{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2CVWDJBDPH2MUONX4TUHY5AOKK","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":"a7338d26052336917d3d9b94fbde618ea4b8648a3ae3f0ecdd2ba43ff14380d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T23:49:42Z","title_canon_sha256":"72a68ca5a5900d8dbd9380ee90570c7bc9ed939e07a21de277bbe13833280025"},"schema_version":"1.0","source":{"id":"2607.18589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18589","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18589v1","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18589","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_12","alias_value":"2CVWDJBDPH2M","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_16","alias_value":"2CVWDJBDPH2MUONX","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_8","alias_value":"2CVWDJBD","created_at":"2026-07-22T00:22:55Z"}],"graph_snapshots":[{"event_id":"sha256:58533e67a144262d38925d6103976e63ab5990c8a6b6a08638f3293dddf2a896","target":"graph","created_at":"2026-07-22T00:22:55Z","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/2607.18589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is conventionally divided into model-based and model-free methods. In this taxonomy, model-based methods perform lookahead planning over a learned world model, whereas model-free methods learn a reactive state-action mapping. Recent work, however, has shown that planning can emerge from model-free reinforcement learning alone. The conditions under which this behavior emerges from a pure reward-maximization objective have so far remained unclear. In this paper, we present evidence that, in the observed cases, the hidden-state structure of the neural architecture is the de","authors_text":"Armin Sommer","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T23:49:42Z","title":"Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18589","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":"sha256:34f5737d6df3e05541915a7bc9c8a4a99d6586573bbcf3704d1d6ec9f9cab176","target":"record","created_at":"2026-07-22T00:22:55Z","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":"a7338d26052336917d3d9b94fbde618ea4b8648a3ae3f0ecdd2ba43ff14380d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T23:49:42Z","title_canon_sha256":"72a68ca5a5900d8dbd9380ee90570c7bc9ed939e07a21de277bbe13833280025"},"schema_version":"1.0","source":{"id":"2607.18589","kind":"arxiv","version":1}},"canonical_sha256":"d0ab61a42379f4ca39b7e4e87c740e52970637ee893d6a2eb46d91a087ec3408","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0ab61a42379f4ca39b7e4e87c740e52970637ee893d6a2eb46d91a087ec3408","first_computed_at":"2026-07-22T00:22:55.598491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:55.598491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LamR+lCdSMF74fwJ4/x7406BZfLBksf7PjB/kTjMQJdjHwdAkxS+x7ipDrrKFZwx+ihp/egFa66HWbG2BGduDg==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:55.599244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34f5737d6df3e05541915a7bc9c8a4a99d6586573bbcf3704d1d6ec9f9cab176","sha256:58533e67a144262d38925d6103976e63ab5990c8a6b6a08638f3293dddf2a896"],"state_sha256":"2cf5620c32afc1e49abf8cf6051efacd1542648667aa322dedf7f4cc3db0c03b"}