{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZNF3S7HMIWQ5QIO5M7JETKFZQZ","short_pith_number":"pith:ZNF3S7HM","schema_version":"1.0","canonical_sha256":"cb4bb97cec45a1d821dd67d249a8b9865fb669cb43e394fa7eb6f73940e5b5cc","source":{"kind":"arxiv","id":"2508.09853","version":2},"attestation_state":"computed","paper":{"title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Chris Painter, Jide Alaga, Luca Righetti, Rishi Bommasani, Samira Nedungadi, Seth Donoughe, Tegan McCaslin, Tom Reed","submitted_at":"2025-08-13T14:36:36Z","abstract_excerpt":"Evaluations of dangerous AI capabilities are important for managing catastrophic risks. Public transparency into these evaluations - including what they test, how they are conducted, and how their results inform decisions - is crucial for building trust in AI development. We propose STREAM (A Standard for Transparently Reporting Evaluations in AI Model Reports), a standard to improve how model reports disclose evaluation results, initially focusing on chemical and biological (ChemBio) benchmarks. Developed in consultation with 23 experts across government, civil society, academia, and frontier"},"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":"2508.09853","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-08-13T14:36:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d1293469027532e8be950820fa73bd49cdc7dde333aaecd47da1d750c8ef6ffd","abstract_canon_sha256":"9c09f61d495452227e0f4e956ded67fc93ac5b9f05384582dc2548b504a651f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:17.016633Z","signature_b64":"Qmq8lKB+xC/JLHX+j3WOhynJ9ktvtOlCdoO6b1FL2dYOXdciXAW8ttmvdkSTO+/fQMJgooAlkd9sK0r4tY6wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb4bb97cec45a1d821dd67d249a8b9865fb669cb43e394fa7eb6f73940e5b5cc","last_reissued_at":"2026-07-05T12:04:17.016048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:17.016048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Chris Painter, Jide Alaga, Luca Righetti, Rishi Bommasani, Samira Nedungadi, Seth Donoughe, Tegan McCaslin, Tom Reed","submitted_at":"2025-08-13T14:36:36Z","abstract_excerpt":"Evaluations of dangerous AI capabilities are important for managing catastrophic risks. Public transparency into these evaluations - including what they test, how they are conducted, and how their results inform decisions - is crucial for building trust in AI development. We propose STREAM (A Standard for Transparently Reporting Evaluations in AI Model Reports), a standard to improve how model reports disclose evaluation results, initially focusing on chemical and biological (ChemBio) benchmarks. Developed in consultation with 23 experts across government, civil society, academia, and frontier"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09853","kind":"arxiv","version":2},"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/2508.09853/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":"2508.09853","created_at":"2026-07-05T12:04:17.016124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09853v2","created_at":"2026-07-05T12:04:17.016124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09853","created_at":"2026-07-05T12:04:17.016124+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNF3S7HMIWQ5","created_at":"2026-07-05T12:04:17.016124+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNF3S7HMIWQ5QIO5","created_at":"2026-07-05T12:04:17.016124+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNF3S7HM","created_at":"2026-07-05T12:04:17.016124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09809","citing_title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08192","citing_title":"NeurIPS Should Require Reproducibility Standards for Frontier AI Safety Claims","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24966","citing_title":"Risk Reporting for Developers' Internal AI Model Use","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ","json":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ.json","graph_json":"https://pith.science/api/pith-number/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/graph.json","events_json":"https://pith.science/api/pith-number/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/events.json","paper":"https://pith.science/paper/ZNF3S7HM"},"agent_actions":{"view_html":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ","download_json":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ.json","view_paper":"https://pith.science/paper/ZNF3S7HM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09853&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZNF3S7HMIWQ5QIO5M7JETKFZQZ/action/replication_record"}},"created_at":"2026-07-05T12:04:17.016124+00:00","updated_at":"2026-07-05T12:04:17.016124+00:00"}