{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4HF35XRJOEXACC5DIWL2F4BY5B","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":"9830ca1e471088d412e5fae78a4cb79e09c94d322e406dab1467d7248f457d3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T17:51:40Z","title_canon_sha256":"e35534c72ca8997f6551ae9a1092fe45f97dfde726a24c5df5a0eef5af9e1a5e"},"schema_version":"1.0","source":{"id":"2606.02556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02556","created_at":"2026-06-02T03:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02556v1","created_at":"2026-06-02T03:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02556","created_at":"2026-06-02T03:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"4HF35XRJOEXA","created_at":"2026-06-02T03:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"4HF35XRJOEXACC5D","created_at":"2026-06-02T03:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"4HF35XRJ","created_at":"2026-06-02T03:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:475d5b987d58c594777058a2b0123f908d68b851e16aabfb1c65e8f9c8ebbb98","target":"graph","created_at":"2026-06-02T03:05:09Z","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/2606.02556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce HERO'S JOURNEY, a benchmark for rule induction in goal-directed episodic tasks, where agents must infer hidden rules from demonstrations and act on them through multi-step execution. HERO'S JOURNEY covers eight tasks across attribute and procedural induction families, each with four structural rule forms, controllable lexical grounding, and identifiability conditions. Evaluating state-of-the-art LLMs, we find that models show evidence of rule induction, but the ability is limited and uneven across tasks. Meanwhile, process execution adds an execution bottleneck for models, whereas","authors_text":"Anshun Asher Zheng, David I. Beaver, Junyi Jessy Li, Kanishka Misra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T17:51:40Z","title":"HERO'S JOURNEY: Testing Complex Rule Induction with Text Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02556","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:f5ce0a35393f61be43d1d7f48ad17366012e1bb5790b162331ee8267b63967f0","target":"record","created_at":"2026-06-02T03:05:09Z","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":"9830ca1e471088d412e5fae78a4cb79e09c94d322e406dab1467d7248f457d3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T17:51:40Z","title_canon_sha256":"e35534c72ca8997f6551ae9a1092fe45f97dfde726a24c5df5a0eef5af9e1a5e"},"schema_version":"1.0","source":{"id":"2606.02556","kind":"arxiv","version":1}},"canonical_sha256":"e1cbbede29712e010ba34597a2f038e85341710b42c34d0baddabd6a41fcad7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1cbbede29712e010ba34597a2f038e85341710b42c34d0baddabd6a41fcad7e","first_computed_at":"2026-06-02T03:05:09.501086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:05:09.501086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jHyylyGfuu6k1GPzTV22dhcEhuV9n/HUo0kfopEGF8vFC7DOQkj78cMnJFlwoVeOksewSUr5qn75j2ZbrJCGAw==","signature_status":"signed_v1","signed_at":"2026-06-02T03:05:09.501440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5ce0a35393f61be43d1d7f48ad17366012e1bb5790b162331ee8267b63967f0","sha256:475d5b987d58c594777058a2b0123f908d68b851e16aabfb1c65e8f9c8ebbb98"],"state_sha256":"a1e110b5284c79560dbe6e14ca63fbea91261d834efffbe4202f9fdd25b787c5"}