{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VXCCAW7IRTJXHRO4XJBL27KOEG","short_pith_number":"pith:VXCCAW7I","canonical_record":{"source":{"id":"2409.05358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"468fb9473bf0a823ea8a31130eaec02fb07a6e9935d116bab1e3b3c29a403598","abstract_canon_sha256":"fbd8475711d78bb834e80e7fd70dcf96dac2dfefae6e1ab5cfe82cc5b30331bc"},"schema_version":"1.0"},"canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","source":{"kind":"arxiv","id":"2409.05358","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05358","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05358v2","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05358","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"VXCCAW7IRTJX","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"VXCCAW7IRTJXHRO4","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"VXCCAW7I","created_at":"2026-07-05T10:37:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VXCCAW7IRTJXHRO4XJBL27KOEG","target":"record","payload":{"canonical_record":{"source":{"id":"2409.05358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"468fb9473bf0a823ea8a31130eaec02fb07a6e9935d116bab1e3b3c29a403598","abstract_canon_sha256":"fbd8475711d78bb834e80e7fd70dcf96dac2dfefae6e1ab5cfe82cc5b30331bc"},"schema_version":"1.0"},"canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:32.653278Z","signature_b64":"Zp8VRbkM3Uc+TOgQ7kCphGz7UhrsQjdajzHmMLvH/2P0R7x8J9driFgTdR5DSK3dDXye0qA8Xqg3S3ovt1ZnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","last_reissued_at":"2026-07-05T10:37:32.652721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:32.652721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.05358","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":"2026-07-05T10:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GslL0mwHCQq8gkZqbVa+l2qBIT8ZYf4WfubQpGaMBgeWvXDpgedzMoCUYxxL/d7pLCr0gZYITo5ripQ3I6hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:11:34.336622Z"},"content_sha256":"cfa0afb84be8041dc53b71e22a2f12c9ec998b5deff4e907ed3c261ffd3283ae","schema_version":"1.0","event_id":"sha256:cfa0afb84be8041dc53b71e22a2f12c9ec998b5deff4e907ed3c261ffd3283ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VXCCAW7IRTJXHRO4XJBL27KOEG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aly Lidayan, Michael Dennis, Stuart Russell","submitted_at":"2024-09-09T06:39:56Z","abstract_excerpt":"Intrinsic motivation and reward shaping guide reinforcement learning (RL) agents by adding pseudo-rewards, which can lead to useful emergent behaviors. However, they can also encourage counterproductive exploits, e.g., fixation with noisy TV screens. Here we provide a theoretical model which anticipates these behaviors, and provides broad criteria under which adverse effects can be bounded. We characterize all pseudo-rewards as reward shaping in Bayes-Adaptive Markov Decision Processes (BAMDPs), which formulates the problem of learning in MDPs as an MDP over the agent's knowledge. Optimal expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05358","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/2409.05358/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":"2026-07-05T10:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8P2NtOsUhxfLtnIboTnGn1WUuGwUwvtq8CWiUWh+TVzIy7QjgvD3a//PuxnEgVMSFKemzT1xUaUE2mGn9bs8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:11:34.337129Z"},"content_sha256":"b64d48d23225e1865af6f43b8ada2fb71fdbb4c0803e6fb689fd70c5bb11ddf8","schema_version":"1.0","event_id":"sha256:b64d48d23225e1865af6f43b8ada2fb71fdbb4c0803e6fb689fd70c5bb11ddf8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/bundle.json","state_url":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/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":"2026-08-15T16:11:34Z","links":{"resolver":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG","bundle":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/bundle.json","state":"https://pith.science/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXCCAW7IRTJXHRO4XJBL27KOEG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VXCCAW7IRTJXHRO4XJBL27KOEG","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":"fbd8475711d78bb834e80e7fd70dcf96dac2dfefae6e1ab5cfe82cc5b30331bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","title_canon_sha256":"468fb9473bf0a823ea8a31130eaec02fb07a6e9935d116bab1e3b3c29a403598"},"schema_version":"1.0","source":{"id":"2409.05358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05358","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05358v2","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05358","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"VXCCAW7IRTJX","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"VXCCAW7IRTJXHRO4","created_at":"2026-07-05T10:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"VXCCAW7I","created_at":"2026-07-05T10:37:32Z"}],"graph_snapshots":[{"event_id":"sha256:b64d48d23225e1865af6f43b8ada2fb71fdbb4c0803e6fb689fd70c5bb11ddf8","target":"graph","created_at":"2026-07-05T10:37:32Z","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/2409.05358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intrinsic motivation and reward shaping guide reinforcement learning (RL) agents by adding pseudo-rewards, which can lead to useful emergent behaviors. However, they can also encourage counterproductive exploits, e.g., fixation with noisy TV screens. Here we provide a theoretical model which anticipates these behaviors, and provides broad criteria under which adverse effects can be bounded. We characterize all pseudo-rewards as reward shaping in Bayes-Adaptive Markov Decision Processes (BAMDPs), which formulates the problem of learning in MDPs as an MDP over the agent's knowledge. Optimal expl","authors_text":"Aly Lidayan, Michael Dennis, Stuart Russell","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05358","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:cfa0afb84be8041dc53b71e22a2f12c9ec998b5deff4e907ed3c261ffd3283ae","target":"record","created_at":"2026-07-05T10:37:32Z","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":"fbd8475711d78bb834e80e7fd70dcf96dac2dfefae6e1ab5cfe82cc5b30331bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T06:39:56Z","title_canon_sha256":"468fb9473bf0a823ea8a31130eaec02fb07a6e9935d116bab1e3b3c29a403598"},"schema_version":"1.0","source":{"id":"2409.05358","kind":"arxiv","version":2}},"canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adc4205be88cd373c5dcba42bd7d4e2184699a090204b80e4b69af312e553060","first_computed_at":"2026-07-05T10:37:32.652721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:32.652721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zp8VRbkM3Uc+TOgQ7kCphGz7UhrsQjdajzHmMLvH/2P0R7x8J9driFgTdR5DSK3dDXye0qA8Xqg3S3ovt1ZnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:32.653278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfa0afb84be8041dc53b71e22a2f12c9ec998b5deff4e907ed3c261ffd3283ae","sha256:b64d48d23225e1865af6f43b8ada2fb71fdbb4c0803e6fb689fd70c5bb11ddf8"],"state_sha256":"1d83b83327919ed90f0865bd01af4f4912846bb813a351b8e2f96f7dd9c86c86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0d5hEvzKBtIMzUnzu9HL+5vqwDhp9tZX4WH+O4ulEobahPRPoEebSyPJ0XUR49qUw9MSoqZBZ7s69svMf8bXBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:11:34.341182Z","bundle_sha256":"813309c19f674069eae827424a670ecc857b2055465de529ec20ca7836abf772"}}