{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FIQXW6YCVRGVYUS4WY5XVGPFR3","short_pith_number":"pith:FIQXW6YC","schema_version":"1.0","canonical_sha256":"2a217b7b02ac4d5c525cb63b7a99e58ef61d50b6d8a081722e46f6a472ef7742","source":{"kind":"arxiv","id":"2403.08890","version":1},"attestation_state":"computed","paper":{"title":"From \"um\" to \"yeah\": Producing, predicting, and regulating information flow in human conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","q-bio.NC"],"primary_cat":"cs.CL","authors_text":"Claire Augusta Bergey, Simon DeDeo","submitted_at":"2024-03-13T18:20:24Z","abstract_excerpt":"Conversation demands attention. Speakers must call words to mind, listeners must make sense of them, and both together must negotiate this flow of information, all in fractions of a second. We used large language models to study how this works in a large-scale dataset of English-language conversation, the CANDOR corpus. We provide a new estimate of the information density of unstructured conversation, of approximately 13 bits/second, and find significant effects associated with the cognitive load of both retrieving, and presenting, that information. We also reveal a role for backchannels -- th"},"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":"2403.08890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T18:20:24Z","cross_cats_sorted":["cs.IT","math.IT","q-bio.NC"],"title_canon_sha256":"787144972af17990e9fba91391c2dba58345b1e5e0224da6168c5087aa787fac","abstract_canon_sha256":"3ffbacf717ad60aa61191b14ff9b45e0c4f01b9ee5259f89516117eb9b5dd228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:48.775565Z","signature_b64":"4wJWt+whDRaJbGL/jOwAnmYdQHPlxBPqCBsfntJIl7oS7nOUY5CkrKNPvZFPRMB/LgC35rACB2k0emNV0noECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a217b7b02ac4d5c525cb63b7a99e58ef61d50b6d8a081722e46f6a472ef7742","last_reissued_at":"2026-07-05T07:55:48.775080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:48.775080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From \"um\" to \"yeah\": Producing, predicting, and regulating information flow in human conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","q-bio.NC"],"primary_cat":"cs.CL","authors_text":"Claire Augusta Bergey, Simon DeDeo","submitted_at":"2024-03-13T18:20:24Z","abstract_excerpt":"Conversation demands attention. Speakers must call words to mind, listeners must make sense of them, and both together must negotiate this flow of information, all in fractions of a second. We used large language models to study how this works in a large-scale dataset of English-language conversation, the CANDOR corpus. We provide a new estimate of the information density of unstructured conversation, of approximately 13 bits/second, and find significant effects associated with the cognitive load of both retrieving, and presenting, that information. We also reveal a role for backchannels -- th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08890","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/2403.08890/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":"2403.08890","created_at":"2026-07-05T07:55:48.775137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08890v1","created_at":"2026-07-05T07:55:48.775137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08890","created_at":"2026-07-05T07:55:48.775137+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIQXW6YCVRGV","created_at":"2026-07-05T07:55:48.775137+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIQXW6YCVRGVYUS4","created_at":"2026-07-05T07:55:48.775137+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIQXW6YC","created_at":"2026-07-05T07:55:48.775137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05330","citing_title":"A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20237","citing_title":"Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23676","citing_title":"Directional Alignment and Narrative Agency in Human-LLM Co-Writing","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16767","citing_title":"When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3","json":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3.json","graph_json":"https://pith.science/api/pith-number/FIQXW6YCVRGVYUS4WY5XVGPFR3/graph.json","events_json":"https://pith.science/api/pith-number/FIQXW6YCVRGVYUS4WY5XVGPFR3/events.json","paper":"https://pith.science/paper/FIQXW6YC"},"agent_actions":{"view_html":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3","download_json":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3.json","view_paper":"https://pith.science/paper/FIQXW6YC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08890&json=true","fetch_graph":"https://pith.science/api/pith-number/FIQXW6YCVRGVYUS4WY5XVGPFR3/graph.json","fetch_events":"https://pith.science/api/pith-number/FIQXW6YCVRGVYUS4WY5XVGPFR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3/action/storage_attestation","attest_author":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3/action/author_attestation","sign_citation":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3/action/citation_signature","submit_replication":"https://pith.science/pith/FIQXW6YCVRGVYUS4WY5XVGPFR3/action/replication_record"}},"created_at":"2026-07-05T07:55:48.775137+00:00","updated_at":"2026-07-05T07:55:48.775137+00:00"}