{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4OENWLUJYQQRU4XEL6GY353WAW","short_pith_number":"pith:4OENWLUJ","schema_version":"1.0","canonical_sha256":"e388db2e89c4211a72e45f8d8df77605a5a52cf5dda7621e6f345a25fd2ebe25","source":{"kind":"arxiv","id":"2505.14964","version":1},"attestation_state":"computed","paper":{"title":"The Achilles Heel of AI: Fundamentals of Risk-Aware Training Data for High-Consequence Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dave Cook, Tim Klawa","submitted_at":"2025-05-20T22:57:35Z","abstract_excerpt":"AI systems in high-consequence domains such as defense, intelligence, and disaster response must detect rare, high-impact events while operating under tight resource constraints. Traditional annotation strategies that prioritize label volume over informational value introduce redundancy and noise, limiting model generalization. This paper introduces smart-sizing, a training data strategy that emphasizes label diversity, model-guided selection, and marginal utility-based stopping. We implement this through Adaptive Label Optimization (ALO), combining pre-labeling triage, annotator disagreement "},"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":"2505.14964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T22:57:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f191d5b0663f3880c0b6bd8cbb5b195db538292e65cccf61a83f41ae02ce59d","abstract_canon_sha256":"669e271905922b47a526c2cc0b90a34eecda20c51a267dfbcf3eb17768fc44ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:38.433572Z","signature_b64":"xq9RbfN69TT2rInHqEtbrOqSslD5MRCWimXrSJkProcWVLq8SqyirTrWS1ZpERIk1t7Wr/6JAnB1nZCk0xH5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e388db2e89c4211a72e45f8d8df77605a5a52cf5dda7621e6f345a25fd2ebe25","last_reissued_at":"2026-07-05T11:06:38.433028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:38.433028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Achilles Heel of AI: Fundamentals of Risk-Aware Training Data for High-Consequence Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dave Cook, Tim Klawa","submitted_at":"2025-05-20T22:57:35Z","abstract_excerpt":"AI systems in high-consequence domains such as defense, intelligence, and disaster response must detect rare, high-impact events while operating under tight resource constraints. Traditional annotation strategies that prioritize label volume over informational value introduce redundancy and noise, limiting model generalization. This paper introduces smart-sizing, a training data strategy that emphasizes label diversity, model-guided selection, and marginal utility-based stopping. We implement this through Adaptive Label Optimization (ALO), combining pre-labeling triage, annotator disagreement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14964","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/2505.14964/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":"2505.14964","created_at":"2026-07-05T11:06:38.433084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14964v1","created_at":"2026-07-05T11:06:38.433084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14964","created_at":"2026-07-05T11:06:38.433084+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OENWLUJYQQR","created_at":"2026-07-05T11:06:38.433084+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OENWLUJYQQRU4XE","created_at":"2026-07-05T11:06:38.433084+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OENWLUJ","created_at":"2026-07-05T11:06:38.433084+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/4OENWLUJYQQRU4XEL6GY353WAW","json":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW.json","graph_json":"https://pith.science/api/pith-number/4OENWLUJYQQRU4XEL6GY353WAW/graph.json","events_json":"https://pith.science/api/pith-number/4OENWLUJYQQRU4XEL6GY353WAW/events.json","paper":"https://pith.science/paper/4OENWLUJ"},"agent_actions":{"view_html":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW","download_json":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW.json","view_paper":"https://pith.science/paper/4OENWLUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14964&json=true","fetch_graph":"https://pith.science/api/pith-number/4OENWLUJYQQRU4XEL6GY353WAW/graph.json","fetch_events":"https://pith.science/api/pith-number/4OENWLUJYQQRU4XEL6GY353WAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW/action/storage_attestation","attest_author":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW/action/author_attestation","sign_citation":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW/action/citation_signature","submit_replication":"https://pith.science/pith/4OENWLUJYQQRU4XEL6GY353WAW/action/replication_record"}},"created_at":"2026-07-05T11:06:38.433084+00:00","updated_at":"2026-07-05T11:06:38.433084+00:00"}