{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2L3JUUFURFHTXH2MCETZZK2D7Q","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":"be4c4991d4d5669096a9bfcfdc0d2083f8da5e9cf25a78933225d632528af5b2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T14:02:25Z","title_canon_sha256":"ac1b54152886066c644b3f0113554d3a4780159278d3b784870c33d82b819cfc"},"schema_version":"1.0","source":{"id":"2606.31689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31689","created_at":"2026-07-01T01:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31689v1","created_at":"2026-07-01T01:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31689","created_at":"2026-07-01T01:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"2L3JUUFURFHT","created_at":"2026-07-01T01:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"2L3JUUFURFHTXH2M","created_at":"2026-07-01T01:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"2L3JUUFU","created_at":"2026-07-01T01:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:c0739a11c4801549e548429756c2f4e646a30adfe68949ccb34cf1fbc0775a41","target":"graph","created_at":"2026-07-01T01:18:11Z","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/2606.31689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"World-model evaluations often score a predicted future by overlap with a target state or observation. In sparse-change worlds, this can turn copied persistent state into apparent accuracy. We introduce ScratchWorld, an offline diagnostic benchmark that treats Scratch projects as executable worlds and uses a pinned Scratch VM to produce replay-verified transitions, hidden variables, causal traces, and counterfactual outcomes. ScratchWorld evaluates next-state prediction, long-horizon tracking, causal event attribution, and counterfactual prediction; each replay-verified target can be presented ","authors_text":"Jialu Zhang, Yufeng Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T14:02:25Z","title":"ScratchWorld: Evaluating If World Models Compute Executable Consequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31689","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:ff97f1c826ade4948289d95060b038d8187858c25e0cd70a84cdf7e17e05cb35","target":"record","created_at":"2026-07-01T01:18:11Z","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":"be4c4991d4d5669096a9bfcfdc0d2083f8da5e9cf25a78933225d632528af5b2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T14:02:25Z","title_canon_sha256":"ac1b54152886066c644b3f0113554d3a4780159278d3b784870c33d82b819cfc"},"schema_version":"1.0","source":{"id":"2606.31689","kind":"arxiv","version":1}},"canonical_sha256":"d2f69a50b4894f3b9f4c11279cab43fc052a6f424590182cea1cd58443a7bff1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2f69a50b4894f3b9f4c11279cab43fc052a6f424590182cea1cd58443a7bff1","first_computed_at":"2026-07-01T01:18:11.720371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:11.720371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dcldgvhsgaV/mtdy/sak6y2twULrSR4ouqflWTjC6X4kbNHP+LewNBntlkTTLHrQL8905syG0x8KEWEhXobHDA==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:11.720985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff97f1c826ade4948289d95060b038d8187858c25e0cd70a84cdf7e17e05cb35","sha256:c0739a11c4801549e548429756c2f4e646a30adfe68949ccb34cf1fbc0775a41"],"state_sha256":"8344f7093318d63aee368f39c803a3e27346e91214148e8be659da18318ecc50"}