{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VCONX27AEGRIV5IE3B2V6O7YOH","short_pith_number":"pith:VCONX27A","schema_version":"1.0","canonical_sha256":"a89cdbebe021a28af504d8755f3bf871c2746292fe9e537b590bff9abb7a28ee","source":{"kind":"arxiv","id":"2301.03567","version":1},"attestation_state":"computed","paper":{"title":"Safer Together: Machine Learning Models Trained on Shared Accident Datasets Predict Construction Injuries Better than Company-Specific Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine J.-P. Tixier, Matthew R. Hallowell","submitted_at":"2023-01-09T18:37:40Z","abstract_excerpt":"In this study, we capitalized on a collective dataset repository of 57k accidents from 9 companies belonging to 3 domains and tested whether models trained on multiple datasets (generic models) predicted safety outcomes better than the company-specific models. We experimented with full generic models (trained on all data), per-domain generic models (construction, electric T&D, oil & gas), and with ensembles of generic and specific models. Results are very positive, with generic models outperforming the company-specific models in most cases while also generating finer-grained, hence more useful"},"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":"2301.03567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-09T18:37:40Z","cross_cats_sorted":[],"title_canon_sha256":"4ef93ca593bda4aa5fd7cae809bef6253f04f1a13477b49e476d9ef04b3b30ad","abstract_canon_sha256":"fa092edf0d96e786d00c395d06f72299b436d06a0d701ce74d20e54ac637266c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:37.028170Z","signature_b64":"DiIOQ+YH6mS1uOQSxsCO+P4C9Arzizygb6w47phdjii0P4fQ6R6/GZnMWWOym4k1WIyFD/dSVGUUrH9vxPvEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a89cdbebe021a28af504d8755f3bf871c2746292fe9e537b590bff9abb7a28ee","last_reissued_at":"2026-07-05T05:31:37.027825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:37.027825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safer Together: Machine Learning Models Trained on Shared Accident Datasets Predict Construction Injuries Better than Company-Specific Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine J.-P. Tixier, Matthew R. Hallowell","submitted_at":"2023-01-09T18:37:40Z","abstract_excerpt":"In this study, we capitalized on a collective dataset repository of 57k accidents from 9 companies belonging to 3 domains and tested whether models trained on multiple datasets (generic models) predicted safety outcomes better than the company-specific models. We experimented with full generic models (trained on all data), per-domain generic models (construction, electric T&D, oil & gas), and with ensembles of generic and specific models. Results are very positive, with generic models outperforming the company-specific models in most cases while also generating finer-grained, hence more useful"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03567","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/2301.03567/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":"2301.03567","created_at":"2026-07-05T05:31:37.027882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.03567v1","created_at":"2026-07-05T05:31:37.027882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03567","created_at":"2026-07-05T05:31:37.027882+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCONX27AEGRI","created_at":"2026-07-05T05:31:37.027882+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCONX27AEGRIV5IE","created_at":"2026-07-05T05:31:37.027882+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCONX27A","created_at":"2026-07-05T05:31:37.027882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09203","citing_title":"Building Safer Sites: A Large-Scale Multi-Level Dataset for Construction Safety Research","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH","json":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH.json","graph_json":"https://pith.science/api/pith-number/VCONX27AEGRIV5IE3B2V6O7YOH/graph.json","events_json":"https://pith.science/api/pith-number/VCONX27AEGRIV5IE3B2V6O7YOH/events.json","paper":"https://pith.science/paper/VCONX27A"},"agent_actions":{"view_html":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH","download_json":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH.json","view_paper":"https://pith.science/paper/VCONX27A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.03567&json=true","fetch_graph":"https://pith.science/api/pith-number/VCONX27AEGRIV5IE3B2V6O7YOH/graph.json","fetch_events":"https://pith.science/api/pith-number/VCONX27AEGRIV5IE3B2V6O7YOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH/action/storage_attestation","attest_author":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH/action/author_attestation","sign_citation":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH/action/citation_signature","submit_replication":"https://pith.science/pith/VCONX27AEGRIV5IE3B2V6O7YOH/action/replication_record"}},"created_at":"2026-07-05T05:31:37.027882+00:00","updated_at":"2026-07-05T05:31:37.027882+00:00"}