{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HRQF7SSZ4MLABR7FK66OPYE23C","short_pith_number":"pith:HRQF7SSZ","canonical_record":{"source":{"id":"2607.03385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-03T14:40:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e6792896a4b79293a8c424e3e392a67db8f1b080edd488d9ffa1318c46774528","abstract_canon_sha256":"4dfb63a6a40e879ebd6f7ebe444a17816d74788bfd210ece8096c9584286565a"},"schema_version":"1.0"},"canonical_sha256":"3c605fca59e31600c7e557bce7e09ad8930c2175d7fc4962d116346b0b3743a5","source":{"kind":"arxiv","id":"2607.03385","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03385","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03385v1","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03385","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"HRQF7SSZ4MLA","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"HRQF7SSZ4MLABR7F","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"HRQF7SSZ","created_at":"2026-07-07T02:17:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HRQF7SSZ4MLABR7FK66OPYE23C","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-03T14:40:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e6792896a4b79293a8c424e3e392a67db8f1b080edd488d9ffa1318c46774528","abstract_canon_sha256":"4dfb63a6a40e879ebd6f7ebe444a17816d74788bfd210ece8096c9584286565a"},"schema_version":"1.0"},"canonical_sha256":"3c605fca59e31600c7e557bce7e09ad8930c2175d7fc4962d116346b0b3743a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:40.678627Z","signature_b64":"7qINbpNil5AcJettMsHvjQrxssbefatWfSNnzOOOdAHTeTX/6KpWcdExkuCG1AEtK8iaY4DLoL+eI9dfxnaKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c605fca59e31600c7e557bce7e09ad8930c2175d7fc4962d116346b0b3743a5","last_reissued_at":"2026-07-07T02:17:40.677871Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:40.677871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03385","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":"2026-07-07T02:17:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rf9l20bmT0B+dE2XajHPUPre9afc6Lb1RyxjZU7y7SHIN2jRwbjZw3arkGM2eHMeq6bieXlhKZXOasYGnn1HAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:27:41.614356Z"},"content_sha256":"1ce6d8e8de95030922c4c599a6231465e40d121b570311eb07a157afda524eb6","schema_version":"1.0","event_id":"sha256:1ce6d8e8de95030922c4c599a6231465e40d121b570311eb07a157afda524eb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HRQF7SSZ4MLABR7FK66OPYE23C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Hierarchy of Policy Learning Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hamsa Bastani, Osbert Bastani, Shihan Chen","submitted_at":"2026-07-03T14:40:47Z","abstract_excerpt":"Policy learning has received substantial attention with the goal of learning policies from observational data for decision-making. A majority of work in this space has focused on developing algorithms for computing policies that minimize regret compared to the optimal policy. However, in many practical settings, there is insufficient data to obtain low regret. As a result, recent work has shifted attention to alternative objectives, most notably, studying whether it is possible to learn an improving policy that statistically significantly outperforms baseline policies. We argue that there is s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03385","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/2607.03385/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":"2026-07-07T02:17:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AtwQ7aKbtGFS1Cu+w2zzrzjn07V07kYEk7RkDA51/qzyfn/QFfPt7vxPtLH4101WL2aiH8Ft3BI6jPW6EyBuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:27:41.614881Z"},"content_sha256":"a89b524aeb8098a38e924cf9e1c28226f6ec27be4512a91dffbc6010c00629b9","schema_version":"1.0","event_id":"sha256:a89b524aeb8098a38e924cf9e1c28226f6ec27be4512a91dffbc6010c00629b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRQF7SSZ4MLABR7FK66OPYE23C/bundle.json","state_url":"https://pith.science/pith/HRQF7SSZ4MLABR7FK66OPYE23C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRQF7SSZ4MLABR7FK66OPYE23C/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":"2026-08-07T21:27:41Z","links":{"resolver":"https://pith.science/pith/HRQF7SSZ4MLABR7FK66OPYE23C","bundle":"https://pith.science/pith/HRQF7SSZ4MLABR7FK66OPYE23C/bundle.json","state":"https://pith.science/pith/HRQF7SSZ4MLABR7FK66OPYE23C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRQF7SSZ4MLABR7FK66OPYE23C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HRQF7SSZ4MLABR7FK66OPYE23C","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":"4dfb63a6a40e879ebd6f7ebe444a17816d74788bfd210ece8096c9584286565a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-03T14:40:47Z","title_canon_sha256":"e6792896a4b79293a8c424e3e392a67db8f1b080edd488d9ffa1318c46774528"},"schema_version":"1.0","source":{"id":"2607.03385","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03385","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03385v1","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03385","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"HRQF7SSZ4MLA","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"HRQF7SSZ4MLABR7F","created_at":"2026-07-07T02:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"HRQF7SSZ","created_at":"2026-07-07T02:17:40Z"}],"graph_snapshots":[{"event_id":"sha256:a89b524aeb8098a38e924cf9e1c28226f6ec27be4512a91dffbc6010c00629b9","target":"graph","created_at":"2026-07-07T02:17:40Z","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/2607.03385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy learning has received substantial attention with the goal of learning policies from observational data for decision-making. A majority of work in this space has focused on developing algorithms for computing policies that minimize regret compared to the optimal policy. However, in many practical settings, there is insufficient data to obtain low regret. As a result, recent work has shifted attention to alternative objectives, most notably, studying whether it is possible to learn an improving policy that statistically significantly outperforms baseline policies. We argue that there is s","authors_text":"Hamsa Bastani, Osbert Bastani, Shihan Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-03T14:40:47Z","title":"A Hierarchy of Policy Learning Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03385","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":"sha256:1ce6d8e8de95030922c4c599a6231465e40d121b570311eb07a157afda524eb6","target":"record","created_at":"2026-07-07T02:17:40Z","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":"4dfb63a6a40e879ebd6f7ebe444a17816d74788bfd210ece8096c9584286565a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-03T14:40:47Z","title_canon_sha256":"e6792896a4b79293a8c424e3e392a67db8f1b080edd488d9ffa1318c46774528"},"schema_version":"1.0","source":{"id":"2607.03385","kind":"arxiv","version":1}},"canonical_sha256":"3c605fca59e31600c7e557bce7e09ad8930c2175d7fc4962d116346b0b3743a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c605fca59e31600c7e557bce7e09ad8930c2175d7fc4962d116346b0b3743a5","first_computed_at":"2026-07-07T02:17:40.677871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:40.677871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7qINbpNil5AcJettMsHvjQrxssbefatWfSNnzOOOdAHTeTX/6KpWcdExkuCG1AEtK8iaY4DLoL+eI9dfxnaKBA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:40.678627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03385","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ce6d8e8de95030922c4c599a6231465e40d121b570311eb07a157afda524eb6","sha256:a89b524aeb8098a38e924cf9e1c28226f6ec27be4512a91dffbc6010c00629b9"],"state_sha256":"624af6a550e82cf6d1daff241fc7a8ea42c33aede5d0956f6ad5b9060283a8c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hg7qsZv0eIc89Fkt2P4a8ocJlhBgz1mgF7nxSZJXrI0Cy1VKK/GtcaijaXF4XrT7xKOjunhEX/7rTlZi5Bi/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:27:41.618957Z","bundle_sha256":"1c2222091da0fb16d16a8c70711cf1db58cb216d3f649975b06610d8fe171f91"}}