{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TENF43URHYGGJMGC4ORSTK4XQ2","short_pith_number":"pith:TENF43UR","canonical_record":{"source":{"id":"2502.19920","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T09:42:23Z","cross_cats_sorted":[],"title_canon_sha256":"fff1f3f4663af9864e335325f0c49b13db1f361a27f2d7b72d2f12e67d2255ee","abstract_canon_sha256":"b6373bcdcfe679bcf77c7dc8532832a48544631042399c844577de24d61dddaa"},"schema_version":"1.0"},"canonical_sha256":"991a5e6e913e0c64b0c2e3a329ab9786822f9b658c0b837c22ee90fdcebed452","source":{"kind":"arxiv","id":"2502.19920","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19920","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19920v2","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19920","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"TENF43URHYGG","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"TENF43URHYGGJMGC","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"TENF43UR","created_at":"2026-07-05T10:28:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TENF43URHYGGJMGC4ORSTK4XQ2","target":"record","payload":{"canonical_record":{"source":{"id":"2502.19920","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T09:42:23Z","cross_cats_sorted":[],"title_canon_sha256":"fff1f3f4663af9864e335325f0c49b13db1f361a27f2d7b72d2f12e67d2255ee","abstract_canon_sha256":"b6373bcdcfe679bcf77c7dc8532832a48544631042399c844577de24d61dddaa"},"schema_version":"1.0"},"canonical_sha256":"991a5e6e913e0c64b0c2e3a329ab9786822f9b658c0b837c22ee90fdcebed452","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:37.240528Z","signature_b64":"902TgmN+JDd8FfM6Nc8DC/TsIqeULShF7XzY6zr6lirhMynSA5+1zqZ2xYNWgcWZe2ZkLloRLymo7PCTafmwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"991a5e6e913e0c64b0c2e3a329ab9786822f9b658c0b837c22ee90fdcebed452","last_reissued_at":"2026-07-05T10:28:37.240028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:37.240028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.19920","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":"2026-07-05T10:28:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGCKB/zWjEbVIVBo9dfQ2obg5gXhfL9zDuPbwl6H/GIrFAFI3wIq7dOJPkl/eByl99DGfZzphbvD+0WU8JvJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:59:49.473813Z"},"content_sha256":"526d4c7f3fe3b84e16c22f2a3675f799e135576c7c94b7513f4627ea5ad62115","schema_version":"1.0","event_id":"sha256:526d4c7f3fe3b84e16c22f2a3675f799e135576c7c94b7513f4627ea5ad62115"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TENF43URHYGGJMGC4ORSTK4XQ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pokemon Red via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Addis, David Rubinstein, Frank Zimmer, Marco Pleines, Mike Preuss, Peter Whidden","submitted_at":"2025-02-27T09:42:23Z","abstract_excerpt":"Pok\\'emon Red, a classic Game Boy JRPG, presents significant challenges as a testbed for agents, including multi-tasking, long horizons of tens of thousands of steps, hard exploration, and a vast array of potential policies. We introduce a simplistic environment and a Deep Reinforcement Learning (DRL) training methodology, demonstrating a baseline agent that completes an initial segment of the game up to completing Cerulean City. Our experiments include various ablations that reveal vulnerabilities in reward shaping, where agents exploit specific reward signals. We also discuss limitations and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19920","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/2502.19920/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":"2026-07-05T10:28:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AnsCbRReENz74n3saxK87DBh0J0bPoQ6rcjdiq4X1XvsaQ/h+OAm1Uz46U1jSNnrzNMKArdDwhILE1MDP7KnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:59:49.474344Z"},"content_sha256":"a66746086856409893c95302b5e5992fd7d18f6a0509f848ba473ee7a1abc662","schema_version":"1.0","event_id":"sha256:a66746086856409893c95302b5e5992fd7d18f6a0509f848ba473ee7a1abc662"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TENF43URHYGGJMGC4ORSTK4XQ2/bundle.json","state_url":"https://pith.science/pith/TENF43URHYGGJMGC4ORSTK4XQ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TENF43URHYGGJMGC4ORSTK4XQ2/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":"2026-08-09T12:59:49Z","links":{"resolver":"https://pith.science/pith/TENF43URHYGGJMGC4ORSTK4XQ2","bundle":"https://pith.science/pith/TENF43URHYGGJMGC4ORSTK4XQ2/bundle.json","state":"https://pith.science/pith/TENF43URHYGGJMGC4ORSTK4XQ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TENF43URHYGGJMGC4ORSTK4XQ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TENF43URHYGGJMGC4ORSTK4XQ2","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":"b6373bcdcfe679bcf77c7dc8532832a48544631042399c844577de24d61dddaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T09:42:23Z","title_canon_sha256":"fff1f3f4663af9864e335325f0c49b13db1f361a27f2d7b72d2f12e67d2255ee"},"schema_version":"1.0","source":{"id":"2502.19920","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19920","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19920v2","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19920","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"TENF43URHYGG","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"TENF43URHYGGJMGC","created_at":"2026-07-05T10:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"TENF43UR","created_at":"2026-07-05T10:28:37Z"}],"graph_snapshots":[{"event_id":"sha256:a66746086856409893c95302b5e5992fd7d18f6a0509f848ba473ee7a1abc662","target":"graph","created_at":"2026-07-05T10:28:37Z","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/2502.19920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pok\\'emon Red, a classic Game Boy JRPG, presents significant challenges as a testbed for agents, including multi-tasking, long horizons of tens of thousands of steps, hard exploration, and a vast array of potential policies. We introduce a simplistic environment and a Deep Reinforcement Learning (DRL) training methodology, demonstrating a baseline agent that completes an initial segment of the game up to completing Cerulean City. Our experiments include various ablations that reveal vulnerabilities in reward shaping, where agents exploit specific reward signals. We also discuss limitations and","authors_text":"Daniel Addis, David Rubinstein, Frank Zimmer, Marco Pleines, Mike Preuss, Peter Whidden","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T09:42:23Z","title":"Pokemon Red via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19920","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":"sha256:526d4c7f3fe3b84e16c22f2a3675f799e135576c7c94b7513f4627ea5ad62115","target":"record","created_at":"2026-07-05T10:28:37Z","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":"b6373bcdcfe679bcf77c7dc8532832a48544631042399c844577de24d61dddaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T09:42:23Z","title_canon_sha256":"fff1f3f4663af9864e335325f0c49b13db1f361a27f2d7b72d2f12e67d2255ee"},"schema_version":"1.0","source":{"id":"2502.19920","kind":"arxiv","version":2}},"canonical_sha256":"991a5e6e913e0c64b0c2e3a329ab9786822f9b658c0b837c22ee90fdcebed452","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"991a5e6e913e0c64b0c2e3a329ab9786822f9b658c0b837c22ee90fdcebed452","first_computed_at":"2026-07-05T10:28:37.240028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:37.240028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"902TgmN+JDd8FfM6Nc8DC/TsIqeULShF7XzY6zr6lirhMynSA5+1zqZ2xYNWgcWZe2ZkLloRLymo7PCTafmwBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:37.240528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19920","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:526d4c7f3fe3b84e16c22f2a3675f799e135576c7c94b7513f4627ea5ad62115","sha256:a66746086856409893c95302b5e5992fd7d18f6a0509f848ba473ee7a1abc662"],"state_sha256":"d0084e21cc569d7f3832c36e2a67306281a1886266e6db69d16bff3a65f91974"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yrtw2S3Mp2MAZFuhbja+PruatZq+pS2RiIOqBpWsnL9uGqt5c09Ezhd+K32ZpSJadfr0E8fW6zSwZhjvHx8ACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:59:49.478616Z","bundle_sha256":"c67d07f31ae6d716c68ff7a7e897eb10c8b78d39a17bb29efd60bffd97a33e33"}}