{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TUF7WCOG72N5T7XECCSPR2XWEO","short_pith_number":"pith:TUF7WCOG","canonical_record":{"source":{"id":"1903.08738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T21:01:22Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"f32354d3d6a08122ec85fe7cf86e77587e1df65e70e469060b308da099d1ebdb","abstract_canon_sha256":"7c9938a879e8515c100d8fb7ad496d46d452c7f3e6549c66734309166448766d"},"schema_version":"1.0"},"canonical_sha256":"9d0bfb09c6fe9bd9fee410a4f8eaf6239dae4eddbedc2e99a78795e86f092f25","source":{"kind":"arxiv","id":"1903.08738","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.08738","created_at":"2026-05-17T23:50:44Z"},{"alias_kind":"arxiv_version","alias_value":"1903.08738v1","created_at":"2026-05-17T23:50:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08738","created_at":"2026-05-17T23:50:44Z"},{"alias_kind":"pith_short_12","alias_value":"TUF7WCOG72N5","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TUF7WCOG72N5T7XE","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TUF7WCOG","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TUF7WCOG72N5T7XECCSPR2XWEO","target":"record","payload":{"canonical_record":{"source":{"id":"1903.08738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T21:01:22Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"f32354d3d6a08122ec85fe7cf86e77587e1df65e70e469060b308da099d1ebdb","abstract_canon_sha256":"7c9938a879e8515c100d8fb7ad496d46d452c7f3e6549c66734309166448766d"},"schema_version":"1.0"},"canonical_sha256":"9d0bfb09c6fe9bd9fee410a4f8eaf6239dae4eddbedc2e99a78795e86f092f25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:44.066662Z","signature_b64":"CZsDnHXjSBFHPKD0NcimmvXRpb5Dh2DXAVucF8IH6xyPhrNoIs9hFlDDbw7HRc/hM8saJ4/22UEmycIUXpP+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d0bfb09c6fe9bd9fee410a4f8eaf6239dae4eddbedc2e99a78795e86f092f25","last_reissued_at":"2026-05-17T23:50:44.066138Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:44.066138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.08738","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":"2026-05-17T23:50:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Ygk41uiiZgXyxPsRlPZf76RJ6nDda0U0V1tJVS3Jv+I/sCTuKgu/BM/dETfO6R5l5NNzJKzH11269/bTEaLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:56:49.877909Z"},"content_sha256":"f27913baa281cc55a4108cfcf1256bfcf576c050d6de7c26ca482bd4fc7529f9","schema_version":"1.0","event_id":"sha256:f27913baa281cc55a4108cfcf1256bfcf576c050d6de7c26ca482bd4fc7529f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TUF7WCOG72N5T7XECCSPR2XWEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Batch Policy Learning under Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cameron Voloshin, Hoang M. Le, Yisong Yue","submitted_at":"2019-03-20T21:01:22Z","abstract_excerpt":"When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We thus study the problem of batch policy learning under multiple constraints, and offer a systematic solution. We first propose a flexible meta-algorithm that admits any batch reinforcement learning and online learning procedure as subroutines. We then present a specific algorithmic instantiation and provide performance guarantees for the main objective and all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08738","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":""},"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":"2026-05-17T23:50:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/RR87Hze2dPjgd5gvsBLUgDN6IrUqUMbmVxy4oxs1YQTFU6mR6QDCwFcRwmfUgS9cDXhmyI8iac2XgWBUOlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:56:49.878603Z"},"content_sha256":"dde37c03d9d9cd5be2abc72486119fa758c482ab7db3be21af2cf08eee89bf49","schema_version":"1.0","event_id":"sha256:dde37c03d9d9cd5be2abc72486119fa758c482ab7db3be21af2cf08eee89bf49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/bundle.json","state_url":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUF7WCOG72N5T7XECCSPR2XWEO/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":"2026-06-10T22:56:49Z","links":{"resolver":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO","bundle":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/bundle.json","state":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUF7WCOG72N5T7XECCSPR2XWEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TUF7WCOG72N5T7XECCSPR2XWEO","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":"7c9938a879e8515c100d8fb7ad496d46d452c7f3e6549c66734309166448766d","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T21:01:22Z","title_canon_sha256":"f32354d3d6a08122ec85fe7cf86e77587e1df65e70e469060b308da099d1ebdb"},"schema_version":"1.0","source":{"id":"1903.08738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.08738","created_at":"2026-05-17T23:50:44Z"},{"alias_kind":"arxiv_version","alias_value":"1903.08738v1","created_at":"2026-05-17T23:50:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08738","created_at":"2026-05-17T23:50:44Z"},{"alias_kind":"pith_short_12","alias_value":"TUF7WCOG72N5","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TUF7WCOG72N5T7XE","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TUF7WCOG","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:dde37c03d9d9cd5be2abc72486119fa758c482ab7db3be21af2cf08eee89bf49","target":"graph","created_at":"2026-05-17T23:50:44Z","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"},"paper":{"abstract_excerpt":"When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We thus study the problem of batch policy learning under multiple constraints, and offer a systematic solution. We first propose a flexible meta-algorithm that admits any batch reinforcement learning and online learning procedure as subroutines. We then present a specific algorithmic instantiation and provide performance guarantees for the main objective and all","authors_text":"Cameron Voloshin, Hoang M. Le, Yisong Yue","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T21:01:22Z","title":"Batch Policy Learning under Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08738","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:f27913baa281cc55a4108cfcf1256bfcf576c050d6de7c26ca482bd4fc7529f9","target":"record","created_at":"2026-05-17T23:50:44Z","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":"7c9938a879e8515c100d8fb7ad496d46d452c7f3e6549c66734309166448766d","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T21:01:22Z","title_canon_sha256":"f32354d3d6a08122ec85fe7cf86e77587e1df65e70e469060b308da099d1ebdb"},"schema_version":"1.0","source":{"id":"1903.08738","kind":"arxiv","version":1}},"canonical_sha256":"9d0bfb09c6fe9bd9fee410a4f8eaf6239dae4eddbedc2e99a78795e86f092f25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d0bfb09c6fe9bd9fee410a4f8eaf6239dae4eddbedc2e99a78795e86f092f25","first_computed_at":"2026-05-17T23:50:44.066138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:44.066138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CZsDnHXjSBFHPKD0NcimmvXRpb5Dh2DXAVucF8IH6xyPhrNoIs9hFlDDbw7HRc/hM8saJ4/22UEmycIUXpP+Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:44.066662Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.08738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f27913baa281cc55a4108cfcf1256bfcf576c050d6de7c26ca482bd4fc7529f9","sha256:dde37c03d9d9cd5be2abc72486119fa758c482ab7db3be21af2cf08eee89bf49"],"state_sha256":"2ccf8d9849e4fb9d72f8ac9aea77508eca6226f4fc22d698de2c6be72e75f2c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nMelRe0L7mwcxxzi7Dlmxkzg9I6BClUfXgH7C958/MBE+e4bkridIbEdTcshbI7Qm1v+pG3X0JVCYYvjCrjBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T22:56:49.883284Z","bundle_sha256":"735ec55f56299687495a48607e903bbff825c0b6ec68cbb6ce050cfae8ac4474"}}