{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GZDI7AT622U36RNE4KYZHGIFGP","short_pith_number":"pith:GZDI7AT6","schema_version":"1.0","canonical_sha256":"36468f827ed6a9bf45a4e2b193990533c6c5d27dd0209213bc5e249668873ced","source":{"kind":"arxiv","id":"2507.08153","version":1},"attestation_state":"computed","paper":{"title":"ALCo-FM: Adaptive Long-Context Foundation Model for Accident Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Rajiv Ramnath","submitted_at":"2025-07-10T20:22:26Z","abstract_excerpt":"Traffic accidents are rare, yet high-impact events that require long-context multimodal reasoning for accurate risk forecasting. In this paper, we introduce ALCo-FM, a unified adaptive long-context foundation model that computes a volatility pre-score to dynamically select context windows for input data and encodes and fuses these multimodal data via shallow cross attention. Following a local GAT layer and a BigBird-style sparse global transformer over H3 hexagonal grids, coupled with Monte Carlo dropout for confidence, the model yields superior, well-calibrated predictions. Trained on data fr"},"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":"2507.08153","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T20:22:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e5e996069183db261ff4f3dce83ac01805cc9b491f053be1b2f7dabae25d7d4","abstract_canon_sha256":"58c550f47fc2ac10290420db473832375c9732f5f298efeaf2e29152703c08e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:18.036810Z","signature_b64":"/WQLSST3/uJ4Srllq5Dni9jukQCGcOZuwkxLAtF627ldhxZcomKGnu1PXPXb7LQ5kQFKgphHxIHaaiMMYM8IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36468f827ed6a9bf45a4e2b193990533c6c5d27dd0209213bc5e249668873ced","last_reissued_at":"2026-07-05T11:35:18.036288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:18.036288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALCo-FM: Adaptive Long-Context Foundation Model for Accident Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Rajiv Ramnath","submitted_at":"2025-07-10T20:22:26Z","abstract_excerpt":"Traffic accidents are rare, yet high-impact events that require long-context multimodal reasoning for accurate risk forecasting. In this paper, we introduce ALCo-FM, a unified adaptive long-context foundation model that computes a volatility pre-score to dynamically select context windows for input data and encodes and fuses these multimodal data via shallow cross attention. Following a local GAT layer and a BigBird-style sparse global transformer over H3 hexagonal grids, coupled with Monte Carlo dropout for confidence, the model yields superior, well-calibrated predictions. Trained on data fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08153","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/2507.08153/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":"2507.08153","created_at":"2026-07-05T11:35:18.036364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08153v1","created_at":"2026-07-05T11:35:18.036364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08153","created_at":"2026-07-05T11:35:18.036364+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZDI7AT622U3","created_at":"2026-07-05T11:35:18.036364+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZDI7AT622U36RNE","created_at":"2026-07-05T11:35:18.036364+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZDI7AT6","created_at":"2026-07-05T11:35:18.036364+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/GZDI7AT622U36RNE4KYZHGIFGP","json":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP.json","graph_json":"https://pith.science/api/pith-number/GZDI7AT622U36RNE4KYZHGIFGP/graph.json","events_json":"https://pith.science/api/pith-number/GZDI7AT622U36RNE4KYZHGIFGP/events.json","paper":"https://pith.science/paper/GZDI7AT6"},"agent_actions":{"view_html":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP","download_json":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP.json","view_paper":"https://pith.science/paper/GZDI7AT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08153&json=true","fetch_graph":"https://pith.science/api/pith-number/GZDI7AT622U36RNE4KYZHGIFGP/graph.json","fetch_events":"https://pith.science/api/pith-number/GZDI7AT622U36RNE4KYZHGIFGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP/action/storage_attestation","attest_author":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP/action/author_attestation","sign_citation":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP/action/citation_signature","submit_replication":"https://pith.science/pith/GZDI7AT622U36RNE4KYZHGIFGP/action/replication_record"}},"created_at":"2026-07-05T11:35:18.036364+00:00","updated_at":"2026-07-05T11:35:18.036364+00:00"}