{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DNRKHSXG5G5NCCWQDARBC72DBH","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":"9ad71b1581099f522ab6965eb5193784bd14d997000023808806cc30e2e873b9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T04:48:17Z","title_canon_sha256":"4d748175157c11f50f479b9e4936629a1f292054b1ccca8a0457a469e2833159"},"schema_version":"1.0","source":{"id":"2606.29196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29196","created_at":"2026-06-30T01:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29196v1","created_at":"2026-06-30T01:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29196","created_at":"2026-06-30T01:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"DNRKHSXG5G5N","created_at":"2026-06-30T01:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"DNRKHSXG5G5NCCWQ","created_at":"2026-06-30T01:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"DNRKHSXG","created_at":"2026-06-30T01:17:56Z"}],"graph_snapshots":[{"event_id":"sha256:762b54e117b9797515b936f9528eb06a1a86c3270238b6ee49846e65281b6e10","target":"graph","created_at":"2026-06-30T01:17:56Z","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/2606.29196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Do language models know when they are being tested? This question matters for AI safety: a model that recognises an evaluation context could alter its behaviour strategically, making downstream benchmarks harder to interpret. Using 11 models spanning Qwen 2.5, Gemma 2, and Llama 3.2, we find a systematic size-dependent shift in representational depth: in both Qwen 2.5 and Gemma 2, the layer at which evaluation-awareness is most linearly recoverable moves from late layers in smaller models to early layers in larger ones. This suggests that scale changes not only the strength of evaluation-aware","authors_text":"Archit Manek","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T04:48:17Z","title":"Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29196","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":"sha256:1d6e2e5847f132b2ac942e3b65336b94cbf297c3e7ad2d5592f1fb0b9543466a","target":"record","created_at":"2026-06-30T01:17:56Z","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":"9ad71b1581099f522ab6965eb5193784bd14d997000023808806cc30e2e873b9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T04:48:17Z","title_canon_sha256":"4d748175157c11f50f479b9e4936629a1f292054b1ccca8a0457a469e2833159"},"schema_version":"1.0","source":{"id":"2606.29196","kind":"arxiv","version":1}},"canonical_sha256":"1b62a3cae6e9bad10ad01822117f4309c9d30c62d5e5b041c08213194c2c34d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b62a3cae6e9bad10ad01822117f4309c9d30c62d5e5b041c08213194c2c34d3","first_computed_at":"2026-06-30T01:17:56.783940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:56.783940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mSPF9cJt3TgoQcUwUSyftR93Ld8zKs2ol70xrJkRC/wUK+vsagqmfANyzOrd+xPwAO5R9OAivTTNkdUG3cQ1Cg==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:56.784473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d6e2e5847f132b2ac942e3b65336b94cbf297c3e7ad2d5592f1fb0b9543466a","sha256:762b54e117b9797515b936f9528eb06a1a86c3270238b6ee49846e65281b6e10"],"state_sha256":"bd9ce3c62d84f1a7c41747c0378dff24a15bd05c1e6fa4143d72caa54acd67e2"}