{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GO5IWCPYSBC7DKYRVBGLU7EP2E","short_pith_number":"pith:GO5IWCPY","canonical_record":{"source":{"id":"2306.00321","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:36:06Z","cross_cats_sorted":[],"title_canon_sha256":"f8684ed62b740b1c2c9df77dc2f3a69fc0515c5d21dd99ec83985778c0589077","abstract_canon_sha256":"65860651b2f6ebf3086b0e506b18dd2e475e7e7bac7926b842fe474ca438b4e2"},"schema_version":"1.0"},"canonical_sha256":"33ba8b09f89045f1ab11a84cba7c8fd10f61c445bf90a1eb28fa4797af6afa29","source":{"kind":"arxiv","id":"2306.00321","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00321","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00321v2","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00321","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_12","alias_value":"GO5IWCPYSBC7","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_16","alias_value":"GO5IWCPYSBC7DKYR","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_8","alias_value":"GO5IWCPY","created_at":"2026-07-05T07:56:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GO5IWCPYSBC7DKYRVBGLU7EP2E","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00321","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:36:06Z","cross_cats_sorted":[],"title_canon_sha256":"f8684ed62b740b1c2c9df77dc2f3a69fc0515c5d21dd99ec83985778c0589077","abstract_canon_sha256":"65860651b2f6ebf3086b0e506b18dd2e475e7e7bac7926b842fe474ca438b4e2"},"schema_version":"1.0"},"canonical_sha256":"33ba8b09f89045f1ab11a84cba7c8fd10f61c445bf90a1eb28fa4797af6afa29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:48.892688Z","signature_b64":"T5VaJVEhvImOyhLjmghM3eJmR1JAEGmU4VK3LI9uu1kbADrLPe12XOciAcp3TCuOOduIXN2Rm7wriHFr9U7rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33ba8b09f89045f1ab11a84cba7c8fd10f61c445bf90a1eb28fa4797af6afa29","last_reissued_at":"2026-07-05T07:56:48.892204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:48.892204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00321","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":"2026-07-05T07:56:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+OAmVRLIyZVaY2QRe5X+qQm50xG2stFfblCBghLX5PTHt551bfUVMwCpF5WYA1zhpbSXhiydc/Z7i5aWN/vDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:10:26.746267Z"},"content_sha256":"74cc047527166368afa39d486442ad13116f6d6dbf312659127c1a6be4809f88","schema_version":"1.0","event_id":"sha256:74cc047527166368afa39d486442ad13116f6d6dbf312659127c1a6be4809f88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GO5IWCPYSBC7DKYRVBGLU7EP2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Offline RL by Blending Heuristics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Andrey Kolobov, Ching-An Cheng, Sinong Geng","submitted_at":"2023-06-01T03:36:06Z","abstract_excerpt":"We propose Heuristic Blending (HUBL), a simple performance-improving technique for a broad class of offline RL algorithms based on value bootstrapping. HUBL modifies the Bellman operators used in these algorithms, partially replacing the bootstrapped values with heuristic ones that are estimated with Monte-Carlo returns. For trajectories with higher returns, HUBL relies more on the heuristic values and less on bootstrapping; otherwise, it leans more heavily on bootstrapping. HUBL is very easy to combine with many existing offline RL implementations by relabeling the offline datasets with adjus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00321","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/2306.00321/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":"2026-07-05T07:56:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tp32eDY0yvk/y0+d8fPA+hfRdOn/aSSYGpLhryd75V5zEX6jKK3IitHnuRY2C9NNpPa32PcAgiZWgTGuTI+YBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:10:26.746750Z"},"content_sha256":"a7aaaa8dc7da39fd71bb425e41dd4835916ba0c9a02f790fb706b3d159be50f1","schema_version":"1.0","event_id":"sha256:a7aaaa8dc7da39fd71bb425e41dd4835916ba0c9a02f790fb706b3d159be50f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GO5IWCPYSBC7DKYRVBGLU7EP2E/bundle.json","state_url":"https://pith.science/pith/GO5IWCPYSBC7DKYRVBGLU7EP2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GO5IWCPYSBC7DKYRVBGLU7EP2E/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":"2026-08-08T20:10:26Z","links":{"resolver":"https://pith.science/pith/GO5IWCPYSBC7DKYRVBGLU7EP2E","bundle":"https://pith.science/pith/GO5IWCPYSBC7DKYRVBGLU7EP2E/bundle.json","state":"https://pith.science/pith/GO5IWCPYSBC7DKYRVBGLU7EP2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GO5IWCPYSBC7DKYRVBGLU7EP2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GO5IWCPYSBC7DKYRVBGLU7EP2E","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":"65860651b2f6ebf3086b0e506b18dd2e475e7e7bac7926b842fe474ca438b4e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:36:06Z","title_canon_sha256":"f8684ed62b740b1c2c9df77dc2f3a69fc0515c5d21dd99ec83985778c0589077"},"schema_version":"1.0","source":{"id":"2306.00321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00321","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00321v2","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00321","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_12","alias_value":"GO5IWCPYSBC7","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_16","alias_value":"GO5IWCPYSBC7DKYR","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_8","alias_value":"GO5IWCPY","created_at":"2026-07-05T07:56:48Z"}],"graph_snapshots":[{"event_id":"sha256:a7aaaa8dc7da39fd71bb425e41dd4835916ba0c9a02f790fb706b3d159be50f1","target":"graph","created_at":"2026-07-05T07:56:48Z","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/2306.00321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Heuristic Blending (HUBL), a simple performance-improving technique for a broad class of offline RL algorithms based on value bootstrapping. HUBL modifies the Bellman operators used in these algorithms, partially replacing the bootstrapped values with heuristic ones that are estimated with Monte-Carlo returns. For trajectories with higher returns, HUBL relies more on the heuristic values and less on bootstrapping; otherwise, it leans more heavily on bootstrapping. HUBL is very easy to combine with many existing offline RL implementations by relabeling the offline datasets with adjus","authors_text":"Aldo Pacchiano, Andrey Kolobov, Ching-An Cheng, Sinong Geng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:36:06Z","title":"Improving Offline RL by Blending Heuristics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00321","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":"sha256:74cc047527166368afa39d486442ad13116f6d6dbf312659127c1a6be4809f88","target":"record","created_at":"2026-07-05T07:56:48Z","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":"65860651b2f6ebf3086b0e506b18dd2e475e7e7bac7926b842fe474ca438b4e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:36:06Z","title_canon_sha256":"f8684ed62b740b1c2c9df77dc2f3a69fc0515c5d21dd99ec83985778c0589077"},"schema_version":"1.0","source":{"id":"2306.00321","kind":"arxiv","version":2}},"canonical_sha256":"33ba8b09f89045f1ab11a84cba7c8fd10f61c445bf90a1eb28fa4797af6afa29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33ba8b09f89045f1ab11a84cba7c8fd10f61c445bf90a1eb28fa4797af6afa29","first_computed_at":"2026-07-05T07:56:48.892204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:48.892204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T5VaJVEhvImOyhLjmghM3eJmR1JAEGmU4VK3LI9uu1kbADrLPe12XOciAcp3TCuOOduIXN2Rm7wriHFr9U7rAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:48.892688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74cc047527166368afa39d486442ad13116f6d6dbf312659127c1a6be4809f88","sha256:a7aaaa8dc7da39fd71bb425e41dd4835916ba0c9a02f790fb706b3d159be50f1"],"state_sha256":"482aa6f3e46f2df6b6fd484ae152479eb7a645b39db16303bd94e796e21c215d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4li7Db0EQKpRBThzqdmyD6tavZQpzkDHSbDyUr35jVJpNynuGwYtdDB864d7c6k3PYgyo9mFCciPm7udK9syBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:10:26.750222Z","bundle_sha256":"0dbeaef1fbf8b2d12f5dae0bab1449d93501e6fb74e0a201cf8f66d7fa8a196b"}}