{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KW6TJEV45U4A47T4TJ6ZEEE26H","short_pith_number":"pith:KW6TJEV4","canonical_record":{"source":{"id":"2505.08988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T21:58:25Z","cross_cats_sorted":[],"title_canon_sha256":"5fa323d208da4d441f52562bbfbe8b238c5f83b786fefb3826f2c910c5446bdf","abstract_canon_sha256":"394f471f272436f81767de272321fa19bc73cfeeecdc7ec549231a345e4a0552"},"schema_version":"1.0"},"canonical_sha256":"55bd3492bced380e7e7c9a7d92109af1caa7a73aab53947ecf2a15fd0520866b","source":{"kind":"arxiv","id":"2505.08988","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08988","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08988v1","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08988","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"KW6TJEV45U4A","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"KW6TJEV45U4A47T4","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"KW6TJEV4","created_at":"2026-07-05T11:02:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KW6TJEV45U4A47T4TJ6ZEEE26H","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T21:58:25Z","cross_cats_sorted":[],"title_canon_sha256":"5fa323d208da4d441f52562bbfbe8b238c5f83b786fefb3826f2c910c5446bdf","abstract_canon_sha256":"394f471f272436f81767de272321fa19bc73cfeeecdc7ec549231a345e4a0552"},"schema_version":"1.0"},"canonical_sha256":"55bd3492bced380e7e7c9a7d92109af1caa7a73aab53947ecf2a15fd0520866b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:48.326907Z","signature_b64":"c8E6ifSgkqRqODX3rJbhh+JDV6SoLGQD4flbDq74pMoA1oAu1SXnbNyLlviyTScUkwKx2g0G3RfWPDsoWbviBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55bd3492bced380e7e7c9a7d92109af1caa7a73aab53947ecf2a15fd0520866b","last_reissued_at":"2026-07-05T11:02:48.326506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:48.326506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08988","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":"2026-07-05T11:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WVs9SB0Bd1QQEPyRUjuWlhU59SRsx7fxvP+sy3ka9P6b0dGd673SM+kaZfYdGi9vgMMbjIFjbYlrjsrBSSDlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:10:15.388279Z"},"content_sha256":"65b5ee9d99eda760f095668e8e7bd5653f348adf7cf15f806beaaa50105625d9","schema_version":"1.0","event_id":"sha256:65b5ee9d99eda760f095668e8e7bd5653f348adf7cf15f806beaaa50105625d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KW6TJEV45U4A47T4TJ6ZEEE26H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization in Monitored Markov Decision Processes (Mon-MDPs)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Michael Bowling, Montaser Mohammedalamen","submitted_at":"2025-05-13T21:58:25Z","abstract_excerpt":"Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world scenarios, rewards are not always observable, which can be modeled as a monitored Markov decision process (Mon-MDP). Prior work on Mon-MDPs have been limited to simple, tabular cases, restricting their applicability to real-world problems. This work explores Mon-MDPs using function approximation (FA) and investigates the challenges involved. We show that combining f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08988","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/2505.08988/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":"2026-07-05T11:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7yhneyxZV/jwwbOzfBLbh8TBlB/OHGMdjezBYpn6jRBNknuboCPNkXj4rT3k3qOY2A9ZJ/wjKaXaf90ZQI+sAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:10:15.388806Z"},"content_sha256":"341e56be525370212b675449dd6c1ba749efcd18afa65c86c395700cb14f5af8","schema_version":"1.0","event_id":"sha256:341e56be525370212b675449dd6c1ba749efcd18afa65c86c395700cb14f5af8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/bundle.json","state_url":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/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":"2026-08-17T04:10:15Z","links":{"resolver":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H","bundle":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/bundle.json","state":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KW6TJEV45U4A47T4TJ6ZEEE26H","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":"394f471f272436f81767de272321fa19bc73cfeeecdc7ec549231a345e4a0552","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T21:58:25Z","title_canon_sha256":"5fa323d208da4d441f52562bbfbe8b238c5f83b786fefb3826f2c910c5446bdf"},"schema_version":"1.0","source":{"id":"2505.08988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08988","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08988v1","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08988","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"KW6TJEV45U4A","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"KW6TJEV45U4A47T4","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"KW6TJEV4","created_at":"2026-07-05T11:02:48Z"}],"graph_snapshots":[{"event_id":"sha256:341e56be525370212b675449dd6c1ba749efcd18afa65c86c395700cb14f5af8","target":"graph","created_at":"2026-07-05T11:02:48Z","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/2505.08988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world scenarios, rewards are not always observable, which can be modeled as a monitored Markov decision process (Mon-MDP). Prior work on Mon-MDPs have been limited to simple, tabular cases, restricting their applicability to real-world problems. This work explores Mon-MDPs using function approximation (FA) and investigates the challenges involved. We show that combining f","authors_text":"Michael Bowling, Montaser Mohammedalamen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T21:58:25Z","title":"Generalization in Monitored Markov Decision Processes (Mon-MDPs)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08988","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":"sha256:65b5ee9d99eda760f095668e8e7bd5653f348adf7cf15f806beaaa50105625d9","target":"record","created_at":"2026-07-05T11:02:48Z","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":"394f471f272436f81767de272321fa19bc73cfeeecdc7ec549231a345e4a0552","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T21:58:25Z","title_canon_sha256":"5fa323d208da4d441f52562bbfbe8b238c5f83b786fefb3826f2c910c5446bdf"},"schema_version":"1.0","source":{"id":"2505.08988","kind":"arxiv","version":1}},"canonical_sha256":"55bd3492bced380e7e7c9a7d92109af1caa7a73aab53947ecf2a15fd0520866b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55bd3492bced380e7e7c9a7d92109af1caa7a73aab53947ecf2a15fd0520866b","first_computed_at":"2026-07-05T11:02:48.326506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:48.326506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8E6ifSgkqRqODX3rJbhh+JDV6SoLGQD4flbDq74pMoA1oAu1SXnbNyLlviyTScUkwKx2g0G3RfWPDsoWbviBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:48.326907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65b5ee9d99eda760f095668e8e7bd5653f348adf7cf15f806beaaa50105625d9","sha256:341e56be525370212b675449dd6c1ba749efcd18afa65c86c395700cb14f5af8"],"state_sha256":"f4d1b356fa2074ad7ea3639c45738619fab78246f0f09c39235846effdb698e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFXdLxTpIodq8xmQIgknFOog9wiiDcOw//67WDB5ZweMeRUP4h7y5I25eGtpwCoZ2qwvKO+vOVnSGShBTRaFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:10:15.392342Z","bundle_sha256":"4a3d6d83a55008cce1f4b821ebe78303f346898924e8366ba856d36a7554b8e2"}}