{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BQSDWS6UQGJSU6H5QGEGGNVSOS","short_pith_number":"pith:BQSDWS6U","canonical_record":{"source":{"id":"2506.04828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T09:50:02Z","cross_cats_sorted":[],"title_canon_sha256":"4a9afc1a143ecb9358169e5c02710c522bf49ce1dd8a6179726c544b60c71e5f","abstract_canon_sha256":"241d6b155cd1cc57d8d3c47b44af46bec43e5b356ed4a72c20864608b6f859c8"},"schema_version":"1.0"},"canonical_sha256":"0c243b4bd481932a78fd81886336b274a88d4b7a02a83b0357f517e0f4c2ac6b","source":{"kind":"arxiv","id":"2506.04828","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04828","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04828v1","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04828","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"BQSDWS6UQGJS","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"BQSDWS6UQGJSU6H5","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"BQSDWS6U","created_at":"2026-07-05T11:16:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BQSDWS6UQGJSU6H5QGEGGNVSOS","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T09:50:02Z","cross_cats_sorted":[],"title_canon_sha256":"4a9afc1a143ecb9358169e5c02710c522bf49ce1dd8a6179726c544b60c71e5f","abstract_canon_sha256":"241d6b155cd1cc57d8d3c47b44af46bec43e5b356ed4a72c20864608b6f859c8"},"schema_version":"1.0"},"canonical_sha256":"0c243b4bd481932a78fd81886336b274a88d4b7a02a83b0357f517e0f4c2ac6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:37.447659Z","signature_b64":"x68ZpMNtr28PKjUaS4eejZDJo5oqvbq+qyjO7SM3wq0g4k1IpiaxX4ALBZwQjCNScY+BQTM7WeARHrnZxBbOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c243b4bd481932a78fd81886336b274a88d4b7a02a83b0357f517e0f4c2ac6b","last_reissued_at":"2026-07-05T11:16:37.447227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:37.447227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04828","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nAV6t13HlY+0Yg1oAmcGdLwJLtzUZyiVVh23N4S/2gqb5vM1sfJgyCeeEadUDtX26xP5GxLsWGkaS3ky5LO7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:00:14.798124Z"},"content_sha256":"d0b063849cbd32f871deb6a1227bda30b02757d353fd882e827bd3e548622f3b","schema_version":"1.0","event_id":"sha256:d0b063849cbd32f871deb6a1227bda30b02757d353fd882e827bd3e548622f3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BQSDWS6UQGJSU6H5QGEGGNVSOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Planning and Policy Optimization via World Model Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aleksandr I. Panov, Artem Latyshev, Gregory Gorbov","submitted_at":"2025-06-05T09:50:02Z","abstract_excerpt":"Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy optimization, but inherent model inaccuracies can lead to catastrophic failures in safety-critical settings. We propose a novel model-based RL framework that jointly optimizes task performance and safety. To address world model errors, our method incorporates an adaptive mechanism that dynamically switches between model-based planning and direct policy execution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04828","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/2506.04828/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmU1kw6lALSbx/qvDnsy3X87dhKd3M+k6fViHuTPApgql5HEMYUVoCftg7YYgCYAKSSARKUPP5lQNedpRVyLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:00:14.799032Z"},"content_sha256":"12b9d0ce24ffb26913513db444197c527b8302a5433c9b4728486d7e4188359c","schema_version":"1.0","event_id":"sha256:12b9d0ce24ffb26913513db444197c527b8302a5433c9b4728486d7e4188359c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQSDWS6UQGJSU6H5QGEGGNVSOS/bundle.json","state_url":"https://pith.science/pith/BQSDWS6UQGJSU6H5QGEGGNVSOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQSDWS6UQGJSU6H5QGEGGNVSOS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T11:00:14Z","links":{"resolver":"https://pith.science/pith/BQSDWS6UQGJSU6H5QGEGGNVSOS","bundle":"https://pith.science/pith/BQSDWS6UQGJSU6H5QGEGGNVSOS/bundle.json","state":"https://pith.science/pith/BQSDWS6UQGJSU6H5QGEGGNVSOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQSDWS6UQGJSU6H5QGEGGNVSOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BQSDWS6UQGJSU6H5QGEGGNVSOS","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":"241d6b155cd1cc57d8d3c47b44af46bec43e5b356ed4a72c20864608b6f859c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T09:50:02Z","title_canon_sha256":"4a9afc1a143ecb9358169e5c02710c522bf49ce1dd8a6179726c544b60c71e5f"},"schema_version":"1.0","source":{"id":"2506.04828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04828","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04828v1","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04828","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"BQSDWS6UQGJS","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"BQSDWS6UQGJSU6H5","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"BQSDWS6U","created_at":"2026-07-05T11:16:37Z"}],"graph_snapshots":[{"event_id":"sha256:12b9d0ce24ffb26913513db444197c527b8302a5433c9b4728486d7e4188359c","target":"graph","created_at":"2026-07-05T11:16:37Z","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/2506.04828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy optimization, but inherent model inaccuracies can lead to catastrophic failures in safety-critical settings. We propose a novel model-based RL framework that jointly optimizes task performance and safety. To address world model errors, our method incorporates an adaptive mechanism that dynamically switches between model-based planning and direct policy execution","authors_text":"Aleksandr I. Panov, Artem Latyshev, Gregory Gorbov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T09:50:02Z","title":"Safe Planning and Policy Optimization via World Model Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04828","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:d0b063849cbd32f871deb6a1227bda30b02757d353fd882e827bd3e548622f3b","target":"record","created_at":"2026-07-05T11:16:37Z","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":"241d6b155cd1cc57d8d3c47b44af46bec43e5b356ed4a72c20864608b6f859c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T09:50:02Z","title_canon_sha256":"4a9afc1a143ecb9358169e5c02710c522bf49ce1dd8a6179726c544b60c71e5f"},"schema_version":"1.0","source":{"id":"2506.04828","kind":"arxiv","version":1}},"canonical_sha256":"0c243b4bd481932a78fd81886336b274a88d4b7a02a83b0357f517e0f4c2ac6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c243b4bd481932a78fd81886336b274a88d4b7a02a83b0357f517e0f4c2ac6b","first_computed_at":"2026-07-05T11:16:37.447227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:37.447227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x68ZpMNtr28PKjUaS4eejZDJo5oqvbq+qyjO7SM3wq0g4k1IpiaxX4ALBZwQjCNScY+BQTM7WeARHrnZxBbOCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:37.447659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0b063849cbd32f871deb6a1227bda30b02757d353fd882e827bd3e548622f3b","sha256:12b9d0ce24ffb26913513db444197c527b8302a5433c9b4728486d7e4188359c"],"state_sha256":"44c7f1b59bf44b7db94c1403c187d1cec6a15f9b20e21bec50778daac5aa26e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvUbNAFSlQo+GFfedUFEKf/uGyWjSY+mTW8ztJc0NffBsZCAZ7/bn0HlB/Ank2rFZRFaOzUenrdQQCceTUOQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:00:14.803798Z","bundle_sha256":"77eba621826641dda2a4d1313c7b71835f4b5844a35c5456f31257fb0afebdad"}}