{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5P2NUIIRZ7XDZ7V6WS3JRM2IVK","short_pith_number":"pith:5P2NUIIR","canonical_record":{"source":{"id":"2404.16399","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T08:22:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"263f15a727a5900ae7d078777abe75f74ec4e31b2dd39a3feb4c751533c5eca0","abstract_canon_sha256":"13d2e0b27982a9d787f72d9349bead2af39205fb36d378d307106a48654f3a3e"},"schema_version":"1.0"},"canonical_sha256":"ebf4da2111cfee3cfebeb4b698b348aa894644907e43f1b5f36550c9dbd64cce","source":{"kind":"arxiv","id":"2404.16399","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16399","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16399v2","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16399","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"5P2NUIIRZ7XD","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"5P2NUIIRZ7XDZ7V6","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"5P2NUIIR","created_at":"2026-07-05T08:49:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5P2NUIIRZ7XDZ7V6WS3JRM2IVK","target":"record","payload":{"canonical_record":{"source":{"id":"2404.16399","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T08:22:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"263f15a727a5900ae7d078777abe75f74ec4e31b2dd39a3feb4c751533c5eca0","abstract_canon_sha256":"13d2e0b27982a9d787f72d9349bead2af39205fb36d378d307106a48654f3a3e"},"schema_version":"1.0"},"canonical_sha256":"ebf4da2111cfee3cfebeb4b698b348aa894644907e43f1b5f36550c9dbd64cce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:09.963806Z","signature_b64":"QgrBB/c0f4ynlBFeIxhNd+KvRZ1N8hS9DZTZlACYKn9HMDg8b9rVws0VVwDS8pJrmQeRQFBk/AWF46tWs+2mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf4da2111cfee3cfebeb4b698b348aa894644907e43f1b5f36550c9dbd64cce","last_reissued_at":"2026-07-05T08:49:09.963327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:09.963327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.16399","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":"2026-07-05T08:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yh+mDI9gXuqiNTWU33IuENcP6mDl12XAjFCJFvis+F9wVpn3lpCTp/J30XXrqtTDQWXB6FO0vRMwwt1m5LB/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:34:23.741926Z"},"content_sha256":"5dc7590cd461da7ddfed5b235874bef3e80768a5a53cff9dc9f243c4144fcfe1","schema_version":"1.0","event_id":"sha256:5dc7590cd461da7ddfed5b235874bef3e80768a5a53cff9dc9f243c4144fcfe1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5P2NUIIRZ7XDZ7V6WS3JRM2IVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Padmanaba Srinivasan, William Knottenbelt","submitted_at":"2024-04-25T08:22:47Z","abstract_excerpt":"Offline reinforcement learning (RL) algorithms are applied to learn performant, well-generalizing policies when provided with a static dataset of interactions. Many recent approaches to offline RL have seen substantial success, but with one key caveat: they demand substantial per-dataset hyperparameter tuning to achieve reported performance, which requires policy rollouts in the environment to evaluate; this can rapidly become cumbersome. Furthermore, substantial tuning requirements can hamper the adoption of these algorithms in practical domains. In this paper, we present TD3 with Behavioral "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16399","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/2404.16399/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":"2026-07-05T08:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+BO47LGIdRAJW58qD9RlgVqbLvjHfW1uqWOkdZamsfRRHiarmexmUaeOhI9fBihzUrJcGR6gf0ZS78dpy16RDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:34:23.742814Z"},"content_sha256":"d4ee917c20f69472a188ab65d350574b5a5bf4443be69a80d59607bbf7811a1c","schema_version":"1.0","event_id":"sha256:d4ee917c20f69472a188ab65d350574b5a5bf4443be69a80d59607bbf7811a1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/bundle.json","state_url":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/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":"2026-08-04T08:34:23Z","links":{"resolver":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK","bundle":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/bundle.json","state":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5P2NUIIRZ7XDZ7V6WS3JRM2IVK","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":"13d2e0b27982a9d787f72d9349bead2af39205fb36d378d307106a48654f3a3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T08:22:47Z","title_canon_sha256":"263f15a727a5900ae7d078777abe75f74ec4e31b2dd39a3feb4c751533c5eca0"},"schema_version":"1.0","source":{"id":"2404.16399","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16399","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16399v2","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16399","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"5P2NUIIRZ7XD","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"5P2NUIIRZ7XDZ7V6","created_at":"2026-07-05T08:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"5P2NUIIR","created_at":"2026-07-05T08:49:09Z"}],"graph_snapshots":[{"event_id":"sha256:d4ee917c20f69472a188ab65d350574b5a5bf4443be69a80d59607bbf7811a1c","target":"graph","created_at":"2026-07-05T08:49:09Z","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/2404.16399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) algorithms are applied to learn performant, well-generalizing policies when provided with a static dataset of interactions. Many recent approaches to offline RL have seen substantial success, but with one key caveat: they demand substantial per-dataset hyperparameter tuning to achieve reported performance, which requires policy rollouts in the environment to evaluate; this can rapidly become cumbersome. Furthermore, substantial tuning requirements can hamper the adoption of these algorithms in practical domains. In this paper, we present TD3 with Behavioral ","authors_text":"Padmanaba Srinivasan, William Knottenbelt","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T08:22:47Z","title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16399","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":"sha256:5dc7590cd461da7ddfed5b235874bef3e80768a5a53cff9dc9f243c4144fcfe1","target":"record","created_at":"2026-07-05T08:49:09Z","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":"13d2e0b27982a9d787f72d9349bead2af39205fb36d378d307106a48654f3a3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T08:22:47Z","title_canon_sha256":"263f15a727a5900ae7d078777abe75f74ec4e31b2dd39a3feb4c751533c5eca0"},"schema_version":"1.0","source":{"id":"2404.16399","kind":"arxiv","version":2}},"canonical_sha256":"ebf4da2111cfee3cfebeb4b698b348aa894644907e43f1b5f36550c9dbd64cce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebf4da2111cfee3cfebeb4b698b348aa894644907e43f1b5f36550c9dbd64cce","first_computed_at":"2026-07-05T08:49:09.963327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:09.963327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QgrBB/c0f4ynlBFeIxhNd+KvRZ1N8hS9DZTZlACYKn9HMDg8b9rVws0VVwDS8pJrmQeRQFBk/AWF46tWs+2mDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:09.963806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16399","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dc7590cd461da7ddfed5b235874bef3e80768a5a53cff9dc9f243c4144fcfe1","sha256:d4ee917c20f69472a188ab65d350574b5a5bf4443be69a80d59607bbf7811a1c"],"state_sha256":"f59f817db21d52514d067279abd231682939415f889df3721931456a4b06b17f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k08huSD/JPOjyjk0hKevY5OxfipNBl+JmwpOSMtuSZLaHmmPsp6wbPyLa+FqxnDeb681ZRHMOIaqpvLpuDNZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:34:23.747814Z","bundle_sha256":"cfa9cca164dbc2ea1d1742006c704a7eef9fc9402fa52224188a011f14782754"}}