2b15e88816d07c3cf7d50","target":"record","created_at":"2026-07-05T00:53:23Z","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":"aee880a1a705aec8c9d075f8b3d583346544f3efd1a0387f5cbd08c947d5f0de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T02:44:50Z","title_canon_sha256":"a477b50335ad7ad20f06c49225f983f99a036fec319e1d0a118281f5ca07dff9"},"schema_version":"1.0","source":{"id":"2004.03090","kind":"arxiv","version":1}},"canonical_sha256":"0ff52616541be26677e7045b4b07f788701cf25cbdff296565c8d980d1579447","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ff52616541be26677e7045b4b07f788701cf25cbdff296565c8d980d1579447","first_computed_at":"2026-07-05T00:53:23.122967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:23.122967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mYde1MX5OL7jJLrAETUwfRwZ98TnnboB+HyXz2tRSwLYhP0aEU2/w/gqxxR9KbD3f/AY/dsxI+2RPc7VPpi+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:23.123466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.03090","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49bb6a5c8277172aa6658f71aa28c8333f81d5dc46b2b15e88816d07c3cf7d50","sha256:2d820b20f0b3fc505a0438cd7b9978f7f2a703e2cfeb707ffebcafadb15fee5c"],"state_sha256":"00a433a7b15d2ef4eecc75943ebfa570124e0eee53845b297b7aacae0b7cc7cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I/mZetUhUFZaHFAGEkL6GfWDWJxhbBFLOV4YkFOj8NHGcjHreQHDsEtzQzLCQm0aiNYR++pAA11XjXBMKN49CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:42:49.666188Z","bundle_sha256":"95c8b86bc4045e8bce78ab0669199f3df0813597cd84beef1afc1e9a8fb0d9f8"}}