{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MPMKXRAKADVPKQQIPUE5QW3CDY","short_pith_number":"pith:MPMKXRAK","canonical_record":{"source":{"id":"2607.11953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T21:33:32Z","cross_cats_sorted":[],"title_canon_sha256":"32714d1ccf48abf3918e4334aca1d3373215328ae8145a75670694c211469a69","abstract_canon_sha256":"18448d4cc9145872e811a33fbbba2d617ac684e5a586dc2fc91cf9f4205c83f5"},"schema_version":"1.0"},"canonical_sha256":"63d8abc40a00eaf542087d09d85b621e360ebb1be64c28d4a34b5ffdcecffa02","source":{"kind":"arxiv","id":"2607.11953","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11953","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11953v1","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11953","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"MPMKXRAKADVP","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"MPMKXRAKADVPKQQI","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"MPMKXRAK","created_at":"2026-07-15T00:21:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MPMKXRAKADVPKQQIPUE5QW3CDY","target":"record","payload":{"canonical_record":{"source":{"id":"2607.11953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T21:33:32Z","cross_cats_sorted":[],"title_canon_sha256":"32714d1ccf48abf3918e4334aca1d3373215328ae8145a75670694c211469a69","abstract_canon_sha256":"18448d4cc9145872e811a33fbbba2d617ac684e5a586dc2fc91cf9f4205c83f5"},"schema_version":"1.0"},"canonical_sha256":"63d8abc40a00eaf542087d09d85b621e360ebb1be64c28d4a34b5ffdcecffa02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T00:21:24.778446Z","signature_b64":"xztt1JDvzmAyUBlFBk7dIewnE7KftwId9EuTk4flndhyb4Ego8UHm8FQ9gZEkI+EPISZ0GzHn7ueuRrfGcZGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63d8abc40a00eaf542087d09d85b621e360ebb1be64c28d4a34b5ffdcecffa02","last_reissued_at":"2026-07-15T00:21:24.777531Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T00:21:24.777531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.11953","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-15T00:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NOW0pgryP4OJ8OfVC/JQdDTI20FMqt9PLWnZ05Qp/SuSxafuODgAbLFVOZJZUxb4nNEINWo4dGb6sE5uFF2pBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:13:34.738242Z"},"content_sha256":"72fa683781674a607eaaba94acb612597c4cbfb2da727b23c85345202743f8ec","schema_version":"1.0","event_id":"sha256:72fa683781674a607eaaba94acb612597c4cbfb2da727b23c85345202743f8ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MPMKXRAKADVPKQQIPUE5QW3CDY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jim Allchin","submitted_at":"2026-07-11T21:33:32Z","abstract_excerpt":"Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut? The question is usually unanswerable: the \"true state\" is undefined. We make it exactly answerable with a white-box instrument: express the task as a hidden deterministic finite automaton (DFA), let the agent observe a symbol stream and intermittently choose the next symbol under partial control, and grant one sparse terminal reward for acceptance. Knowing the automaton gives two things for free: the optimal return (so reward becomes an interpretable normalized sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11953","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/2607.11953/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":"2026-07-15T00:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYEzXVQ+o0yMxpCpsxC2zNQLOAhjojrgWvB4zNMpx91U9oVzd937mBzb+KareEIwVfkJo7kthbPfKZQwKJfpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:13:34.738791Z"},"content_sha256":"91e7330c34faf500be7203aae91d4d53b1cc2ad291e5544dad80d98dcfced8f4","schema_version":"1.0","event_id":"sha256:91e7330c34faf500be7203aae91d4d53b1cc2ad291e5544dad80d98dcfced8f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/bundle.json","state_url":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/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":"2026-08-04T07:13:34Z","links":{"resolver":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY","bundle":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/bundle.json","state":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MPMKXRAKADVPKQQIPUE5QW3CDY","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":"18448d4cc9145872e811a33fbbba2d617ac684e5a586dc2fc91cf9f4205c83f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T21:33:32Z","title_canon_sha256":"32714d1ccf48abf3918e4334aca1d3373215328ae8145a75670694c211469a69"},"schema_version":"1.0","source":{"id":"2607.11953","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11953","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11953v1","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11953","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"MPMKXRAKADVP","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"MPMKXRAKADVPKQQI","created_at":"2026-07-15T00:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"MPMKXRAK","created_at":"2026-07-15T00:21:24Z"}],"graph_snapshots":[{"event_id":"sha256:91e7330c34faf500be7203aae91d4d53b1cc2ad291e5544dad80d98dcfced8f4","target":"graph","created_at":"2026-07-15T00:21:24Z","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/2607.11953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut? The question is usually unanswerable: the \"true state\" is undefined. We make it exactly answerable with a white-box instrument: express the task as a hidden deterministic finite automaton (DFA), let the agent observe a symbol stream and intermittently choose the next symbol under partial control, and grant one sparse terminal reward for acceptance. Knowing the automaton gives two things for free: the optimal return (so reward becomes an interpretable normalized sc","authors_text":"Jim Allchin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T21:33:32Z","title":"When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11953","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":"sha256:72fa683781674a607eaaba94acb612597c4cbfb2da727b23c85345202743f8ec","target":"record","created_at":"2026-07-15T00:21:24Z","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":"18448d4cc9145872e811a33fbbba2d617ac684e5a586dc2fc91cf9f4205c83f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T21:33:32Z","title_canon_sha256":"32714d1ccf48abf3918e4334aca1d3373215328ae8145a75670694c211469a69"},"schema_version":"1.0","source":{"id":"2607.11953","kind":"arxiv","version":1}},"canonical_sha256":"63d8abc40a00eaf542087d09d85b621e360ebb1be64c28d4a34b5ffdcecffa02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63d8abc40a00eaf542087d09d85b621e360ebb1be64c28d4a34b5ffdcecffa02","first_computed_at":"2026-07-15T00:21:24.777531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T00:21:24.777531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xztt1JDvzmAyUBlFBk7dIewnE7KftwId9EuTk4flndhyb4Ego8UHm8FQ9gZEkI+EPISZ0GzHn7ueuRrfGcZGAg==","signature_status":"signed_v1","signed_at":"2026-07-15T00:21:24.778446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11953","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72fa683781674a607eaaba94acb612597c4cbfb2da727b23c85345202743f8ec","sha256:91e7330c34faf500be7203aae91d4d53b1cc2ad291e5544dad80d98dcfced8f4"],"state_sha256":"923731f1745c2b7e8b012073109740ae3e18b49fe335e3c834b77ac4a3816775"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NR7STJx0+4uuGdsHZWdZTbWXobPaNVet6/uUU+6DsD05/coAtd1pC6mrOVSkubAAHC0bgm8h7IUrJp33xN4jCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:13:34.742643Z","bundle_sha256":"49c135d121d9d595f1508e6f1cf3a5fdd381ef36de7ac34d53653e4f2690476b"}}