{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6DVF5ESVWDWELBENJ6CJT3OXJT","short_pith_number":"pith:6DVF5ESV","canonical_record":{"source":{"id":"2106.09973","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T07:54:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a2055776c4f1b93acd8f7a70aa4060f73d718fd17b06a54175fa69230f50d65e","abstract_canon_sha256":"4b232d416a297a8d930233a48783402d2bbc0dca68ac5dc28a6208428b2dba82"},"schema_version":"1.0"},"canonical_sha256":"f0ea5e9255b0ec45848d4f8499edd74cc2aa1d209ca0cf2b61bffe018688a0fd","source":{"kind":"arxiv","id":"2106.09973","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09973","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09973v3","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09973","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"pith_short_12","alias_value":"6DVF5ESVWDWE","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"pith_short_16","alias_value":"6DVF5ESVWDWELBEN","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"pith_short_8","alias_value":"6DVF5ESV","created_at":"2026-07-05T06:27:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6DVF5ESVWDWELBENJ6CJT3OXJT","target":"record","payload":{"canonical_record":{"source":{"id":"2106.09973","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T07:54:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a2055776c4f1b93acd8f7a70aa4060f73d718fd17b06a54175fa69230f50d65e","abstract_canon_sha256":"4b232d416a297a8d930233a48783402d2bbc0dca68ac5dc28a6208428b2dba82"},"schema_version":"1.0"},"canonical_sha256":"f0ea5e9255b0ec45848d4f8499edd74cc2aa1d209ca0cf2b61bffe018688a0fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:37.302082Z","signature_b64":"mAqMCmE6DO5/6qIMmlpgxVig6+HjtYvYSNZdodjmXGA8B4mou1l5rnIB7SqZJ68YJQvgWlkqhfYOVhgwrd4VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ea5e9255b0ec45848d4f8499edd74cc2aa1d209ca0cf2b61bffe018688a0fd","last_reissued_at":"2026-07-05T06:27:37.301583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:37.301583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.09973","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:27:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjJlMq0TW3RskUHCjBJMkOI/3DWoqjUYOQfFqoSMpHZEkV6WHlZUAZWoQKYX7w+lvnC3aXncQxU17ZtuhdasBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:26:30.089978Z"},"content_sha256":"ef5d5b299f77d6ccf810c358950a509c4e4f06acfa31822c4423c544e0bdf4ee","schema_version":"1.0","event_id":"sha256:ef5d5b299f77d6ccf810c358950a509c4e4f06acfa31822c4423c544e0bdf4ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6DVF5ESVWDWELBENJ6CJT3OXJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans, Ilbin Lee","submitted_at":"2021-06-18T07:54:23Z","abstract_excerpt":"In high stake applications, active experimentation may be considered too risky and thus data are often collected passively. While in simple cases, such as in bandits, passive and active data collection are similarly effective, the price of passive sampling can be much higher when collecting data from a system with controlled states. The main focus of the current paper is the characterization of this price. For example, when learning in episodic finite state-action Markov decision processes (MDPs) with $\\mathrm{S}$ states and $\\mathrm{A}$ actions, we show that even with the best (but passively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09973","kind":"arxiv","version":3},"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/2106.09973/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":"2026-07-05T06:27:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3n0RThsfo+hoz5k1FmDU2F9Ws36zyI3tdoJkdJxO7iuRwmRk58VMeAXeOJwwpCVzEAwRpFBrC3pPvlSku8YZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:26:30.090496Z"},"content_sha256":"f542c820b5c2e7ecd07b3f58296e32ceeca95c0547d60b838af04059d833b5c7","schema_version":"1.0","event_id":"sha256:f542c820b5c2e7ecd07b3f58296e32ceeca95c0547d60b838af04059d833b5c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DVF5ESVWDWELBENJ6CJT3OXJT/bundle.json","state_url":"https://pith.science/pith/6DVF5ESVWDWELBENJ6CJT3OXJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DVF5ESVWDWELBENJ6CJT3OXJT/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":"2026-08-03T15:26:30Z","links":{"resolver":"https://pith.science/pith/6DVF5ESVWDWELBENJ6CJT3OXJT","bundle":"https://pith.science/pith/6DVF5ESVWDWELBENJ6CJT3OXJT/bundle.json","state":"https://pith.science/pith/6DVF5ESVWDWELBENJ6CJT3OXJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DVF5ESVWDWELBENJ6CJT3OXJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6DVF5ESVWDWELBENJ6CJT3OXJT","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":"4b232d416a297a8d930233a48783402d2bbc0dca68ac5dc28a6208428b2dba82","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T07:54:23Z","title_canon_sha256":"a2055776c4f1b93acd8f7a70aa4060f73d718fd17b06a54175fa69230f50d65e"},"schema_version":"1.0","source":{"id":"2106.09973","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09973","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09973v3","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09973","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"pith_short_12","alias_value":"6DVF5ESVWDWE","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"pith_short_16","alias_value":"6DVF5ESVWDWELBEN","created_at":"2026-07-05T06:27:37Z"},{"alias_kind":"pith_short_8","alias_value":"6DVF5ESV","created_at":"2026-07-05T06:27:37Z"}],"graph_snapshots":[{"event_id":"sha256:f542c820b5c2e7ecd07b3f58296e32ceeca95c0547d60b838af04059d833b5c7","target":"graph","created_at":"2026-07-05T06:27:37Z","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/2106.09973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In high stake applications, active experimentation may be considered too risky and thus data are often collected passively. While in simple cases, such as in bandits, passive and active data collection are similarly effective, the price of passive sampling can be much higher when collecting data from a system with controlled states. The main focus of the current paper is the characterization of this price. For example, when learning in episodic finite state-action Markov decision processes (MDPs) with $\\mathrm{S}$ states and $\\mathrm{A}$ actions, we show that even with the best (but passively ","authors_text":"Bo Dai, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans, Ilbin Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T07:54:23Z","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09973","kind":"arxiv","version":3},"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:ef5d5b299f77d6ccf810c358950a509c4e4f06acfa31822c4423c544e0bdf4ee","target":"record","created_at":"2026-07-05T06:27:37Z","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":"4b232d416a297a8d930233a48783402d2bbc0dca68ac5dc28a6208428b2dba82","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T07:54:23Z","title_canon_sha256":"a2055776c4f1b93acd8f7a70aa4060f73d718fd17b06a54175fa69230f50d65e"},"schema_version":"1.0","source":{"id":"2106.09973","kind":"arxiv","version":3}},"canonical_sha256":"f0ea5e9255b0ec45848d4f8499edd74cc2aa1d209ca0cf2b61bffe018688a0fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0ea5e9255b0ec45848d4f8499edd74cc2aa1d209ca0cf2b61bffe018688a0fd","first_computed_at":"2026-07-05T06:27:37.301583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:37.301583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mAqMCmE6DO5/6qIMmlpgxVig6+HjtYvYSNZdodjmXGA8B4mou1l5rnIB7SqZJ68YJQvgWlkqhfYOVhgwrd4VAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:37.302082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09973","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef5d5b299f77d6ccf810c358950a509c4e4f06acfa31822c4423c544e0bdf4ee","sha256:f542c820b5c2e7ecd07b3f58296e32ceeca95c0547d60b838af04059d833b5c7"],"state_sha256":"24afcc6c6ea8203dc08d9489560e2140fa95a67086a653a31c2f888cf612d8a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l4emquRQJ+I740UpA+pc2R0KvdUydccAoRpLQFMcE+9wsEu07xzcP37CHx6Nq2W8S9KduZ48zy4d/+R6ma7GCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:26:30.094877Z","bundle_sha256":"93d42bd085ed829b47eaa1c4595106a65aca502c71cf0f6dc9e9de25213ee031"}}