{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:45X5I7DEK2IV7Q4V2SIWI4GHZC","short_pith_number":"pith:45X5I7DE","canonical_record":{"source":{"id":"1907.07073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-16T15:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"d6e2f2720899dc74d8bcad0d8b6b10e48bc28fbf6a57978a86a9e49bfd7b1917","abstract_canon_sha256":"ad2a8ba6a16ebc88d8205b590d71b283b6d96f6bad0d5139b766cd7db4c5839b"},"schema_version":"1.0"},"canonical_sha256":"e76fd47c6456915fc395d4916470c7c883f9e2636e07917aa315bb1ce10af381","source":{"kind":"arxiv","id":"1907.07073","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07073","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07073v1","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07073","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"45X5I7DEK2IV","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"45X5I7DEK2IV7Q4V","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"45X5I7DE","created_at":"2026-07-05T00:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:45X5I7DEK2IV7Q4V2SIWI4GHZC","target":"record","payload":{"canonical_record":{"source":{"id":"1907.07073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-16T15:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"d6e2f2720899dc74d8bcad0d8b6b10e48bc28fbf6a57978a86a9e49bfd7b1917","abstract_canon_sha256":"ad2a8ba6a16ebc88d8205b590d71b283b6d96f6bad0d5139b766cd7db4c5839b"},"schema_version":"1.0"},"canonical_sha256":"e76fd47c6456915fc395d4916470c7c883f9e2636e07917aa315bb1ce10af381","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:12.459218Z","signature_b64":"Y3cysnAk9tEeaitOm4Cg9Lkqiz/trZ22nm8GSfKSTnjmkyJLaYRmb8WiccQQIV+MxMz7cmFn/8nFoarPVFdUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e76fd47c6456915fc395d4916470c7c883f9e2636e07917aa315bb1ce10af381","last_reissued_at":"2026-07-05T00:05:12.458613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:12.458613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.07073","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":"2026-07-05T00:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MORzfY+GiDe5xzXBrFaqD2uxuCOlgImlRUn9LJHVZS16KQN0dx9O0docA9BS9gm63B9IWuzHvG/WvIXLLMx+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:06:40.235561Z"},"content_sha256":"e5489c27c1a74acb6930ca6a39e92046636f678b32b7531cebc21bec24a5904f","schema_version":"1.0","event_id":"sha256:e5489c27c1a74acb6930ca6a39e92046636f678b32b7531cebc21bec24a5904f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:45X5I7DEK2IV7Q4V2SIWI4GHZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RadioTalk: a large-scale corpus of talk radio transcripts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deb Roy, Doug Beeferman, William Brannon","submitted_at":"2019-07-16T15:34:58Z","abstract_excerpt":"We introduce RadioTalk, a corpus of speech recognition transcripts sampled from talk radio broadcasts in the United States between October of 2018 and March of 2019. The corpus is intended for use by researchers in the fields of natural language processing, conversational analysis, and the social sciences. The corpus encompasses approximately 2.8 billion words of automatically transcribed speech from 284,000 hours of radio, together with metadata about the speech, such as geographical location, speaker turn boundaries, gender, and radio program information. In this paper we summarize why and h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07073","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/1907.07073/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":"2026-07-05T00:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFhnT6BtbNZfaTp9sJJxKxBOHZzxcvpYyCmngm61GQeo51nS/kiihUlcIBGAkwhdLDKHBIlXiqq+Wq6x/yCFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:06:40.236341Z"},"content_sha256":"215d1edfe8d88dcd501c7ee06d4753784327ce96a1c30437b961c42db285ae5b","schema_version":"1.0","event_id":"sha256:215d1edfe8d88dcd501c7ee06d4753784327ce96a1c30437b961c42db285ae5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45X5I7DEK2IV7Q4V2SIWI4GHZC/bundle.json","state_url":"https://pith.science/pith/45X5I7DEK2IV7Q4V2SIWI4GHZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45X5I7DEK2IV7Q4V2SIWI4GHZC/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":"2026-08-11T00:06:40Z","links":{"resolver":"https://pith.science/pith/45X5I7DEK2IV7Q4V2SIWI4GHZC","bundle":"https://pith.science/pith/45X5I7DEK2IV7Q4V2SIWI4GHZC/bundle.json","state":"https://pith.science/pith/45X5I7DEK2IV7Q4V2SIWI4GHZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45X5I7DEK2IV7Q4V2SIWI4GHZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:45X5I7DEK2IV7Q4V2SIWI4GHZC","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":"ad2a8ba6a16ebc88d8205b590d71b283b6d96f6bad0d5139b766cd7db4c5839b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-16T15:34:58Z","title_canon_sha256":"d6e2f2720899dc74d8bcad0d8b6b10e48bc28fbf6a57978a86a9e49bfd7b1917"},"schema_version":"1.0","source":{"id":"1907.07073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07073","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07073v1","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07073","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"45X5I7DEK2IV","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"45X5I7DEK2IV7Q4V","created_at":"2026-07-05T00:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"45X5I7DE","created_at":"2026-07-05T00:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:215d1edfe8d88dcd501c7ee06d4753784327ce96a1c30437b961c42db285ae5b","target":"graph","created_at":"2026-07-05T00:05:12Z","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/1907.07073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce RadioTalk, a corpus of speech recognition transcripts sampled from talk radio broadcasts in the United States between October of 2018 and March of 2019. The corpus is intended for use by researchers in the fields of natural language processing, conversational analysis, and the social sciences. The corpus encompasses approximately 2.8 billion words of automatically transcribed speech from 284,000 hours of radio, together with metadata about the speech, such as geographical location, speaker turn boundaries, gender, and radio program information. In this paper we summarize why and h","authors_text":"Deb Roy, Doug Beeferman, William Brannon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-16T15:34:58Z","title":"RadioTalk: a large-scale corpus of talk radio transcripts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07073","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:e5489c27c1a74acb6930ca6a39e92046636f678b32b7531cebc21bec24a5904f","target":"record","created_at":"2026-07-05T00:05:12Z","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":"ad2a8ba6a16ebc88d8205b590d71b283b6d96f6bad0d5139b766cd7db4c5839b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-16T15:34:58Z","title_canon_sha256":"d6e2f2720899dc74d8bcad0d8b6b10e48bc28fbf6a57978a86a9e49bfd7b1917"},"schema_version":"1.0","source":{"id":"1907.07073","kind":"arxiv","version":1}},"canonical_sha256":"e76fd47c6456915fc395d4916470c7c883f9e2636e07917aa315bb1ce10af381","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e76fd47c6456915fc395d4916470c7c883f9e2636e07917aa315bb1ce10af381","first_computed_at":"2026-07-05T00:05:12.458613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:05:12.458613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y3cysnAk9tEeaitOm4Cg9Lkqiz/trZ22nm8GSfKSTnjmkyJLaYRmb8WiccQQIV+MxMz7cmFn/8nFoarPVFdUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:05:12.459218Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.07073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5489c27c1a74acb6930ca6a39e92046636f678b32b7531cebc21bec24a5904f","sha256:215d1edfe8d88dcd501c7ee06d4753784327ce96a1c30437b961c42db285ae5b"],"state_sha256":"ec9f60beaaa0e371ba9a6ecd41652b25d93b53e575fc082a1f45405708e8fc51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCJgzwiAXZWgxwasJZf0RkqJxZIgKTSoFxpnViMU+1OoJoKq9a7vZK7Rz9I+GRDccSw357k9a87o0oP5AL1rAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:06:40.243377Z","bundle_sha256":"3cb6e755a3e15f2db26595b9da1d43c63e101d9be182c9b00ca495ded2a760a9"}}