{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NVLNYISW7N7Y7B7VKUKPRX24H7","short_pith_number":"pith:NVLNYISW","canonical_record":{"source":{"id":"2307.06328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T17:47:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e6f477f7aa1a435d4164e688ba90a1b860226504010e629b9367564cb39da49","abstract_canon_sha256":"06619e0841b2dc0d665dec7001c50cf55c617d39b2918e5dab00324b1c52154d"},"schema_version":"1.0"},"canonical_sha256":"6d56dc2256fb7f8f87f55514f8df5c3ff837ebf1a3684db4978b345a03b87dc1","source":{"kind":"arxiv","id":"2307.06328","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06328","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06328v2","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06328","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"NVLNYISW7N7Y","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"NVLNYISW7N7Y7B7V","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"NVLNYISW","created_at":"2026-07-05T08:21:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NVLNYISW7N7Y7B7VKUKPRX24H7","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T17:47:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e6f477f7aa1a435d4164e688ba90a1b860226504010e629b9367564cb39da49","abstract_canon_sha256":"06619e0841b2dc0d665dec7001c50cf55c617d39b2918e5dab00324b1c52154d"},"schema_version":"1.0"},"canonical_sha256":"6d56dc2256fb7f8f87f55514f8df5c3ff837ebf1a3684db4978b345a03b87dc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:05.719766Z","signature_b64":"lU2wJnRaj/2Evo+TzCMVXU70LyHsNXBxbDgzSLv0SDgc+NRaT758keODMfxJMvYPCLg8U3SKEQvyMNJlvSD9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d56dc2256fb7f8f87f55514f8df5c3ff837ebf1a3684db4978b345a03b87dc1","last_reissued_at":"2026-07-05T08:21:05.719228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:05.719228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06328","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":"2026-07-05T08:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qY+V7GV4phfBPOu7B9Ca1uluZHiuDVAL2tn5165OwlC2tt9227iozJ8+7ne0GypVMDm/faKIHs7kWiWJd0fCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:07:54.145781Z"},"content_sha256":"0b4b38c4f27f5efecd2a480c48bfbc2973d7427a6738e9679d0d5e718355cd63","schema_version":"1.0","event_id":"sha256:0b4b38c4f27f5efecd2a480c48bfbc2973d7427a6738e9679d0d5e718355cd63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NVLNYISW7N7Y7B7VKUKPRX24H7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Budgeting Counterfactual for Offline RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Pratik Chaudhari, Rasool Fakoor, Yao Liu","submitted_at":"2023-07-12T17:47:35Z","abstract_excerpt":"The main challenge of offline reinforcement learning, where data is limited, arises from a sequence of counterfactual reasoning dilemmas within the realm of potential actions: What if we were to choose a different course of action? These circumstances frequently give rise to extrapolation errors, which tend to accumulate exponentially with the problem horizon. Hence, it becomes crucial to acknowledge that not all decision steps are equally important to the final outcome, and to budget the number of counterfactual decisions a policy make in order to control the extrapolation. Contrary to existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06328","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/2307.06328/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":"2026-07-05T08:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B29mFllGkGlH3L/RK2eHznQpw0A7vyMn5CAChYFWpAfG6GvbjFE361SBDgzhmLDfRKv7Ihtvxb9wo775kcczBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:07:54.146327Z"},"content_sha256":"037b724737aa034c5081f6afa7116ae35848ee06e104b14688825f46890dc809","schema_version":"1.0","event_id":"sha256:037b724737aa034c5081f6afa7116ae35848ee06e104b14688825f46890dc809"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVLNYISW7N7Y7B7VKUKPRX24H7/bundle.json","state_url":"https://pith.science/pith/NVLNYISW7N7Y7B7VKUKPRX24H7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVLNYISW7N7Y7B7VKUKPRX24H7/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":"2026-08-20T15:07:54Z","links":{"resolver":"https://pith.science/pith/NVLNYISW7N7Y7B7VKUKPRX24H7","bundle":"https://pith.science/pith/NVLNYISW7N7Y7B7VKUKPRX24H7/bundle.json","state":"https://pith.science/pith/NVLNYISW7N7Y7B7VKUKPRX24H7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVLNYISW7N7Y7B7VKUKPRX24H7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NVLNYISW7N7Y7B7VKUKPRX24H7","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":"06619e0841b2dc0d665dec7001c50cf55c617d39b2918e5dab00324b1c52154d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T17:47:35Z","title_canon_sha256":"6e6f477f7aa1a435d4164e688ba90a1b860226504010e629b9367564cb39da49"},"schema_version":"1.0","source":{"id":"2307.06328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06328","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06328v2","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06328","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"NVLNYISW7N7Y","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"NVLNYISW7N7Y7B7V","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"NVLNYISW","created_at":"2026-07-05T08:21:05Z"}],"graph_snapshots":[{"event_id":"sha256:037b724737aa034c5081f6afa7116ae35848ee06e104b14688825f46890dc809","target":"graph","created_at":"2026-07-05T08:21:05Z","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/2307.06328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The main challenge of offline reinforcement learning, where data is limited, arises from a sequence of counterfactual reasoning dilemmas within the realm of potential actions: What if we were to choose a different course of action? These circumstances frequently give rise to extrapolation errors, which tend to accumulate exponentially with the problem horizon. Hence, it becomes crucial to acknowledge that not all decision steps are equally important to the final outcome, and to budget the number of counterfactual decisions a policy make in order to control the extrapolation. Contrary to existi","authors_text":"Pratik Chaudhari, Rasool Fakoor, Yao Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T17:47:35Z","title":"Budgeting Counterfactual for Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06328","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":"sha256:0b4b38c4f27f5efecd2a480c48bfbc2973d7427a6738e9679d0d5e718355cd63","target":"record","created_at":"2026-07-05T08:21:05Z","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":"06619e0841b2dc0d665dec7001c50cf55c617d39b2918e5dab00324b1c52154d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T17:47:35Z","title_canon_sha256":"6e6f477f7aa1a435d4164e688ba90a1b860226504010e629b9367564cb39da49"},"schema_version":"1.0","source":{"id":"2307.06328","kind":"arxiv","version":2}},"canonical_sha256":"6d56dc2256fb7f8f87f55514f8df5c3ff837ebf1a3684db4978b345a03b87dc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d56dc2256fb7f8f87f55514f8df5c3ff837ebf1a3684db4978b345a03b87dc1","first_computed_at":"2026-07-05T08:21:05.719228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:05.719228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lU2wJnRaj/2Evo+TzCMVXU70LyHsNXBxbDgzSLv0SDgc+NRaT758keODMfxJMvYPCLg8U3SKEQvyMNJlvSD9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:05.719766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b4b38c4f27f5efecd2a480c48bfbc2973d7427a6738e9679d0d5e718355cd63","sha256:037b724737aa034c5081f6afa7116ae35848ee06e104b14688825f46890dc809"],"state_sha256":"83f74b79575ac3ab025871f1cf662b99191b3e364c3fb2570f05c5c9a0738de1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqJvjqtBOaFZ7b/z6iWN+TL5h7C5Bm083sTFdwbGyuXqNJiu3eL+WoIV/J2Cb/I3rR4j9U35CgK2+dZtrlCRAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T15:07:54.149781Z","bundle_sha256":"ab799aec846895f795b4051dec0be42bfec44440bd9c5b1ceacc340af2e866fd"}}