{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LFW6ASD3QHVPTIQP5CENB3SG6I","short_pith_number":"pith:LFW6ASD3","canonical_record":{"source":{"id":"2507.01786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T15:12:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56636a26c4da649c3b0a660bb402345062e2c9001b4e15b25b1748a7e9e9c801","abstract_canon_sha256":"993088979a7d3b8738358cc22e8ecdda6e8b73984333b1671fb8f002df03974c"},"schema_version":"1.0"},"canonical_sha256":"596de0487b81eaf9a20fe888d0ee46f230672823d64ab7a06d86eee389cd1755","source":{"kind":"arxiv","id":"2507.01786","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01786","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01786v2","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01786","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"LFW6ASD3QHVP","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_16","alias_value":"LFW6ASD3QHVPTIQP","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_8","alias_value":"LFW6ASD3","created_at":"2026-07-05T11:34:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LFW6ASD3QHVPTIQP5CENB3SG6I","target":"record","payload":{"canonical_record":{"source":{"id":"2507.01786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T15:12:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56636a26c4da649c3b0a660bb402345062e2c9001b4e15b25b1748a7e9e9c801","abstract_canon_sha256":"993088979a7d3b8738358cc22e8ecdda6e8b73984333b1671fb8f002df03974c"},"schema_version":"1.0"},"canonical_sha256":"596de0487b81eaf9a20fe888d0ee46f230672823d64ab7a06d86eee389cd1755","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:10.622226Z","signature_b64":"jeenObD+61kiyqbuN+H+UaUtsM3yLh4JPLOMqn9A/SPYGyTFCXchML52at5VyQ9A+7j5oWkfFYMDQVueqsQHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"596de0487b81eaf9a20fe888d0ee46f230672823d64ab7a06d86eee389cd1755","last_reissued_at":"2026-07-05T11:34:10.621576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:10.621576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.01786","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kfG6uUanFvm9gA6VtnXrfgNUnVwM7HsA0gwj6MDHuBESalu+xYlgBFPtVXYXgU0rltGjadiIgB//tJMrJAO1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:22:30.877926Z"},"content_sha256":"4a5511a95bd653e7954c7d6a9b33789efcb2d97bcd754f0cc48037613b2740cc","schema_version":"1.0","event_id":"sha256:4a5511a95bd653e7954c7d6a9b33789efcb2d97bcd754f0cc48037613b2740cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LFW6ASD3QHVPTIQP5CENB3SG6I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probing and Steering Evaluation Awareness of Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carlo Leonardo Attubato, Felix Hofst\\\"atter, Jord Nguyen, Khiem Hoang","submitted_at":"2025-07-02T15:12:43Z","abstract_excerpt":"Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are central to AI governance frameworks and voluntary industry commitments. In this paper, we study evaluation awareness in Llama-3.3-70B-Instruct. We show that linear probes can separate real-world evaluation and deployment prompts, suggesting that current models internally represent this distinction. We also find that current safety evaluations are correctly classif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01786","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/2507.01786/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mlgTucHCnUxfUh/0PLiYzh6OrzWaS2bzQrD28vJa8gTeXXutkPQ7KrgfoPs5X/up1IHv8Zaynhledkn1QB/DAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:22:30.878498Z"},"content_sha256":"c7e2c39e7aca8e20739d6c75c6f0e74005a5288591b5a4326e7785615189a0d8","schema_version":"1.0","event_id":"sha256:c7e2c39e7aca8e20739d6c75c6f0e74005a5288591b5a4326e7785615189a0d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFW6ASD3QHVPTIQP5CENB3SG6I/bundle.json","state_url":"https://pith.science/pith/LFW6ASD3QHVPTIQP5CENB3SG6I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFW6ASD3QHVPTIQP5CENB3SG6I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T17:22:30Z","links":{"resolver":"https://pith.science/pith/LFW6ASD3QHVPTIQP5CENB3SG6I","bundle":"https://pith.science/pith/LFW6ASD3QHVPTIQP5CENB3SG6I/bundle.json","state":"https://pith.science/pith/LFW6ASD3QHVPTIQP5CENB3SG6I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFW6ASD3QHVPTIQP5CENB3SG6I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LFW6ASD3QHVPTIQP5CENB3SG6I","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":"993088979a7d3b8738358cc22e8ecdda6e8b73984333b1671fb8f002df03974c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T15:12:43Z","title_canon_sha256":"56636a26c4da649c3b0a660bb402345062e2c9001b4e15b25b1748a7e9e9c801"},"schema_version":"1.0","source":{"id":"2507.01786","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01786","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01786v2","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01786","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"LFW6ASD3QHVP","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_16","alias_value":"LFW6ASD3QHVPTIQP","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_8","alias_value":"LFW6ASD3","created_at":"2026-07-05T11:34:10Z"}],"graph_snapshots":[{"event_id":"sha256:c7e2c39e7aca8e20739d6c75c6f0e74005a5288591b5a4326e7785615189a0d8","target":"graph","created_at":"2026-07-05T11:34:10Z","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/2507.01786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are central to AI governance frameworks and voluntary industry commitments. In this paper, we study evaluation awareness in Llama-3.3-70B-Instruct. We show that linear probes can separate real-world evaluation and deployment prompts, suggesting that current models internally represent this distinction. We also find that current safety evaluations are correctly classif","authors_text":"Carlo Leonardo Attubato, Felix Hofst\\\"atter, Jord Nguyen, Khiem Hoang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T15:12:43Z","title":"Probing and Steering Evaluation Awareness of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01786","kind":"arxiv","version":2},"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":"sha256:4a5511a95bd653e7954c7d6a9b33789efcb2d97bcd754f0cc48037613b2740cc","target":"record","created_at":"2026-07-05T11:34:10Z","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":"993088979a7d3b8738358cc22e8ecdda6e8b73984333b1671fb8f002df03974c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T15:12:43Z","title_canon_sha256":"56636a26c4da649c3b0a660bb402345062e2c9001b4e15b25b1748a7e9e9c801"},"schema_version":"1.0","source":{"id":"2507.01786","kind":"arxiv","version":2}},"canonical_sha256":"596de0487b81eaf9a20fe888d0ee46f230672823d64ab7a06d86eee389cd1755","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"596de0487b81eaf9a20fe888d0ee46f230672823d64ab7a06d86eee389cd1755","first_computed_at":"2026-07-05T11:34:10.621576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:10.621576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jeenObD+61kiyqbuN+H+UaUtsM3yLh4JPLOMqn9A/SPYGyTFCXchML52at5VyQ9A+7j5oWkfFYMDQVueqsQHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:10.622226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01786","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a5511a95bd653e7954c7d6a9b33789efcb2d97bcd754f0cc48037613b2740cc","sha256:c7e2c39e7aca8e20739d6c75c6f0e74005a5288591b5a4326e7785615189a0d8"],"state_sha256":"8e7e3f3e7ab3a60945b08c73978df60756c80d9b5f7f9a15f71041d3d1b41bdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tl3TOt01+IG+THFTmRrYCFFBZ0pf1hbGTAeJEBZChWkFJ+CRIo+DO+NqbYyCZtrGTlPgIjnfFl/mN903l6b4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:22:30.883229Z","bundle_sha256":"a98078b7ee0186556f2b5686fcbbc47972093456b5d46306ca855a5d7f978437"}}