{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:533GWVAR3V52F22HXNACAPLQVA","short_pith_number":"pith:533GWVAR","canonical_record":{"source":{"id":"1705.07262","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-20T05:31:52Z","cross_cats_sorted":["cs.AI","cs.NE","cs.SY"],"title_canon_sha256":"6d411bcb2aeb7d445d05ca4803ae06d4b77f91237ff7ea64c640fddc565a1474","abstract_canon_sha256":"c1ea2c4033f6949149fd909eafe1a97a455ff6a71d6cecb28aa77dec9da302db"},"schema_version":"1.0"},"canonical_sha256":"eef66b5411dd7ba2eb47bb40203d70a81c07b9c6c72c59a3c81cad4f2b31c2cd","source":{"kind":"arxiv","id":"1705.07262","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07262","created_at":"2026-05-18T00:25:07Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07262v2","created_at":"2026-05-18T00:25:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07262","created_at":"2026-05-18T00:25:07Z"},{"alias_kind":"pith_short_12","alias_value":"533GWVAR3V52","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"533GWVAR3V52F22H","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"533GWVAR","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:533GWVAR3V52F22HXNACAPLQVA","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07262","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-20T05:31:52Z","cross_cats_sorted":["cs.AI","cs.NE","cs.SY"],"title_canon_sha256":"6d411bcb2aeb7d445d05ca4803ae06d4b77f91237ff7ea64c640fddc565a1474","abstract_canon_sha256":"c1ea2c4033f6949149fd909eafe1a97a455ff6a71d6cecb28aa77dec9da302db"},"schema_version":"1.0"},"canonical_sha256":"eef66b5411dd7ba2eb47bb40203d70a81c07b9c6c72c59a3c81cad4f2b31c2cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:07.716285Z","signature_b64":"GlLtIByC9w523QEl1TqkAnWx7h8kKJ6BardAjakVaAdjGBgSf9VDNbApgyFRhHVeN61ziDJfgRSStRXGd7YwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eef66b5411dd7ba2eb47bb40203d70a81c07b9c6c72c59a3c81cad4f2b31c2cd","last_reissued_at":"2026-05-18T00:25:07.715649Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:07.715649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07262","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":"2026-05-18T00:25:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bxGgsg0qjdEpadfaWCecJJ4WN/czkDtoq5o1M2AzWaiYKMGQJB+6Lk+ec3TQ8MR0oR56bD8cyRJP/p2DXYHuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:50:05.011172Z"},"content_sha256":"f148b67371b17a7a7b2fd1c5ac157135178f8c10b8ab7335822f1ad062689278","schema_version":"1.0","event_id":"sha256:f148b67371b17a7a7b2fd1c5ac157135178f8c10b8ab7335822f1ad062689278"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:533GWVAR3V52F22HXNACAPLQVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Batch Reinforcement Learning on the Industrial Benchmark: First Experiences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.SY"],"primary_cat":"cs.LG","authors_text":"Alexander Hentschel, Daniel Hein, Michel Tokic, Steffen Udluft, Thomas A. Runkler, Volkmar Sterzing","submitted_at":"2017-05-20T05:31:52Z","abstract_excerpt":"The Particle Swarm Optimization Policy (PSO-P) has been recently introduced and proven to produce remarkable results on interacting with academic reinforcement learning benchmarks in an off-policy, batch-based setting. To further investigate the properties and feasibility on real-world applications, this paper investigates PSO-P on the so-called Industrial Benchmark (IB), a novel reinforcement learning (RL) benchmark that aims at being realistic by including a variety of aspects found in industrial applications, like continuous state and action spaces, a high dimensional, partially observable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07262","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":""},"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":"2026-05-18T00:25:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+sk0mIf9Z+OKflHIEndC8v2W5RVbXZHXSvHCUbL67bP2ORgYKpuKhdOgzvw9CLeKwiOcTgLWmWVMSNdrUuuDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:50:05.011851Z"},"content_sha256":"152f8fac7e3acde9630801fa98c880abd7206ca2075beea0f59377ac3aed065d","schema_version":"1.0","event_id":"sha256:152f8fac7e3acde9630801fa98c880abd7206ca2075beea0f59377ac3aed065d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/533GWVAR3V52F22HXNACAPLQVA/bundle.json","state_url":"https://pith.science/pith/533GWVAR3V52F22HXNACAPLQVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/533GWVAR3V52F22HXNACAPLQVA/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":"2026-05-26T02:50:05Z","links":{"resolver":"https://pith.science/pith/533GWVAR3V52F22HXNACAPLQVA","bundle":"https://pith.science/pith/533GWVAR3V52F22HXNACAPLQVA/bundle.json","state":"https://pith.science/pith/533GWVAR3V52F22HXNACAPLQVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/533GWVAR3V52F22HXNACAPLQVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:533GWVAR3V52F22HXNACAPLQVA","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":"c1ea2c4033f6949149fd909eafe1a97a455ff6a71d6cecb28aa77dec9da302db","cross_cats_sorted":["cs.AI","cs.NE","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-20T05:31:52Z","title_canon_sha256":"6d411bcb2aeb7d445d05ca4803ae06d4b77f91237ff7ea64c640fddc565a1474"},"schema_version":"1.0","source":{"id":"1705.07262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07262","created_at":"2026-05-18T00:25:07Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07262v2","created_at":"2026-05-18T00:25:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07262","created_at":"2026-05-18T00:25:07Z"},{"alias_kind":"pith_short_12","alias_value":"533GWVAR3V52","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"533GWVAR3V52F22H","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"533GWVAR","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:152f8fac7e3acde9630801fa98c880abd7206ca2075beea0f59377ac3aed065d","target":"graph","created_at":"2026-05-18T00:25:07Z","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":"The Particle Swarm Optimization Policy (PSO-P) has been recently introduced and proven to produce remarkable results on interacting with academic reinforcement learning benchmarks in an off-policy, batch-based setting. To further investigate the properties and feasibility on real-world applications, this paper investigates PSO-P on the so-called Industrial Benchmark (IB), a novel reinforcement learning (RL) benchmark that aims at being realistic by including a variety of aspects found in industrial applications, like continuous state and action spaces, a high dimensional, partially observable ","authors_text":"Alexander Hentschel, Daniel Hein, Michel Tokic, Steffen Udluft, Thomas A. Runkler, Volkmar Sterzing","cross_cats":["cs.AI","cs.NE","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-20T05:31:52Z","title":"Batch Reinforcement Learning on the Industrial Benchmark: First Experiences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07262","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:f148b67371b17a7a7b2fd1c5ac157135178f8c10b8ab7335822f1ad062689278","target":"record","created_at":"2026-05-18T00:25:07Z","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":"c1ea2c4033f6949149fd909eafe1a97a455ff6a71d6cecb28aa77dec9da302db","cross_cats_sorted":["cs.AI","cs.NE","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-20T05:31:52Z","title_canon_sha256":"6d411bcb2aeb7d445d05ca4803ae06d4b77f91237ff7ea64c640fddc565a1474"},"schema_version":"1.0","source":{"id":"1705.07262","kind":"arxiv","version":2}},"canonical_sha256":"eef66b5411dd7ba2eb47bb40203d70a81c07b9c6c72c59a3c81cad4f2b31c2cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eef66b5411dd7ba2eb47bb40203d70a81c07b9c6c72c59a3c81cad4f2b31c2cd","first_computed_at":"2026-05-18T00:25:07.715649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:07.715649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GlLtIByC9w523QEl1TqkAnWx7h8kKJ6BardAjakVaAdjGBgSf9VDNbApgyFRhHVeN61ziDJfgRSStRXGd7YwDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:07.716285Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f148b67371b17a7a7b2fd1c5ac157135178f8c10b8ab7335822f1ad062689278","sha256:152f8fac7e3acde9630801fa98c880abd7206ca2075beea0f59377ac3aed065d"],"state_sha256":"ac13f8f4114215d0fbaef7167208061334c052b4e9e07df1bd01d62d2ef8867f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9fTnPxkp4XooFsLqcnGpR/9zIA0eyPl+Q686wgxiBZMIokQzgVnHQ77fNX/QkicuE4JBFJKxMnb38dz+KTI0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:50:05.015563Z","bundle_sha256":"02c00a8e3be3f9bffcfe7254ff29f17067342cf235581a176d6ab8c16b6a3fcc"}}