{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6MXAIPD2GIXGVZIWVVKZI77N7G","short_pith_number":"pith:6MXAIPD2","canonical_record":{"source":{"id":"2109.08331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-17T02:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"a0f200ec30fad050f89eb5565104f5728ee0605f00bc777a56586416d87fb070","abstract_canon_sha256":"c7b68c4b96d7c8dba4730845c217be66b3ef321df127b4042687328d88e61922"},"schema_version":"1.0"},"canonical_sha256":"f32e043c7a322e6ae516ad55947fedf987a4781df5a40ae6d61539ab03c200db","source":{"kind":"arxiv","id":"2109.08331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08331","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08331v1","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08331","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"6MXAIPD2GIXG","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"6MXAIPD2GIXGVZIW","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"6MXAIPD2","created_at":"2026-07-05T03:15:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6MXAIPD2GIXGVZIWVVKZI77N7G","target":"record","payload":{"canonical_record":{"source":{"id":"2109.08331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-17T02:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"a0f200ec30fad050f89eb5565104f5728ee0605f00bc777a56586416d87fb070","abstract_canon_sha256":"c7b68c4b96d7c8dba4730845c217be66b3ef321df127b4042687328d88e61922"},"schema_version":"1.0"},"canonical_sha256":"f32e043c7a322e6ae516ad55947fedf987a4781df5a40ae6d61539ab03c200db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:14.767681Z","signature_b64":"Zt5FWcUXj2YMLfPE6v3txvCbaxnNryoN1QJsTy3X7u/qpJf2x5t7zq6FuwFaXwzE3iCQINYeiqXayqPoGQ3yCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f32e043c7a322e6ae516ad55947fedf987a4781df5a40ae6d61539ab03c200db","last_reissued_at":"2026-07-05T03:15:14.767229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:14.767229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.08331","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":"2026-07-05T03:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SQ2f7xQU303JG3AAY/xFd4QAYAuAbWaxUBHaAqBybhOtczzza7NBJd7OZGfDNU/dv61xGl/kuDyv7XV9wRmhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T16:59:20.251639Z"},"content_sha256":"5edcebfd40bd0973e4e8fd66c9cef9dda1352806306f14d3b282248e771b098f","schema_version":"1.0","event_id":"sha256:5edcebfd40bd0973e4e8fd66c9cef9dda1352806306f14d3b282248e771b098f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6MXAIPD2GIXGVZIWVVKZI77N7G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haruka Kiyohara, Kosuke Kawakami, Yuta Saito","submitted_at":"2021-09-17T02:56:10Z","abstract_excerpt":"In recommender systems (RecSys) and real-time bidding (RTB) for online advertisements, we often try to optimize sequential decision making using bandit and reinforcement learning (RL) techniques. In these applications, offline reinforcement learning (offline RL) and off-policy evaluation (OPE) are beneficial because they enable safe policy optimization using only logged data without any risky online interaction. In this position paper, we explore the potential of using simulation to accelerate practical research of offline RL and OPE, particularly in RecSys and RTB. Specifically, we discuss ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08331","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/2109.08331/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":"2026-07-05T03:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z3ZNsmSO7VixYflGMj7kpaVG61bftPMYgo866ddSkyStdl4AXtLcc7Yo5dBaHNolvzR5ixG3yggOiZJs+O+TDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T16:59:20.251992Z"},"content_sha256":"a1acb65ca042186abfb0644c70830b940d643c2be3fafde5f992eadb45d3b97a","schema_version":"1.0","event_id":"sha256:a1acb65ca042186abfb0644c70830b940d643c2be3fafde5f992eadb45d3b97a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6MXAIPD2GIXGVZIWVVKZI77N7G/bundle.json","state_url":"https://pith.science/pith/6MXAIPD2GIXGVZIWVVKZI77N7G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6MXAIPD2GIXGVZIWVVKZI77N7G/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":"2026-07-14T16:59:20Z","links":{"resolver":"https://pith.science/pith/6MXAIPD2GIXGVZIWVVKZI77N7G","bundle":"https://pith.science/pith/6MXAIPD2GIXGVZIWVVKZI77N7G/bundle.json","state":"https://pith.science/pith/6MXAIPD2GIXGVZIWVVKZI77N7G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6MXAIPD2GIXGVZIWVVKZI77N7G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6MXAIPD2GIXGVZIWVVKZI77N7G","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":"c7b68c4b96d7c8dba4730845c217be66b3ef321df127b4042687328d88e61922","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-17T02:56:10Z","title_canon_sha256":"a0f200ec30fad050f89eb5565104f5728ee0605f00bc777a56586416d87fb070"},"schema_version":"1.0","source":{"id":"2109.08331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08331","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08331v1","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08331","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"6MXAIPD2GIXG","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"6MXAIPD2GIXGVZIW","created_at":"2026-07-05T03:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"6MXAIPD2","created_at":"2026-07-05T03:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:a1acb65ca042186abfb0644c70830b940d643c2be3fafde5f992eadb45d3b97a","target":"graph","created_at":"2026-07-05T03:15:14Z","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/2109.08331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recommender systems (RecSys) and real-time bidding (RTB) for online advertisements, we often try to optimize sequential decision making using bandit and reinforcement learning (RL) techniques. In these applications, offline reinforcement learning (offline RL) and off-policy evaluation (OPE) are beneficial because they enable safe policy optimization using only logged data without any risky online interaction. In this position paper, we explore the potential of using simulation to accelerate practical research of offline RL and OPE, particularly in RecSys and RTB. Specifically, we discuss ho","authors_text":"Haruka Kiyohara, Kosuke Kawakami, Yuta Saito","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-17T02:56:10Z","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08331","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":"sha256:5edcebfd40bd0973e4e8fd66c9cef9dda1352806306f14d3b282248e771b098f","target":"record","created_at":"2026-07-05T03:15:14Z","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":"c7b68c4b96d7c8dba4730845c217be66b3ef321df127b4042687328d88e61922","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-17T02:56:10Z","title_canon_sha256":"a0f200ec30fad050f89eb5565104f5728ee0605f00bc777a56586416d87fb070"},"schema_version":"1.0","source":{"id":"2109.08331","kind":"arxiv","version":1}},"canonical_sha256":"f32e043c7a322e6ae516ad55947fedf987a4781df5a40ae6d61539ab03c200db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f32e043c7a322e6ae516ad55947fedf987a4781df5a40ae6d61539ab03c200db","first_computed_at":"2026-07-05T03:15:14.767229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:14.767229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zt5FWcUXj2YMLfPE6v3txvCbaxnNryoN1QJsTy3X7u/qpJf2x5t7zq6FuwFaXwzE3iCQINYeiqXayqPoGQ3yCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:14.767681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.08331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5edcebfd40bd0973e4e8fd66c9cef9dda1352806306f14d3b282248e771b098f","sha256:a1acb65ca042186abfb0644c70830b940d643c2be3fafde5f992eadb45d3b97a"],"state_sha256":"1c319189299f6c03ca3ce632ca9a0cbbdb1f2d5bc7ed4490afb15a6afc64d539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQZppcBumKOYgsXUmjmaEYIxemKFfFl/ppCxlwYBCCeGS9HRYDaEVJ292k4OCXeWZYjTZPYxLC8YJeIzCwRrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T16:59:20.254066Z","bundle_sha256":"d6743e230f5976da7883b246139f9134272fbac997a8434ef6a702c5d59404d1"}}