{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S3RH3ESHZBK5GCHSWXGMGS5HOJ","short_pith_number":"pith:S3RH3ESH","schema_version":"1.0","canonical_sha256":"96e27d9247c855d308f2b5ccc34ba772553c83e1026b00a77fa1d04a8607d822","source":{"kind":"arxiv","id":"2507.04893","version":1},"attestation_state":"computed","paper":{"title":"MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jiashu Zhang, Kaleem Ullah Qasim","submitted_at":"2025-07-07T11:27:49Z","abstract_excerpt":"Accident severity prediction plays a critical role in transportation safety systems but is a persistently difficult task due to incomplete data, strong feature dependencies, and severe class imbalance in which rare but high-severity cases are underrepresented and hard to detect. Existing methods often rely on monolithic models or black box prompting, which struggle to scale in noisy, real-world settings and offer limited interpretability. To address these challenges, we propose MARBLE a multiagent rule based LLM engine that decomposes the severity prediction task across a team of specialized r"},"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":"2507.04893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T11:27:49Z","cross_cats_sorted":["cs.CL","cs.MA"],"title_canon_sha256":"b8bd2f8faa1d9acd8e2b62a2c7f7a1c58715cb1717468c9dc9a68df6bf5eed63","abstract_canon_sha256":"b5571e58a2c9607e56ca50b06e12e095302fc070bb3b780a6764e683f553a2c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:55.978073Z","signature_b64":"ost/mYFAz9AFZprjnNUHoyAixyasOPtO9Xh7g7RsK4ObyuspwIoswm6lWLYgWLoytlCuNk2VFYS2EDLwQ2UpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96e27d9247c855d308f2b5ccc34ba772553c83e1026b00a77fa1d04a8607d822","last_reissued_at":"2026-07-05T11:32:55.977523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:55.977523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jiashu Zhang, Kaleem Ullah Qasim","submitted_at":"2025-07-07T11:27:49Z","abstract_excerpt":"Accident severity prediction plays a critical role in transportation safety systems but is a persistently difficult task due to incomplete data, strong feature dependencies, and severe class imbalance in which rare but high-severity cases are underrepresented and hard to detect. Existing methods often rely on monolithic models or black box prompting, which struggle to scale in noisy, real-world settings and offer limited interpretability. To address these challenges, we propose MARBLE a multiagent rule based LLM engine that decomposes the severity prediction task across a team of specialized r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04893","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/2507.04893/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":"2507.04893","created_at":"2026-07-05T11:32:55.977602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04893v1","created_at":"2026-07-05T11:32:55.977602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04893","created_at":"2026-07-05T11:32:55.977602+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3RH3ESHZBK5","created_at":"2026-07-05T11:32:55.977602+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3RH3ESHZBK5GCHS","created_at":"2026-07-05T11:32:55.977602+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3RH3ESH","created_at":"2026-07-05T11:32:55.977602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ","json":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ.json","graph_json":"https://pith.science/api/pith-number/S3RH3ESHZBK5GCHSWXGMGS5HOJ/graph.json","events_json":"https://pith.science/api/pith-number/S3RH3ESHZBK5GCHSWXGMGS5HOJ/events.json","paper":"https://pith.science/paper/S3RH3ESH"},"agent_actions":{"view_html":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ","download_json":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ.json","view_paper":"https://pith.science/paper/S3RH3ESH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04893&json=true","fetch_graph":"https://pith.science/api/pith-number/S3RH3ESHZBK5GCHSWXGMGS5HOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/S3RH3ESHZBK5GCHSWXGMGS5HOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ/action/storage_attestation","attest_author":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ/action/author_attestation","sign_citation":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ/action/citation_signature","submit_replication":"https://pith.science/pith/S3RH3ESHZBK5GCHSWXGMGS5HOJ/action/replication_record"}},"created_at":"2026-07-05T11:32:55.977602+00:00","updated_at":"2026-07-05T11:32:55.977602+00:00"}