{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MPMKXRAKADVPKQQIPUE5QW3CDY","short_pith_number":"pith:MPMKXRAK","schema_version":"1.0","canonical_sha256":"63d8abc40a00eaf542087d09d85b621e360ebb1be64c28d4a34b5ffdcecffa02","source":{"kind":"arxiv","id":"2607.11953","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.11953","created_at":"2026-07-15T00:21:24.777981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11953v1","created_at":"2026-07-15T00:21:24.777981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11953","created_at":"2026-07-15T00:21:24.777981+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPMKXRAKADVP","created_at":"2026-07-15T00:21:24.777981+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPMKXRAKADVPKQQI","created_at":"2026-07-15T00:21:24.777981+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPMKXRAK","created_at":"2026-07-15T00:21:24.777981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY","json":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY.json","graph_json":"https://pith.science/api/pith-number/MPMKXRAKADVPKQQIPUE5QW3CDY/graph.json","events_json":"https://pith.science/api/pith-number/MPMKXRAKADVPKQQIPUE5QW3CDY/events.json","paper":"https://pith.science/paper/MPMKXRAK"},"agent_actions":{"view_html":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY","download_json":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY.json","view_paper":"https://pith.science/paper/MPMKXRAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11953&json=true","fetch_graph":"https://pith.science/api/pith-number/MPMKXRAKADVPKQQIPUE5QW3CDY/graph.json","fetch_events":"https://pith.science/api/pith-number/MPMKXRAKADVPKQQIPUE5QW3CDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/action/storage_attestation","attest_author":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/action/author_attestation","sign_citation":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/action/citation_signature","submit_replication":"https://pith.science/pith/MPMKXRAKADVPKQQIPUE5QW3CDY/action/replication_record"}},"created_at":"2026-07-15T00:21:24.777981+00:00","updated_at":"2026-07-15T00:21:24.777981+00:00"}