{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:36SVPK76GLVA4V7VGTNPKRVUXK","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":"6d295b9d9912219d50c7cebde24bec56f0f3e570617bd2dc2792729fe93513c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T02:50:26Z","title_canon_sha256":"2326fbadebf0d98cd7912255319651bd143c4701043e7da0b0638d8ed582dd03"},"schema_version":"1.0","source":{"id":"2606.05625","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05625","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05625v1","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05625","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"36SVPK76GLVA","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"36SVPK76GLVA4V7V","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"36SVPK76","created_at":"2026-06-05T01:14:56Z"}],"graph_snapshots":[{"event_id":"sha256:0699030564e197fb4db4339e6882c9df8697e9782ae1af988ea01296b034e2b1","target":"graph","created_at":"2026-06-05T01:14:56Z","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/2606.05625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Implicit reward hacking is hard to audit when a language model's chain of thought appears benign: a final answer may be anchored by a prompt shortcut while the written reasoning still resembles ordinary problem solving. Verifier-based probes expose such behavior by measuring how early truncated reasoning contexts obtain high reward, but require a task-specific reward signal. This paper proposes a weaker-input alternative, self-commitment latency, which measures how early a prompted reasoning context commits to the model's own final answer. We evaluate the probe in a controlled paired GSM8K set","authors_text":"Bonan Shen, Dingyan Shang, Tao Ning, Youting Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T02:50:26Z","title":"Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05625","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:f339a4d163336f1d41fb78af5977a797c21cea8b721a76c5514bff778cc59fa6","target":"record","created_at":"2026-06-05T01:14:56Z","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":"6d295b9d9912219d50c7cebde24bec56f0f3e570617bd2dc2792729fe93513c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T02:50:26Z","title_canon_sha256":"2326fbadebf0d98cd7912255319651bd143c4701043e7da0b0638d8ed582dd03"},"schema_version":"1.0","source":{"id":"2606.05625","kind":"arxiv","version":1}},"canonical_sha256":"dfa557abfe32ea0e57f534daf546b4baba64b72d3227ae45c630b0d88b7c3285","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfa557abfe32ea0e57f534daf546b4baba64b72d3227ae45c630b0d88b7c3285","first_computed_at":"2026-06-05T01:14:56.944202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:56.944202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aWMwO3hZ0tmLLOLmUzw258EVaC1o4CV+imTARf4+O+J+P/fTgkispS+grwGl+W9Zw1NxCOxdjC7OL7Y+wCv5BA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:56.944753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05625","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f339a4d163336f1d41fb78af5977a797c21cea8b721a76c5514bff778cc59fa6","sha256:0699030564e197fb4db4339e6882c9df8697e9782ae1af988ea01296b034e2b1"],"state_sha256":"90e9a44ff5937443895610bfe100d025e4ce91635f9fb3d4ecd3c1b12275f13b"}