{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OOCUTVSWEUDS2SU2XRGI7NDKN6","short_pith_number":"pith:OOCUTVSW","canonical_record":{"source":{"id":"2507.03066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a33df782765294a85888b0ead29fed83344e7a4863e0ea845fa90741c49397f2","abstract_canon_sha256":"08a4a9d2f36acac9636f18dd5c7c70ee3a947106eeb9ea2b4c9326828baa5318"},"schema_version":"1.0"},"canonical_sha256":"738549d65625072d4a9abc4c8fb46a6f805f514f84fe7639adb5669b1272f726","source":{"kind":"arxiv","id":"2507.03066","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03066","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03066v1","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03066","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"OOCUTVSWEUDS","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"OOCUTVSWEUDS2SU2","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"OOCUTVSW","created_at":"2026-07-05T11:31:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OOCUTVSWEUDS2SU2XRGI7NDKN6","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a33df782765294a85888b0ead29fed83344e7a4863e0ea845fa90741c49397f2","abstract_canon_sha256":"08a4a9d2f36acac9636f18dd5c7c70ee3a947106eeb9ea2b4c9326828baa5318"},"schema_version":"1.0"},"canonical_sha256":"738549d65625072d4a9abc4c8fb46a6f805f514f84fe7639adb5669b1272f726","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:52.004033Z","signature_b64":"oKDlT4iJSj0VakmzZSNXZQKJ896mcC8iJWNEnx+BZJTmcuihm40yf6UMWU27MVl46UGpHtooYt17Z+Zc6IeuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"738549d65625072d4a9abc4c8fb46a6f805f514f84fe7639adb5669b1272f726","last_reissued_at":"2026-07-05T11:31:52.003409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:52.003409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03066","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":"2026-07-05T11:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQ2o8gujD964N8HtJ/BzqZ7hg78EQyZjeiA24lZ/PDhAvJm2jEjZCFmYJSIa60A43ii0BshNmkHWhxSBQnKdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:38:05.033686Z"},"content_sha256":"b7bde8b1df02d938dbbefe807554d50f5ad535a852fe7e1f0883a978b209a6a6","schema_version":"1.0","event_id":"sha256:b7bde8b1df02d938dbbefe807554d50f5ad535a852fe7e1f0883a978b209a6a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OOCUTVSWEUDS2SU2XRGI7NDKN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identification of Potentially Misclassified Crash Narratives using Machine Learning (ML) and Deep Learning (DL)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ibne Farabi Shihab, Jonathan Wood, Sudesh Bhagat","submitted_at":"2025-07-03T17:26:27Z","abstract_excerpt":"This research investigates the efficacy of machine learning (ML) and deep learning (DL) methods in detecting misclassified intersection-related crashes in police-reported narratives. Using 2019 crash data from the Iowa Department of Transportation, we implemented and compared a comprehensive set of models, including Support Vector Machine (SVM), XGBoost, BERT Sentence Embeddings, BERT Word Embeddings, and Albert Model. Model performance was systematically validated against expert reviews of potentially misclassified narratives, providing a rigorous assessment of classification accuracy. Result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03066","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/2507.03066/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":"2026-07-05T11:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3IGD/cl99JLqOCwfjaSCrbREppQRTsJKwcVQUZyPOngCAVd/BpDTc2dAdxPaFzxLObtIRa7iYWHoOSfXxfnBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:38:05.034063Z"},"content_sha256":"8bcbd8e79059986be9b11600594a68a227620f2f020d6cb5c672f54aef794071","schema_version":"1.0","event_id":"sha256:8bcbd8e79059986be9b11600594a68a227620f2f020d6cb5c672f54aef794071"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOCUTVSWEUDS2SU2XRGI7NDKN6/bundle.json","state_url":"https://pith.science/pith/OOCUTVSWEUDS2SU2XRGI7NDKN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOCUTVSWEUDS2SU2XRGI7NDKN6/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":"2026-07-07T12:38:05Z","links":{"resolver":"https://pith.science/pith/OOCUTVSWEUDS2SU2XRGI7NDKN6","bundle":"https://pith.science/pith/OOCUTVSWEUDS2SU2XRGI7NDKN6/bundle.json","state":"https://pith.science/pith/OOCUTVSWEUDS2SU2XRGI7NDKN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOCUTVSWEUDS2SU2XRGI7NDKN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OOCUTVSWEUDS2SU2XRGI7NDKN6","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":"08a4a9d2f36acac9636f18dd5c7c70ee3a947106eeb9ea2b4c9326828baa5318","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:26:27Z","title_canon_sha256":"a33df782765294a85888b0ead29fed83344e7a4863e0ea845fa90741c49397f2"},"schema_version":"1.0","source":{"id":"2507.03066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03066","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03066v1","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03066","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"OOCUTVSWEUDS","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"OOCUTVSWEUDS2SU2","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"OOCUTVSW","created_at":"2026-07-05T11:31:52Z"}],"graph_snapshots":[{"event_id":"sha256:8bcbd8e79059986be9b11600594a68a227620f2f020d6cb5c672f54aef794071","target":"graph","created_at":"2026-07-05T11:31:52Z","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/2507.03066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This research investigates the efficacy of machine learning (ML) and deep learning (DL) methods in detecting misclassified intersection-related crashes in police-reported narratives. Using 2019 crash data from the Iowa Department of Transportation, we implemented and compared a comprehensive set of models, including Support Vector Machine (SVM), XGBoost, BERT Sentence Embeddings, BERT Word Embeddings, and Albert Model. Model performance was systematically validated against expert reviews of potentially misclassified narratives, providing a rigorous assessment of classification accuracy. Result","authors_text":"Ibne Farabi Shihab, Jonathan Wood, Sudesh Bhagat","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:26:27Z","title":"Identification of Potentially Misclassified Crash Narratives using Machine Learning (ML) and Deep Learning (DL)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03066","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:b7bde8b1df02d938dbbefe807554d50f5ad535a852fe7e1f0883a978b209a6a6","target":"record","created_at":"2026-07-05T11:31:52Z","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":"08a4a9d2f36acac9636f18dd5c7c70ee3a947106eeb9ea2b4c9326828baa5318","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:26:27Z","title_canon_sha256":"a33df782765294a85888b0ead29fed83344e7a4863e0ea845fa90741c49397f2"},"schema_version":"1.0","source":{"id":"2507.03066","kind":"arxiv","version":1}},"canonical_sha256":"738549d65625072d4a9abc4c8fb46a6f805f514f84fe7639adb5669b1272f726","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"738549d65625072d4a9abc4c8fb46a6f805f514f84fe7639adb5669b1272f726","first_computed_at":"2026-07-05T11:31:52.003409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:52.003409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oKDlT4iJSj0VakmzZSNXZQKJ896mcC8iJWNEnx+BZJTmcuihm40yf6UMWU27MVl46UGpHtooYt17Z+Zc6IeuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:52.004033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7bde8b1df02d938dbbefe807554d50f5ad535a852fe7e1f0883a978b209a6a6","sha256:8bcbd8e79059986be9b11600594a68a227620f2f020d6cb5c672f54aef794071"],"state_sha256":"1130ef79c37715838f3034086a87eaffa9e16890d973bf57c754af2bc9eb6dd0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MM06zqsspd0ee4G00pDal0Bxtcmn7RstTn0YXpnV6tYhLPZVgV1+1xQqAIfoSVcXSSittgyM/dMZXUC0QoO2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:38:05.036152Z","bundle_sha256":"4add52dd2002a765b3fddeaf3ca43c2fe68786e57fe7dc81746c3e205f2dba7e"}}