{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DBVE6DG6OS3TXJ5JTERE7PDW3L","short_pith_number":"pith:DBVE6DG6","canonical_record":{"source":{"id":"2608.08158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a92e24fb2d7b867c45897793d2aa3dee6d50e8cec7da2d9a6164d790387d3d39","abstract_canon_sha256":"b1fa4b4d2ef4cf0925e9eb18fb86ebee907f524a3acca5cf744988247a6e7027"},"schema_version":"1.0"},"canonical_sha256":"186a4f0cde74b73ba7a999224fbc76dad95ff739718431b925f24d9c8b5ee43b","source":{"kind":"arxiv","id":"2608.08158","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08158","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08158v1","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08158","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"DBVE6DG6OS3T","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"DBVE6DG6OS3TXJ5J","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"DBVE6DG6","created_at":"2026-08-11T01:21:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DBVE6DG6OS3TXJ5JTERE7PDW3L","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a92e24fb2d7b867c45897793d2aa3dee6d50e8cec7da2d9a6164d790387d3d39","abstract_canon_sha256":"b1fa4b4d2ef4cf0925e9eb18fb86ebee907f524a3acca5cf744988247a6e7027"},"schema_version":"1.0"},"canonical_sha256":"186a4f0cde74b73ba7a999224fbc76dad95ff739718431b925f24d9c8b5ee43b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:21:50.849820Z","signature_b64":"UgT9C1+qXs4dHHc0zZCtO1zKkrmjdxZybkw5ThyvBTVpL68AUt0ePxXaXb3o0alOe8CcLPh9ZZdOXMjfSa1OCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"186a4f0cde74b73ba7a999224fbc76dad95ff739718431b925f24d9c8b5ee43b","last_reissued_at":"2026-08-11T01:21:50.847359Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:21:50.847359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08158","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":"2026-08-11T01:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14odcDfu1BkeygvXJlIFtmC1aYcOrB8U3YRLUNcb/mu+rQUyHrBpc0sUdP++HJ4cvBF/mT8HB8VUDtCAItCkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:36:52.011761Z"},"content_sha256":"aaab9afba65a613dc9b44a8da6ea2ce01722acacec8b0a85393f3f4e6d74b9ce","schema_version":"1.0","event_id":"sha256:aaab9afba65a613dc9b44a8da6ea2ce01722acacec8b0a85393f3f4e6d74b9ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DBVE6DG6OS3TXJ5JTERE7PDW3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fouad Bahrpeyma","submitted_at":"2026-08-08T14:35:29Z","abstract_excerpt":"Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning. Reward shaping addresses these limitations by supplementing the task reward with an auxiliary signal that can accelerate learning while, in the classical setting, the original objective remains the evaluation criterion. Established theory guarantees safety for fixed shaping signals: potential-based reward shaping preserves optimal policies when the auxiliary term is the discounted difference of a time-invariant potential. In contemporary reinforcement learning systems, however, both th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08158","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/2608.08158/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":"2026-08-11T01:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQ4IlDd/xvo1X+DvScVIk5/Iej1Hqmzy5Njkue7QynA3e6KGJXbSTgYRVOvjSrQruHw8GpvJu7IAdVbXLCgwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:36:52.012389Z"},"content_sha256":"14e8b07c4ca61c1e743a939950add5a874e82c0f6a5f0634a5713ad7ded65e76","schema_version":"1.0","event_id":"sha256:14e8b07c4ca61c1e743a939950add5a874e82c0f6a5f0634a5713ad7ded65e76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBVE6DG6OS3TXJ5JTERE7PDW3L/bundle.json","state_url":"https://pith.science/pith/DBVE6DG6OS3TXJ5JTERE7PDW3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBVE6DG6OS3TXJ5JTERE7PDW3L/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":"2026-08-12T22:36:52Z","links":{"resolver":"https://pith.science/pith/DBVE6DG6OS3TXJ5JTERE7PDW3L","bundle":"https://pith.science/pith/DBVE6DG6OS3TXJ5JTERE7PDW3L/bundle.json","state":"https://pith.science/pith/DBVE6DG6OS3TXJ5JTERE7PDW3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBVE6DG6OS3TXJ5JTERE7PDW3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DBVE6DG6OS3TXJ5JTERE7PDW3L","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":"b1fa4b4d2ef4cf0925e9eb18fb86ebee907f524a3acca5cf744988247a6e7027","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","title_canon_sha256":"a92e24fb2d7b867c45897793d2aa3dee6d50e8cec7da2d9a6164d790387d3d39"},"schema_version":"1.0","source":{"id":"2608.08158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08158","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08158v1","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08158","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"DBVE6DG6OS3T","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"DBVE6DG6OS3TXJ5J","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"DBVE6DG6","created_at":"2026-08-11T01:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:14e8b07c4ca61c1e743a939950add5a874e82c0f6a5f0634a5713ad7ded65e76","target":"graph","created_at":"2026-08-11T01:21:50Z","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/2608.08158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning. Reward shaping addresses these limitations by supplementing the task reward with an auxiliary signal that can accelerate learning while, in the classical setting, the original objective remains the evaluation criterion. Established theory guarantees safety for fixed shaping signals: potential-based reward shaping preserves optimal policies when the auxiliary term is the discounted difference of a time-invariant potential. In contemporary reinforcement learning systems, however, both th","authors_text":"Fouad Bahrpeyma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","title":"A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08158","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:aaab9afba65a613dc9b44a8da6ea2ce01722acacec8b0a85393f3f4e6d74b9ce","target":"record","created_at":"2026-08-11T01:21:50Z","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":"b1fa4b4d2ef4cf0925e9eb18fb86ebee907f524a3acca5cf744988247a6e7027","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","title_canon_sha256":"a92e24fb2d7b867c45897793d2aa3dee6d50e8cec7da2d9a6164d790387d3d39"},"schema_version":"1.0","source":{"id":"2608.08158","kind":"arxiv","version":1}},"canonical_sha256":"186a4f0cde74b73ba7a999224fbc76dad95ff739718431b925f24d9c8b5ee43b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"186a4f0cde74b73ba7a999224fbc76dad95ff739718431b925f24d9c8b5ee43b","first_computed_at":"2026-08-11T01:21:50.847359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:21:50.847359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UgT9C1+qXs4dHHc0zZCtO1zKkrmjdxZybkw5ThyvBTVpL68AUt0ePxXaXb3o0alOe8CcLPh9ZZdOXMjfSa1OCw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:21:50.849820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaab9afba65a613dc9b44a8da6ea2ce01722acacec8b0a85393f3f4e6d74b9ce","sha256:14e8b07c4ca61c1e743a939950add5a874e82c0f6a5f0634a5713ad7ded65e76"],"state_sha256":"b9d277a0a5822bec7e8743e66e6760bafe82ac0a3734cffbe43150557ffceb49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nIZanaYhoHJ3vy3i+VIb5e1YHiZXh1dq0FNMZwlcpT4llQ7J9mj6AtoVP4uQ8+Iq1XTrV4R4wfYErsAtXPyMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:36:52.016517Z","bundle_sha256":"030e6510ea53f9779e33bd2acd91e5482cc4ce5f62f11cf3524a8e96f7fcca54"}}