{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YZXSIO3UTEZMGLQ6VXFGDFLHDW","short_pith_number":"pith:YZXSIO3U","canonical_record":{"source":{"id":"2507.19725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T00:49:25Z","cross_cats_sorted":[],"title_canon_sha256":"03f9709f39d364fe4aaa8ba44bac09ef0946e56afd1ef3667644ffd7413799b2","abstract_canon_sha256":"e9c4f6d9434b0367b8674358b2501b241cb1dad4b7dc1057feb281221a99e83a"},"schema_version":"1.0"},"canonical_sha256":"c66f243b749932c32e1eadca6195671d9999c204316bb3b453091636f1d5306d","source":{"kind":"arxiv","id":"2507.19725","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19725","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19725v1","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19725","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"YZXSIO3UTEZM","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"pith_short_16","alias_value":"YZXSIO3UTEZMGLQ6","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"pith_short_8","alias_value":"YZXSIO3U","created_at":"2026-07-05T11:43:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YZXSIO3UTEZMGLQ6VXFGDFLHDW","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T00:49:25Z","cross_cats_sorted":[],"title_canon_sha256":"03f9709f39d364fe4aaa8ba44bac09ef0946e56afd1ef3667644ffd7413799b2","abstract_canon_sha256":"e9c4f6d9434b0367b8674358b2501b241cb1dad4b7dc1057feb281221a99e83a"},"schema_version":"1.0"},"canonical_sha256":"c66f243b749932c32e1eadca6195671d9999c204316bb3b453091636f1d5306d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:40.380365Z","signature_b64":"IzhzOxDVzCFgPJveQYLizMrlVIU1xSNfieT2LTKyQjkqaNG9FxghsMUX+uecLLjyfmpFhDmjAs3ojMBpErwACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c66f243b749932c32e1eadca6195671d9999c204316bb3b453091636f1d5306d","last_reissued_at":"2026-07-05T11:43:40.379857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:40.379857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19725","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":"2026-07-05T11:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pTKrL3m2e3wrwiSLOsYMbK0Kmo+1v6srSHn6CPQWDPVcU2deAxr1h1NgBD4D4jRwOpWOES2TKvySucVmqyPcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:41:16.536527Z"},"content_sha256":"67d5d2e145da5b77aa7a5e3a651f4525eaa6324df58ddb78718bada0b42d18b6","schema_version":"1.0","event_id":"sha256:67d5d2e145da5b77aa7a5e3a651f4525eaa6324df58ddb78718bada0b42d18b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YZXSIO3UTEZMGLQ6VXFGDFLHDW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Arnav Jhala, David L Roberts, Grant Forbes, Jianxun Wang, Leonardo Villalobos-Arias","submitted_at":"2025-07-26T00:49:25Z","abstract_excerpt":"Games are challenging for Reinforcement Learning~(RL) agents due to their reward-sparsity, as rewards are only obtainable after long sequences of deliberate actions. Intrinsic Motivation~(IM) methods -- which introduce exploration rewards -- are an effective solution to reward-sparsity. However, IM also causes an issue known as `reward hacking' where the agent optimizes for the new reward at the expense of properly playing the game. The larger problem is that reward hacking itself is largely unknown; there is no answer to whether, and to what extent, IM rewards change the behavior of RL agents"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19725","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/2507.19725/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":"2026-07-05T11:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hfuUgU/sXBVRWjQys3SNBKAmaONk8lOqNNh8K8YQAVsCa80o1mxvjEe8h0AZhnZpjvGyj8nhKZpoQ9s7GcABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:41:16.536933Z"},"content_sha256":"9d74abafa4ca0405604b89c147c80ea395c7e1f0bad0141c1b51014efd8839c4","schema_version":"1.0","event_id":"sha256:9d74abafa4ca0405604b89c147c80ea395c7e1f0bad0141c1b51014efd8839c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZXSIO3UTEZMGLQ6VXFGDFLHDW/bundle.json","state_url":"https://pith.science/pith/YZXSIO3UTEZMGLQ6VXFGDFLHDW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZXSIO3UTEZMGLQ6VXFGDFLHDW/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":"2026-08-07T12:41:16Z","links":{"resolver":"https://pith.science/pith/YZXSIO3UTEZMGLQ6VXFGDFLHDW","bundle":"https://pith.science/pith/YZXSIO3UTEZMGLQ6VXFGDFLHDW/bundle.json","state":"https://pith.science/pith/YZXSIO3UTEZMGLQ6VXFGDFLHDW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZXSIO3UTEZMGLQ6VXFGDFLHDW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YZXSIO3UTEZMGLQ6VXFGDFLHDW","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":"e9c4f6d9434b0367b8674358b2501b241cb1dad4b7dc1057feb281221a99e83a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T00:49:25Z","title_canon_sha256":"03f9709f39d364fe4aaa8ba44bac09ef0946e56afd1ef3667644ffd7413799b2"},"schema_version":"1.0","source":{"id":"2507.19725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19725","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19725v1","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19725","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"YZXSIO3UTEZM","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"pith_short_16","alias_value":"YZXSIO3UTEZMGLQ6","created_at":"2026-07-05T11:43:40Z"},{"alias_kind":"pith_short_8","alias_value":"YZXSIO3U","created_at":"2026-07-05T11:43:40Z"}],"graph_snapshots":[{"event_id":"sha256:9d74abafa4ca0405604b89c147c80ea395c7e1f0bad0141c1b51014efd8839c4","target":"graph","created_at":"2026-07-05T11:43:40Z","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/2507.19725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Games are challenging for Reinforcement Learning~(RL) agents due to their reward-sparsity, as rewards are only obtainable after long sequences of deliberate actions. Intrinsic Motivation~(IM) methods -- which introduce exploration rewards -- are an effective solution to reward-sparsity. However, IM also causes an issue known as `reward hacking' where the agent optimizes for the new reward at the expense of properly playing the game. The larger problem is that reward hacking itself is largely unknown; there is no answer to whether, and to what extent, IM rewards change the behavior of RL agents","authors_text":"Arnav Jhala, David L Roberts, Grant Forbes, Jianxun Wang, Leonardo Villalobos-Arias","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T00:49:25Z","title":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19725","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":"sha256:67d5d2e145da5b77aa7a5e3a651f4525eaa6324df58ddb78718bada0b42d18b6","target":"record","created_at":"2026-07-05T11:43:40Z","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":"e9c4f6d9434b0367b8674358b2501b241cb1dad4b7dc1057feb281221a99e83a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T00:49:25Z","title_canon_sha256":"03f9709f39d364fe4aaa8ba44bac09ef0946e56afd1ef3667644ffd7413799b2"},"schema_version":"1.0","source":{"id":"2507.19725","kind":"arxiv","version":1}},"canonical_sha256":"c66f243b749932c32e1eadca6195671d9999c204316bb3b453091636f1d5306d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c66f243b749932c32e1eadca6195671d9999c204316bb3b453091636f1d5306d","first_computed_at":"2026-07-05T11:43:40.379857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:40.379857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IzhzOxDVzCFgPJveQYLizMrlVIU1xSNfieT2LTKyQjkqaNG9FxghsMUX+uecLLjyfmpFhDmjAs3ojMBpErwACw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:40.380365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67d5d2e145da5b77aa7a5e3a651f4525eaa6324df58ddb78718bada0b42d18b6","sha256:9d74abafa4ca0405604b89c147c80ea395c7e1f0bad0141c1b51014efd8839c4"],"state_sha256":"6088c3390cd9312ad7eb2bf62e3203f9473ddd22493da62f1779ac3bbc3445dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDzd5AiiqAfdm4ZeXFWjuqrfqyyzn48D6UfXjDiqw8rZKgZwY78rZm7cLPmeCmHnEhkNPGdgMNY2Ebfe0gxxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:41:16.539626Z","bundle_sha256":"d85e1e05fa5b8f4cad89cea64fe4318507400e39a1d687f4b8d8c3c797bda438"}}