{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AP45VC5IUSDC76GTCCZ2LKOTOW","short_pith_number":"pith:AP45VC5I","canonical_record":{"source":{"id":"2412.07177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:22:11Z","cross_cats_sorted":[],"title_canon_sha256":"667e609d69503f6150a2e61947815de1a5acffbdfa81e56ad5f5bd02fc33b607","abstract_canon_sha256":"33ac6d6e06b4f51f585b24a815c268ea9b24e0f1e8976a255c0b176af6190d13"},"schema_version":"1.0"},"canonical_sha256":"03f9da8ba8a4862ff8d310b3a5a9d375b955432f363acd411beeac2b50108ed3","source":{"kind":"arxiv","id":"2412.07177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07177","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07177v1","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07177","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"AP45VC5IUSDC","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"AP45VC5IUSDC76GT","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"AP45VC5I","created_at":"2026-07-05T09:47:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AP45VC5IUSDC76GTCCZ2LKOTOW","target":"record","payload":{"canonical_record":{"source":{"id":"2412.07177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:22:11Z","cross_cats_sorted":[],"title_canon_sha256":"667e609d69503f6150a2e61947815de1a5acffbdfa81e56ad5f5bd02fc33b607","abstract_canon_sha256":"33ac6d6e06b4f51f585b24a815c268ea9b24e0f1e8976a255c0b176af6190d13"},"schema_version":"1.0"},"canonical_sha256":"03f9da8ba8a4862ff8d310b3a5a9d375b955432f363acd411beeac2b50108ed3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:05.237767Z","signature_b64":"sZj/Q8chn6HnQXjvGU0thmUH7XrfdPpp6mr0AR6Bg/1ZbOG+TxX/Blpxl53dL4FL/eJfs9+YWutP+LjjUNiFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03f9da8ba8a4862ff8d310b3a5a9d375b955432f363acd411beeac2b50108ed3","last_reissued_at":"2026-07-05T09:47:05.237371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:05.237371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.07177","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":"2026-07-05T09:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIoWoc7z+3vrWm+HuGXg96/tw5BGEuD/caSBjZdtqMtL7r2TqD40wOekDa4sz8DV9SArmKvCejBobUXDL7vjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:55:47.606476Z"},"content_sha256":"c31ce6f9d2af18e60219d971b8f8e55d8f1501517042c0e2780773431b158146","schema_version":"1.0","event_id":"sha256:c31ce6f9d2af18e60219d971b8f8e55d8f1501517042c0e2780773431b158146"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AP45VC5IUSDC76GTCCZ2LKOTOW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Reward Specification in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Julien Roy","submitted_at":"2024-12-10T04:22:11Z","abstract_excerpt":"In the last decade, Deep Reinforcement Learning has evolved into a powerful tool for complex sequential decision-making problems. It combines deep learning's proficiency in processing rich input signals with reinforcement learning's adaptability across diverse control tasks. At its core, an RL agent seeks to maximize its cumulative reward, enabling AI algorithms to uncover novel solutions previously unknown to experts. However, this focus on reward maximization also introduces a significant difficulty: improper reward specification can result in unexpected, misaligned agent behavior and ineffi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07177","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/2412.07177/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":"2026-07-05T09:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sareGBrUjc4c2EtSHd8+6P1ISJOaDdtU+7Qa5n9TISzI3iEdbA+gx7iFFOc8X/ImL86CUImraUEgN8eLs79bDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:55:47.607266Z"},"content_sha256":"dbe740dddf36c9e8d9f701b04271eafa2636c9645dc64f761e56418adcf2feb0","schema_version":"1.0","event_id":"sha256:dbe740dddf36c9e8d9f701b04271eafa2636c9645dc64f761e56418adcf2feb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AP45VC5IUSDC76GTCCZ2LKOTOW/bundle.json","state_url":"https://pith.science/pith/AP45VC5IUSDC76GTCCZ2LKOTOW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AP45VC5IUSDC76GTCCZ2LKOTOW/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":"2026-08-12T11:55:47Z","links":{"resolver":"https://pith.science/pith/AP45VC5IUSDC76GTCCZ2LKOTOW","bundle":"https://pith.science/pith/AP45VC5IUSDC76GTCCZ2LKOTOW/bundle.json","state":"https://pith.science/pith/AP45VC5IUSDC76GTCCZ2LKOTOW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AP45VC5IUSDC76GTCCZ2LKOTOW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AP45VC5IUSDC76GTCCZ2LKOTOW","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":"33ac6d6e06b4f51f585b24a815c268ea9b24e0f1e8976a255c0b176af6190d13","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:22:11Z","title_canon_sha256":"667e609d69503f6150a2e61947815de1a5acffbdfa81e56ad5f5bd02fc33b607"},"schema_version":"1.0","source":{"id":"2412.07177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07177","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07177v1","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07177","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"AP45VC5IUSDC","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"AP45VC5IUSDC76GT","created_at":"2026-07-05T09:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"AP45VC5I","created_at":"2026-07-05T09:47:05Z"}],"graph_snapshots":[{"event_id":"sha256:dbe740dddf36c9e8d9f701b04271eafa2636c9645dc64f761e56418adcf2feb0","target":"graph","created_at":"2026-07-05T09:47:05Z","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/2412.07177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the last decade, Deep Reinforcement Learning has evolved into a powerful tool for complex sequential decision-making problems. It combines deep learning's proficiency in processing rich input signals with reinforcement learning's adaptability across diverse control tasks. At its core, an RL agent seeks to maximize its cumulative reward, enabling AI algorithms to uncover novel solutions previously unknown to experts. However, this focus on reward maximization also introduces a significant difficulty: improper reward specification can result in unexpected, misaligned agent behavior and ineffi","authors_text":"Julien Roy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:22:11Z","title":"Effective Reward Specification in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07177","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:c31ce6f9d2af18e60219d971b8f8e55d8f1501517042c0e2780773431b158146","target":"record","created_at":"2026-07-05T09:47:05Z","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":"33ac6d6e06b4f51f585b24a815c268ea9b24e0f1e8976a255c0b176af6190d13","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:22:11Z","title_canon_sha256":"667e609d69503f6150a2e61947815de1a5acffbdfa81e56ad5f5bd02fc33b607"},"schema_version":"1.0","source":{"id":"2412.07177","kind":"arxiv","version":1}},"canonical_sha256":"03f9da8ba8a4862ff8d310b3a5a9d375b955432f363acd411beeac2b50108ed3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03f9da8ba8a4862ff8d310b3a5a9d375b955432f363acd411beeac2b50108ed3","first_computed_at":"2026-07-05T09:47:05.237371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:05.237371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sZj/Q8chn6HnQXjvGU0thmUH7XrfdPpp6mr0AR6Bg/1ZbOG+TxX/Blpxl53dL4FL/eJfs9+YWutP+LjjUNiFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:05.237767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c31ce6f9d2af18e60219d971b8f8e55d8f1501517042c0e2780773431b158146","sha256:dbe740dddf36c9e8d9f701b04271eafa2636c9645dc64f761e56418adcf2feb0"],"state_sha256":"8b39537610922d612984e0a2f6d12d25fda49285f7371da97981d38a84d6ee0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tBRFINcxS2kddOfEGOuCxZts9aRd5Nwtnygvrli5PNRqHJXUiHty2y+0PpjAi8nly3uj/bG3JLJpbnSnK9CDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T11:55:47.614536Z","bundle_sha256":"4c450314f1b96338acbd298bb343e008e162c624751493734f644d6dc75263d8"}}