{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RRYNIMFSCLIWSHM2YPBGGLKYND","short_pith_number":"pith:RRYNIMFS","canonical_record":{"source":{"id":"2501.00989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T00:40:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebee948d9f3d427172e62993ab6e3a7cb35d7424a1dac983c51809eb0f43d566","abstract_canon_sha256":"e2e79e052137bffa43a31c53af1e3ab67d81155bd6b04f43fb77ac5682f6e9d8"},"schema_version":"1.0"},"canonical_sha256":"8c70d430b212d1691d9ac3c2632d5868dd84e6540de3fd7d8adbc77dcc8f0264","source":{"kind":"arxiv","id":"2501.00989","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00989","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00989v2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00989","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"RRYNIMFSCLIW","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"RRYNIMFSCLIWSHM2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"RRYNIMFS","created_at":"2026-07-05T11:42:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RRYNIMFSCLIWSHM2YPBGGLKYND","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T00:40:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebee948d9f3d427172e62993ab6e3a7cb35d7424a1dac983c51809eb0f43d566","abstract_canon_sha256":"e2e79e052137bffa43a31c53af1e3ab67d81155bd6b04f43fb77ac5682f6e9d8"},"schema_version":"1.0"},"canonical_sha256":"8c70d430b212d1691d9ac3c2632d5868dd84e6540de3fd7d8adbc77dcc8f0264","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:53.004261Z","signature_b64":"DCVac7wfX0obT8loWE+R1N3VbHi1BUmfaTwjP0aV3Cmyi6FTAo1WkjHs4J2YEhmuVg18qHN1UueHSF4cnrHnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c70d430b212d1691d9ac3c2632d5868dd84e6540de3fd7d8adbc77dcc8f0264","last_reissued_at":"2026-07-05T11:42:53.003870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:53.003870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00989","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":"2026-07-05T11:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/cd7g5FNQLc4/aNGJDbJobczI4rPyiEFPJnM0obqoTsTfwYHbwnm/FntuS15JPFqYyqP2JnAHQK71/pzv7+2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:40:27.639203Z"},"content_sha256":"3f092fe0fe7a25ce1b3db4fed213b1b3e81fa5267c2603047019e8452787d895","schema_version":"1.0","event_id":"sha256:3f092fe0fe7a25ce1b3db4fed213b1b3e81fa5267c2603047019e8452787d895"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RRYNIMFSCLIWSHM2YPBGGLKYND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bootstrapped Reward Shaping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jacob Adamczyk, Rahul V. Kulkarni, Stas Tiomkin, Volodymyr Makarenko","submitted_at":"2025-01-02T00:40:55Z","abstract_excerpt":"In reinforcement learning, especially in sparse-reward domains, many environment steps are required to observe reward information. In order to increase the frequency of such observations, \"potential-based reward shaping\" (PBRS) has been proposed as a method of providing a more dense reward signal while leaving the optimal policy invariant. However, the required \"potential function\" must be carefully designed with task-dependent knowledge to not deter training performance. In this work, we propose a \"bootstrapped\" method of reward shaping, termed BSRS, in which the agent's current estimate of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00989","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/2501.00989/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":"2026-07-05T11:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swkLRrAPJvoaXf8tIB8AWk4ww7Q+ftGjzj5kubiPvr5GQiIHUV8D3A08kVro+WA+/DbkSP54sJVZpiBKmtxRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:40:27.639728Z"},"content_sha256":"a8f1700721d0f2e92cf1cbb8d4256d8ba94aa0dc7546355ca4270259910d2c7d","schema_version":"1.0","event_id":"sha256:a8f1700721d0f2e92cf1cbb8d4256d8ba94aa0dc7546355ca4270259910d2c7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRYNIMFSCLIWSHM2YPBGGLKYND/bundle.json","state_url":"https://pith.science/pith/RRYNIMFSCLIWSHM2YPBGGLKYND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRYNIMFSCLIWSHM2YPBGGLKYND/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":"2026-08-21T16:40:27Z","links":{"resolver":"https://pith.science/pith/RRYNIMFSCLIWSHM2YPBGGLKYND","bundle":"https://pith.science/pith/RRYNIMFSCLIWSHM2YPBGGLKYND/bundle.json","state":"https://pith.science/pith/RRYNIMFSCLIWSHM2YPBGGLKYND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRYNIMFSCLIWSHM2YPBGGLKYND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RRYNIMFSCLIWSHM2YPBGGLKYND","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":"e2e79e052137bffa43a31c53af1e3ab67d81155bd6b04f43fb77ac5682f6e9d8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T00:40:55Z","title_canon_sha256":"ebee948d9f3d427172e62993ab6e3a7cb35d7424a1dac983c51809eb0f43d566"},"schema_version":"1.0","source":{"id":"2501.00989","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00989","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00989v2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00989","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"RRYNIMFSCLIW","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"RRYNIMFSCLIWSHM2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"RRYNIMFS","created_at":"2026-07-05T11:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:a8f1700721d0f2e92cf1cbb8d4256d8ba94aa0dc7546355ca4270259910d2c7d","target":"graph","created_at":"2026-07-05T11:42:53Z","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/2501.00989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, especially in sparse-reward domains, many environment steps are required to observe reward information. In order to increase the frequency of such observations, \"potential-based reward shaping\" (PBRS) has been proposed as a method of providing a more dense reward signal while leaving the optimal policy invariant. However, the required \"potential function\" must be carefully designed with task-dependent knowledge to not deter training performance. In this work, we propose a \"bootstrapped\" method of reward shaping, termed BSRS, in which the agent's current estimate of t","authors_text":"Jacob Adamczyk, Rahul V. Kulkarni, Stas Tiomkin, Volodymyr Makarenko","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T00:40:55Z","title":"Bootstrapped Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00989","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":"sha256:3f092fe0fe7a25ce1b3db4fed213b1b3e81fa5267c2603047019e8452787d895","target":"record","created_at":"2026-07-05T11:42:53Z","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":"e2e79e052137bffa43a31c53af1e3ab67d81155bd6b04f43fb77ac5682f6e9d8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T00:40:55Z","title_canon_sha256":"ebee948d9f3d427172e62993ab6e3a7cb35d7424a1dac983c51809eb0f43d566"},"schema_version":"1.0","source":{"id":"2501.00989","kind":"arxiv","version":2}},"canonical_sha256":"8c70d430b212d1691d9ac3c2632d5868dd84e6540de3fd7d8adbc77dcc8f0264","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c70d430b212d1691d9ac3c2632d5868dd84e6540de3fd7d8adbc77dcc8f0264","first_computed_at":"2026-07-05T11:42:53.003870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:53.003870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DCVac7wfX0obT8loWE+R1N3VbHi1BUmfaTwjP0aV3Cmyi6FTAo1WkjHs4J2YEhmuVg18qHN1UueHSF4cnrHnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:53.004261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00989","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f092fe0fe7a25ce1b3db4fed213b1b3e81fa5267c2603047019e8452787d895","sha256:a8f1700721d0f2e92cf1cbb8d4256d8ba94aa0dc7546355ca4270259910d2c7d"],"state_sha256":"216fd8feddd64f3b2625f3060d7c68c6000dd0e87605efb778d41de22203a5c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xAjHN/nxd/jQSK3ZdK1akqsxxyoFoKVu/v5TkdTFkO5Qt9BxRwPI+hNFt1t0nnQjDo5cIxr+Ybvj7gZJugqlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T16:40:27.645435Z","bundle_sha256":"1a84e031ef51d132c4579a81689e19ec074a7e385b6eaf974c6707f4d0fbc7b9"}}