{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DHDUMQRHHTQVUPU7LOKPTRXQLN","short_pith_number":"pith:DHDUMQRH","canonical_record":{"source":{"id":"2505.08073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T21:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"875cfeec2ec973cb9f0c650d9d57007cb580160672836e1df467916247e0e28b","abstract_canon_sha256":"097c14600da37207c724208caf3c04c40d6f4a6ba1d0fcbfdc4a18f4358ced6d"},"schema_version":"1.0"},"canonical_sha256":"19c74642273ce15a3e9f5b94f9c6f05b5016443f58f0ca9ec4a3924a1b8e6617","source":{"kind":"arxiv","id":"2505.08073","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08073","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08073v2","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08073","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"DHDUMQRHHTQV","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"DHDUMQRHHTQVUPU7","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"DHDUMQRH","created_at":"2026-07-05T11:55:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DHDUMQRHHTQVUPU7LOKPTRXQLN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T21:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"875cfeec2ec973cb9f0c650d9d57007cb580160672836e1df467916247e0e28b","abstract_canon_sha256":"097c14600da37207c724208caf3c04c40d6f4a6ba1d0fcbfdc4a18f4358ced6d"},"schema_version":"1.0"},"canonical_sha256":"19c74642273ce15a3e9f5b94f9c6f05b5016443f58f0ca9ec4a3924a1b8e6617","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:19.250149Z","signature_b64":"+O2/jfNAMw+HWz7KDHgnvt5t3lwt0FWqObkpaEUzUKPBRnMf/n1pZ48gjU8nAURStLbW7C4KH1cVTJ1fiacOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19c74642273ce15a3e9f5b94f9c6f05b5016443f58f0ca9ec4a3924a1b8e6617","last_reissued_at":"2026-07-05T11:55:19.249728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:19.249728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08073","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qI+S5nQ2bYztGC74Di6xjtH0LzBg9T4bh1qXrPjFIDUadUWDb+q7XFMkSQxxvehZd0qD/zMoj5RyMdD/5DhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:46:56.107610Z"},"content_sha256":"fb7c26bbe5e273845001bc6899fa1c4919a34244f9c3d6880cfdd790bfa5dd84","schema_version":"1.0","event_id":"sha256:fb7c26bbe5e273845001bc6899fa1c4919a34244f9c3d6880cfdd790bfa5dd84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DHDUMQRHHTQVUPU7LOKPTRXQLN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explainable Reinforcement Learning Agents Using World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amal Alabdulkarim, Gennie Mansi, Madhuri Singh, Mark O. Riedl","submitted_at":"2025-05-12T21:18:31Z","abstract_excerpt":"Explainable AI (XAI) systems have been proposed to help people understand how AI systems produce outputs and behaviors. Explainable Reinforcement Learning (XRL) has an added complexity due to the temporal nature of sequential decision-making. Further, non-AI experts do not necessarily have the ability to alter an agent or its policy. We introduce a technique for using World Models to generate explanations for Model-Based Deep RL agents. World Models predict how the world will change when actions are performed, allowing for the generation of counterfactual trajectories. However, identifying wha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08073","kind":"arxiv","version":2},"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/2505.08073/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":"2026-07-05T11:55:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IEMUAQmD2b4BLhYuWb0CCGriCAv53OOou5RO4YTdH0Xai40cvnaThX1gsW0spGoqJ9ch3QMdsGxMA8LiJ0THBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:46:56.108162Z"},"content_sha256":"7b40210d011c08c24320ebc09a45c2aed1437b8f812f445ebd5c4d9e33197880","schema_version":"1.0","event_id":"sha256:7b40210d011c08c24320ebc09a45c2aed1437b8f812f445ebd5c4d9e33197880"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHDUMQRHHTQVUPU7LOKPTRXQLN/bundle.json","state_url":"https://pith.science/pith/DHDUMQRHHTQVUPU7LOKPTRXQLN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHDUMQRHHTQVUPU7LOKPTRXQLN/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":"2026-08-23T05:46:56Z","links":{"resolver":"https://pith.science/pith/DHDUMQRHHTQVUPU7LOKPTRXQLN","bundle":"https://pith.science/pith/DHDUMQRHHTQVUPU7LOKPTRXQLN/bundle.json","state":"https://pith.science/pith/DHDUMQRHHTQVUPU7LOKPTRXQLN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHDUMQRHHTQVUPU7LOKPTRXQLN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DHDUMQRHHTQVUPU7LOKPTRXQLN","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":"097c14600da37207c724208caf3c04c40d6f4a6ba1d0fcbfdc4a18f4358ced6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T21:18:31Z","title_canon_sha256":"875cfeec2ec973cb9f0c650d9d57007cb580160672836e1df467916247e0e28b"},"schema_version":"1.0","source":{"id":"2505.08073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08073","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08073v2","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08073","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"DHDUMQRHHTQV","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"DHDUMQRHHTQVUPU7","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"DHDUMQRH","created_at":"2026-07-05T11:55:19Z"}],"graph_snapshots":[{"event_id":"sha256:7b40210d011c08c24320ebc09a45c2aed1437b8f812f445ebd5c4d9e33197880","target":"graph","created_at":"2026-07-05T11:55:19Z","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/2505.08073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explainable AI (XAI) systems have been proposed to help people understand how AI systems produce outputs and behaviors. Explainable Reinforcement Learning (XRL) has an added complexity due to the temporal nature of sequential decision-making. Further, non-AI experts do not necessarily have the ability to alter an agent or its policy. We introduce a technique for using World Models to generate explanations for Model-Based Deep RL agents. World Models predict how the world will change when actions are performed, allowing for the generation of counterfactual trajectories. However, identifying wha","authors_text":"Amal Alabdulkarim, Gennie Mansi, Madhuri Singh, Mark O. Riedl","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08073","kind":"arxiv","version":2},"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:fb7c26bbe5e273845001bc6899fa1c4919a34244f9c3d6880cfdd790bfa5dd84","target":"record","created_at":"2026-07-05T11:55:19Z","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":"097c14600da37207c724208caf3c04c40d6f4a6ba1d0fcbfdc4a18f4358ced6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T21:18:31Z","title_canon_sha256":"875cfeec2ec973cb9f0c650d9d57007cb580160672836e1df467916247e0e28b"},"schema_version":"1.0","source":{"id":"2505.08073","kind":"arxiv","version":2}},"canonical_sha256":"19c74642273ce15a3e9f5b94f9c6f05b5016443f58f0ca9ec4a3924a1b8e6617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19c74642273ce15a3e9f5b94f9c6f05b5016443f58f0ca9ec4a3924a1b8e6617","first_computed_at":"2026-07-05T11:55:19.249728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:19.249728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+O2/jfNAMw+HWz7KDHgnvt5t3lwt0FWqObkpaEUzUKPBRnMf/n1pZ48gjU8nAURStLbW7C4KH1cVTJ1fiacOAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:19.250149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb7c26bbe5e273845001bc6899fa1c4919a34244f9c3d6880cfdd790bfa5dd84","sha256:7b40210d011c08c24320ebc09a45c2aed1437b8f812f445ebd5c4d9e33197880"],"state_sha256":"cdf265d0da293761b72bcc299792c92e80d70e5a4fe6beb03c913115958e3ea0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D24i+jN063j/C0CvSitrM73hJmUA3NUhZS7G5ZYhEnZdxLW/D0XyJxqHZcWKjobk9pb55979pJMZtEzun6V7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T05:46:56.113071Z","bundle_sha256":"50fbf8e254d77684cafeb5eef5f05b4b07bb376197ff878b9c98462199ba1916"}}