{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z3SG5TFPYEI7OPED2OB22KAAXO","short_pith_number":"pith:Z3SG5TFP","schema_version":"1.0","canonical_sha256":"cee46eccafc111f73c83d383ad2800bb864df9d7783e1027483c7b45e0b180e4","source":{"kind":"arxiv","id":"2606.20634","version":1},"attestation_state":"computed","paper":{"title":"DEMM-Bench: A Cross-Regime Benchmark for Agent-Runtime Governance-Evidence Sufficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Oleg Solozobov","submitted_at":"2026-05-30T09:36:29Z","abstract_excerpt":"Agent-runtime systems emit traces, ledgers, provenance graphs, policy logs, delegation tokens, cache events, and tool-firewall records, but those containers do not necessarily answer governance questions about a specific decision. DEMM-Bench is a cross-regime benchmark for agent-runtime governance-evidence sufficiency, grounded in the Decision Evidence Maturity Model (DEMM): it measures whether records across eight evidence regimes are sufficient to reconstruct decision-level properties rather than merely present. The benchmark normalizes the regimes through adapters, asks property questions o"},"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":"2606.20634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T09:36:29Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"38afdc7076f75a21b0c2a5e6228972e860879aa8b2aadad9bc23f8a0c254be25","abstract_canon_sha256":"b1ab565ec014c02591b73b166e85ca22d94de00fa8ae5043ca56f39f99e97613"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:52.074287Z","signature_b64":"/+rvCGKlHqs4UUuekguE0XWyN+MdwMxabrCNB9S13/kr76mG5usmxC/CeDQGiKscAU7V2md/qP71X6iZ2D3aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cee46eccafc111f73c83d383ad2800bb864df9d7783e1027483c7b45e0b180e4","last_reissued_at":"2026-06-23T00:11:52.073806Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:52.073806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEMM-Bench: A Cross-Regime Benchmark for Agent-Runtime Governance-Evidence Sufficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Oleg Solozobov","submitted_at":"2026-05-30T09:36:29Z","abstract_excerpt":"Agent-runtime systems emit traces, ledgers, provenance graphs, policy logs, delegation tokens, cache events, and tool-firewall records, but those containers do not necessarily answer governance questions about a specific decision. DEMM-Bench is a cross-regime benchmark for agent-runtime governance-evidence sufficiency, grounded in the Decision Evidence Maturity Model (DEMM): it measures whether records across eight evidence regimes are sufficient to reconstruct decision-level properties rather than merely present. The benchmark normalizes the regimes through adapters, asks property questions o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20634","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/2606.20634/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":"2606.20634","created_at":"2026-06-23T00:11:52.073872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20634v1","created_at":"2026-06-23T00:11:52.073872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20634","created_at":"2026-06-23T00:11:52.073872+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3SG5TFPYEI7","created_at":"2026-06-23T00:11:52.073872+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3SG5TFPYEI7OPED","created_at":"2026-06-23T00:11:52.073872+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3SG5TFP","created_at":"2026-06-23T00:11:52.073872+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/Z3SG5TFPYEI7OPED2OB22KAAXO","json":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO.json","graph_json":"https://pith.science/api/pith-number/Z3SG5TFPYEI7OPED2OB22KAAXO/graph.json","events_json":"https://pith.science/api/pith-number/Z3SG5TFPYEI7OPED2OB22KAAXO/events.json","paper":"https://pith.science/paper/Z3SG5TFP"},"agent_actions":{"view_html":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO","download_json":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO.json","view_paper":"https://pith.science/paper/Z3SG5TFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20634&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3SG5TFPYEI7OPED2OB22KAAXO/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3SG5TFPYEI7OPED2OB22KAAXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO/action/storage_attestation","attest_author":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO/action/author_attestation","sign_citation":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO/action/citation_signature","submit_replication":"https://pith.science/pith/Z3SG5TFPYEI7OPED2OB22KAAXO/action/replication_record"}},"created_at":"2026-06-23T00:11:52.073872+00:00","updated_at":"2026-06-23T00:11:52.073872+00:00"}