{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ALOLLCXU7NSNVLPUJV4RHVLBUB","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":"fb67fbfc0a6841c7bfbe8ab099052168ef6f1bf137978715d735f22646a6f61c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T13:40:19Z","title_canon_sha256":"79320c799ebed4165ca593b16ff2e267dafbf51b44039dc08ef824bdf958977e"},"schema_version":"1.0","source":{"id":"2606.12072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12072","created_at":"2026-06-11T01:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12072v1","created_at":"2026-06-11T01:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12072","created_at":"2026-06-11T01:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"ALOLLCXU7NSN","created_at":"2026-06-11T01:10:46Z"},{"alias_kind":"pith_short_16","alias_value":"ALOLLCXU7NSNVLPU","created_at":"2026-06-11T01:10:46Z"},{"alias_kind":"pith_short_8","alias_value":"ALOLLCXU","created_at":"2026-06-11T01:10:46Z"}],"graph_snapshots":[{"event_id":"sha256:523d25f60e6a2c5f53c3cb32fc4db2f24ad62f3f72fd5b27f0f09871cbee7f63","target":"graph","created_at":"2026-06-11T01:10:46Z","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/2606.12072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual descriptions limits their direct use for planning and decision-making. Existing approaches either outsource this reasoning to language or vision-language models, or rely on supervised fine-tuning with paired task-execution videos, which are costly to collect and difficult to scale. We propose a scalable framework that elicits task-solving ability in such models by combining self-distillation with reinforcement learning. Given an unlabeled scene","authors_text":"Aram Davtyan, Pablo Acuaviva Huertos, Paolo Favaro, Sebastian Stapf","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T13:40:19Z","title":"World Model Self-Distillation: Training World Models to Solve General Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12072","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":"sha256:05f68f123674a9504b5dd54bec737c43f13abb0cdf34e17aea494c4acd79cdc1","target":"record","created_at":"2026-06-11T01:10:46Z","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":"fb67fbfc0a6841c7bfbe8ab099052168ef6f1bf137978715d735f22646a6f61c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T13:40:19Z","title_canon_sha256":"79320c799ebed4165ca593b16ff2e267dafbf51b44039dc08ef824bdf958977e"},"schema_version":"1.0","source":{"id":"2606.12072","kind":"arxiv","version":1}},"canonical_sha256":"02dcb58af4fb64daadf44d7913d561a0544acc067585e807875732f2ed3d5309","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02dcb58af4fb64daadf44d7913d561a0544acc067585e807875732f2ed3d5309","first_computed_at":"2026-06-11T01:10:46.159776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:46.159776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mJ4xCiEg7c1RR9eiFT/O5v9Oz03oRXu1F3s8qvQpzq6nMoqMhadTYv2CkQb6xsvuDbj0HgDwE+DphnvAnHyqBw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:46.160695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f68f123674a9504b5dd54bec737c43f13abb0cdf34e17aea494c4acd79cdc1","sha256:523d25f60e6a2c5f53c3cb32fc4db2f24ad62f3f72fd5b27f0f09871cbee7f63"],"state_sha256":"7a44358f19b6714af4260427b2dd3198df38c0f07e45ca3204955e761952b934"}