{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IFVWVXSLHEW4T76DRS4WP4RO2P","short_pith_number":"pith:IFVWVXSL","schema_version":"1.0","canonical_sha256":"416b6ade4b392dc9ffc38cb967f22ed3c854e10552a7f005bde2f4add0805376","source":{"kind":"arxiv","id":"2407.12812","version":1},"attestation_state":"computed","paper":{"title":"Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Joshua L. Proctor, Katherine A. Rosenfeld, Kevin A. McCarthy, Maike Sonnewald, Sonia J. Jindal","submitted_at":"2024-06-27T05:03:03Z","abstract_excerpt":"We introduce a framework for the use of large language models (LLMs) in Building Understandable Messaging for Policy and Evidence Review (BUMPER). LLMs are proving capable of providing interfaces for understanding and synthesizing large databases of diverse media. This presents an exciting opportunity to supercharge the translation of scientific evidence into policy and action, thereby improving livelihoods around the world. However, these models also pose challenges related to access, trust-worthiness, and accountability. The BUMPER framework is built atop a scientific knowledge base (e.g., d"},"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":"2407.12812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T05:03:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c97be3c3dcf92d7fcd3397e275e90b5945f5da69180479750eb92f15fbfc246c","abstract_canon_sha256":"1f717e348f67847f934e6c536e04f811945854e9ded153d6673ba4c586d518c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:11.868282Z","signature_b64":"Q+LUcKYzryTkfZMdm5J+eK+eIyC55EtmCc7WQ2t7CLitEL3VlKVUJuQhxJRJgpKFMp0F6d+4kj+p6p/OyOSIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"416b6ade4b392dc9ffc38cb967f22ed3c854e10552a7f005bde2f4add0805376","last_reissued_at":"2026-07-05T08:45:11.867934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:11.867934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Joshua L. Proctor, Katherine A. Rosenfeld, Kevin A. McCarthy, Maike Sonnewald, Sonia J. Jindal","submitted_at":"2024-06-27T05:03:03Z","abstract_excerpt":"We introduce a framework for the use of large language models (LLMs) in Building Understandable Messaging for Policy and Evidence Review (BUMPER). LLMs are proving capable of providing interfaces for understanding and synthesizing large databases of diverse media. This presents an exciting opportunity to supercharge the translation of scientific evidence into policy and action, thereby improving livelihoods around the world. However, these models also pose challenges related to access, trust-worthiness, and accountability. The BUMPER framework is built atop a scientific knowledge base (e.g., d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12812","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/2407.12812/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":"2407.12812","created_at":"2026-07-05T08:45:11.867989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12812v1","created_at":"2026-07-05T08:45:11.867989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12812","created_at":"2026-07-05T08:45:11.867989+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFVWVXSLHEW4","created_at":"2026-07-05T08:45:11.867989+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFVWVXSLHEW4T76D","created_at":"2026-07-05T08:45:11.867989+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFVWVXSL","created_at":"2026-07-05T08:45:11.867989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15828","citing_title":"Investigating the Use of LLMs for Evidence Briefings Generation in Software Engineering","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P","json":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P.json","graph_json":"https://pith.science/api/pith-number/IFVWVXSLHEW4T76DRS4WP4RO2P/graph.json","events_json":"https://pith.science/api/pith-number/IFVWVXSLHEW4T76DRS4WP4RO2P/events.json","paper":"https://pith.science/paper/IFVWVXSL"},"agent_actions":{"view_html":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P","download_json":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P.json","view_paper":"https://pith.science/paper/IFVWVXSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12812&json=true","fetch_graph":"https://pith.science/api/pith-number/IFVWVXSLHEW4T76DRS4WP4RO2P/graph.json","fetch_events":"https://pith.science/api/pith-number/IFVWVXSLHEW4T76DRS4WP4RO2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P/action/storage_attestation","attest_author":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P/action/author_attestation","sign_citation":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P/action/citation_signature","submit_replication":"https://pith.science/pith/IFVWVXSLHEW4T76DRS4WP4RO2P/action/replication_record"}},"created_at":"2026-07-05T08:45:11.867989+00:00","updated_at":"2026-07-05T08:45:11.867989+00:00"}