{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2L3JUUFURFHTXH2MCETZZK2D7Q","short_pith_number":"pith:2L3JUUFU","schema_version":"1.0","canonical_sha256":"d2f69a50b4894f3b9f4c11279cab43fc052a6f424590182cea1cd58443a7bff1","source":{"kind":"arxiv","id":"2606.31689","version":1},"attestation_state":"computed","paper":{"title":"ScratchWorld: Evaluating If World Models Compute Executable Consequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jialu Zhang, Yufeng Lin","submitted_at":"2026-06-30T14:02:25Z","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 "},"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":"2606.31689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T14:02:25Z","cross_cats_sorted":[],"title_canon_sha256":"ac1b54152886066c644b3f0113554d3a4780159278d3b784870c33d82b819cfc","abstract_canon_sha256":"be4c4991d4d5669096a9bfcfdc0d2083f8da5e9cf25a78933225d632528af5b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:11.720985Z","signature_b64":"dcldgvhsgaV/mtdy/sak6y2twULrSR4ouqflWTjC6X4kbNHP+LewNBntlkTTLHrQL8905syG0x8KEWEhXobHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2f69a50b4894f3b9f4c11279cab43fc052a6f424590182cea1cd58443a7bff1","last_reissued_at":"2026-07-01T01:18:11.720371Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:11.720371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScratchWorld: Evaluating If World Models Compute Executable Consequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jialu Zhang, Yufeng Lin","submitted_at":"2026-06-30T14:02:25Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31689","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/2606.31689/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":"2606.31689","created_at":"2026-07-01T01:18:11.720455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31689v1","created_at":"2026-07-01T01:18:11.720455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31689","created_at":"2026-07-01T01:18:11.720455+00:00"},{"alias_kind":"pith_short_12","alias_value":"2L3JUUFURFHT","created_at":"2026-07-01T01:18:11.720455+00:00"},{"alias_kind":"pith_short_16","alias_value":"2L3JUUFURFHTXH2M","created_at":"2026-07-01T01:18:11.720455+00:00"},{"alias_kind":"pith_short_8","alias_value":"2L3JUUFU","created_at":"2026-07-01T01:18:11.720455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2607.01280","citing_title":"Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00623","citing_title":"SchedCheck: Schedule-Robustness Analysis for Event-Driven Block Programs","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00635","citing_title":"Checked Program Recovery from Execution Video: A Sound Oracle for Untrusted Generators","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00563","citing_title":"Certificate-Carrying Transformation of Event-Driven Block Programs","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q","json":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q.json","graph_json":"https://pith.science/api/pith-number/2L3JUUFURFHTXH2MCETZZK2D7Q/graph.json","events_json":"https://pith.science/api/pith-number/2L3JUUFURFHTXH2MCETZZK2D7Q/events.json","paper":"https://pith.science/paper/2L3JUUFU"},"agent_actions":{"view_html":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q","download_json":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q.json","view_paper":"https://pith.science/paper/2L3JUUFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31689&json=true","fetch_graph":"https://pith.science/api/pith-number/2L3JUUFURFHTXH2MCETZZK2D7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/2L3JUUFURFHTXH2MCETZZK2D7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q/action/storage_attestation","attest_author":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q/action/author_attestation","sign_citation":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q/action/citation_signature","submit_replication":"https://pith.science/pith/2L3JUUFURFHTXH2MCETZZK2D7Q/action/replication_record"}},"created_at":"2026-07-01T01:18:11.720455+00:00","updated_at":"2026-07-01T01:18:11.720455+00:00"}