{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DNEV45Z2WNKWCVOEQ2UEHXCVR4","short_pith_number":"pith:DNEV45Z2","schema_version":"1.0","canonical_sha256":"1b495e773ab3556155c486a843dc558f32b079cd2330cf88aa60d012cc2ad5f5","source":{"kind":"arxiv","id":"2511.17813","version":3},"attestation_state":"computed","paper":{"title":"Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Scott Merrill, Shashank Srivastava","submitted_at":"2025-11-21T22:07:33Z","abstract_excerpt":"LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior. ASR transcripts typically use anonymous labels such as $Speaker\\_1$, preventing models from learning stable participant behavior across meetings. We present a reproducible pipeline that converts public Zoom recordings into speaker-attributed transcripts enriched with persona profiles, topics, and pragmatic \"action tags\" such as $[propose\\_motion]$. Using this pipeline, we release three public datasets of governm"},"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":"2511.17813","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-21T22:07:33Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"title_canon_sha256":"a85851fd64c4b9c0e496994de2c3ed38a4328e123b2319aacd9a4cf0243653fb","abstract_canon_sha256":"2e49f7be022a0fb017aff39d03ce3e066fcb674c0786d47ca5d4e0a75b5de6ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:04.586004Z","signature_b64":"TS4D7Lh0svneQjOarHhkAClPw8F6CSwjaBrGTmEOdxYsGbKOQHlAKEDja81AXaDqJB5CB4ACqvItMZPmF+ijAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b495e773ab3556155c486a843dc558f32b079cd2330cf88aa60d012cc2ad5f5","last_reissued_at":"2026-07-13T00:17:04.583823Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:04.583823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Scott Merrill, Shashank Srivastava","submitted_at":"2025-11-21T22:07:33Z","abstract_excerpt":"LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior. ASR transcripts typically use anonymous labels such as $Speaker\\_1$, preventing models from learning stable participant behavior across meetings. We present a reproducible pipeline that converts public Zoom recordings into speaker-attributed transcripts enriched with persona profiles, topics, and pragmatic \"action tags\" such as $[propose\\_motion]$. Using this pipeline, we release three public datasets of governm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.17813","kind":"arxiv","version":3},"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/2511.17813/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":"2511.17813","created_at":"2026-07-13T00:17:04.584982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.17813v3","created_at":"2026-07-13T00:17:04.584982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.17813","created_at":"2026-07-13T00:17:04.584982+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNEV45Z2WNKW","created_at":"2026-07-13T00:17:04.584982+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNEV45Z2WNKWCVOE","created_at":"2026-07-13T00:17:04.584982+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNEV45Z2","created_at":"2026-07-13T00:17:04.584982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.09198","citing_title":"MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2601.10102","citing_title":"When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4","json":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4.json","graph_json":"https://pith.science/api/pith-number/DNEV45Z2WNKWCVOEQ2UEHXCVR4/graph.json","events_json":"https://pith.science/api/pith-number/DNEV45Z2WNKWCVOEQ2UEHXCVR4/events.json","paper":"https://pith.science/paper/DNEV45Z2"},"agent_actions":{"view_html":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4","download_json":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4.json","view_paper":"https://pith.science/paper/DNEV45Z2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.17813&json=true","fetch_graph":"https://pith.science/api/pith-number/DNEV45Z2WNKWCVOEQ2UEHXCVR4/graph.json","fetch_events":"https://pith.science/api/pith-number/DNEV45Z2WNKWCVOEQ2UEHXCVR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4/action/storage_attestation","attest_author":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4/action/author_attestation","sign_citation":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4/action/citation_signature","submit_replication":"https://pith.science/pith/DNEV45Z2WNKWCVOEQ2UEHXCVR4/action/replication_record"}},"created_at":"2026-07-13T00:17:04.584982+00:00","updated_at":"2026-07-13T00:17:04.584982+00:00"}