{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7E3EVI7YSWMKJIWMEDHJ2YI5R7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"12d124c5ef393d9bd0358bf721648a2836a9e65e0a695af665e02fe69e65d9e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T16:48:43Z","title_canon_sha256":"8bfc6e1a12c05c90d6d21c3af2606cbbdca950549ed19b0dddfd04107a66a13b"},"schema_version":"1.0","source":{"id":"2606.23583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23583","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23583v1","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23583","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"7E3EVI7YSWMK","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"7E3EVI7YSWMKJIWM","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"7E3EVI7Y","created_at":"2026-06-23T03:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:5ff9ee5ece90b7ce494894590fab0ee946a19d00cdfe64f3ce07d92016b4d30f","target":"graph","created_at":"2026-06-23T03:14:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.23583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety benchmarks assume that test-condition behavior predicts deployment behavior, an assumption that fails if models detect evaluation cues and adapt. This opens a gap between benchmark performance and deployment behavior: compliance measured under test conditions becomes an optimistic upper bound that overstates how safely a model behaves once the evaluation harness is removed. We characterize this evaluation awareness through eight experiments across 37 open-weight models and seven families. (i)Detection is moderate and training-driven (24/37 models exceed chance, best AUROC 0.714 vs.0.819","authors_text":"Aishwarya Sampath Kumar, David A. Nader Palacio, Nilesh Nayan, Reshmi Ghosh, Rishiraj Girmal, Sankaran Vaidyanathan, Shivani Anilkumar, Soundararajan Srinivasan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T16:48:43Z","title":"Evaluation Awareness Is Not One Capability: Evidence from Open Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23583","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c7078d598a1712da818dd4468f43770e6dbdeff9e66d61bce13971467479b331","target":"record","created_at":"2026-06-23T03:14:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"12d124c5ef393d9bd0358bf721648a2836a9e65e0a695af665e02fe69e65d9e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T16:48:43Z","title_canon_sha256":"8bfc6e1a12c05c90d6d21c3af2606cbbdca950549ed19b0dddfd04107a66a13b"},"schema_version":"1.0","source":{"id":"2606.23583","kind":"arxiv","version":1}},"canonical_sha256":"f9364aa3f89598a4a2cc20ce9d611d8fc162f7361adf5631819f2e8c4af86132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9364aa3f89598a4a2cc20ce9d611d8fc162f7361adf5631819f2e8c4af86132","first_computed_at":"2026-06-23T03:14:31.522452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:31.522452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J919VX+PdsgRdZEg6vg4DM9RWSP3nHwRYysT6rKgmHxAhGXo1/9OcSxXYYuKZYJ/PbvxjhAWWZn9LtqmGr+nCw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:31.522884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7078d598a1712da818dd4468f43770e6dbdeff9e66d61bce13971467479b331","sha256:5ff9ee5ece90b7ce494894590fab0ee946a19d00cdfe64f3ce07d92016b4d30f"],"state_sha256":"a78497a7e7228c553caecb1b89d08e6ad8594ec193772a20630bd3084517f132"}