{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5URZLP5EHPJEL7KQY4ZTO6SRIN","short_pith_number":"pith:5URZLP5E","canonical_record":{"source":{"id":"1706.00074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T18:57:42Z","cross_cats_sorted":["cs.AI","cs.NE","math.OC","quant-ph"],"title_canon_sha256":"9008553db07ea9d707f7c4396ee18f222c0d3b715cb00d0d96964e1e4a5a7e0f","abstract_canon_sha256":"667661a9f2e5ebbbf1adab7a736529b29297460b3cd3d5becda9e0351d92a76d"},"schema_version":"1.0"},"canonical_sha256":"ed2395bfa43bd245fd50c733377a51434ccf14a9cffab6dac44453c7a01b551d","source":{"kind":"arxiv","id":"1706.00074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00074","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00074v1","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00074","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"pith_short_12","alias_value":"5URZLP5EHPJE","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5URZLP5EHPJEL7KQ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5URZLP5E","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5URZLP5EHPJEL7KQY4ZTO6SRIN","target":"record","payload":{"canonical_record":{"source":{"id":"1706.00074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T18:57:42Z","cross_cats_sorted":["cs.AI","cs.NE","math.OC","quant-ph"],"title_canon_sha256":"9008553db07ea9d707f7c4396ee18f222c0d3b715cb00d0d96964e1e4a5a7e0f","abstract_canon_sha256":"667661a9f2e5ebbbf1adab7a736529b29297460b3cd3d5becda9e0351d92a76d"},"schema_version":"1.0"},"canonical_sha256":"ed2395bfa43bd245fd50c733377a51434ccf14a9cffab6dac44453c7a01b551d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:15.110640Z","signature_b64":"8OZXelBylLOM1Rci0gdRjW77I8Ou6dQJOVTYKgCmcSesKABwyniv9I/Jo09Gw1jIiEi5HasyisiPByk3LeMUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed2395bfa43bd245fd50c733377a51434ccf14a9cffab6dac44453c7a01b551d","last_reissued_at":"2026-05-18T00:43:15.109964Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:15.109964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.00074","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":"2026-05-18T00:43:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3WOjbc9Kj9c1tFNw3Ms9lxiUndQVqW/wOgR14WnLBaXDu0LzevIc/o1dTq5RWWqN30v+TVjKORK5D80exQeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:31:04.928583Z"},"content_sha256":"a70c42a6b59973d03f7b9d25d920e0c67dffd36b3afee771dbc84aaf25a79254","schema_version":"1.0","event_id":"sha256:a70c42a6b59973d03f7b9d25d920e0c67dffd36b3afee771dbc84aaf25a79254"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5URZLP5EHPJEL7KQY4ZTO6SRIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Free energy-based reinforcement learning using a quantum processor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","math.OC","quant-ph"],"primary_cat":"cs.LG","authors_text":"Anna Levit, Daniel Crawford, Ehsan Zahedinejad, Jaspreet S. Oberoi, Navid Ghadermarzy, Pooya Ronagh","submitted_at":"2017-05-29T18:57:42Z","abstract_excerpt":"Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer's measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our techniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00074","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":"2026-05-18T00:43:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4brVQWmEcWNXq8hKZpsz9F1mlArsQycIg3RhZVplQaOZWP5Ko2QlPidBUk0SM4vWwttRaNiVihwx5C8l6hHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:31:04.929240Z"},"content_sha256":"cf0108007f0ee9cd6861a29e413d5ffa09a93f876fc366aff49f9680b20186d1","schema_version":"1.0","event_id":"sha256:cf0108007f0ee9cd6861a29e413d5ffa09a93f876fc366aff49f9680b20186d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5URZLP5EHPJEL7KQY4ZTO6SRIN/bundle.json","state_url":"https://pith.science/pith/5URZLP5EHPJEL7KQY4ZTO6SRIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5URZLP5EHPJEL7KQY4ZTO6SRIN/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":"2026-05-27T01:31:04Z","links":{"resolver":"https://pith.science/pith/5URZLP5EHPJEL7KQY4ZTO6SRIN","bundle":"https://pith.science/pith/5URZLP5EHPJEL7KQY4ZTO6SRIN/bundle.json","state":"https://pith.science/pith/5URZLP5EHPJEL7KQY4ZTO6SRIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5URZLP5EHPJEL7KQY4ZTO6SRIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5URZLP5EHPJEL7KQY4ZTO6SRIN","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":"667661a9f2e5ebbbf1adab7a736529b29297460b3cd3d5becda9e0351d92a76d","cross_cats_sorted":["cs.AI","cs.NE","math.OC","quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T18:57:42Z","title_canon_sha256":"9008553db07ea9d707f7c4396ee18f222c0d3b715cb00d0d96964e1e4a5a7e0f"},"schema_version":"1.0","source":{"id":"1706.00074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00074","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00074v1","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00074","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"pith_short_12","alias_value":"5URZLP5EHPJE","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5URZLP5EHPJEL7KQ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5URZLP5E","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:cf0108007f0ee9cd6861a29e413d5ffa09a93f876fc366aff49f9680b20186d1","target":"graph","created_at":"2026-05-18T00:43:15Z","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":"Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer's measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our techniqu","authors_text":"Anna Levit, Daniel Crawford, Ehsan Zahedinejad, Jaspreet S. Oberoi, Navid Ghadermarzy, Pooya Ronagh","cross_cats":["cs.AI","cs.NE","math.OC","quant-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T18:57:42Z","title":"Free energy-based reinforcement learning using a quantum processor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00074","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:a70c42a6b59973d03f7b9d25d920e0c67dffd36b3afee771dbc84aaf25a79254","target":"record","created_at":"2026-05-18T00:43:15Z","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":"667661a9f2e5ebbbf1adab7a736529b29297460b3cd3d5becda9e0351d92a76d","cross_cats_sorted":["cs.AI","cs.NE","math.OC","quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T18:57:42Z","title_canon_sha256":"9008553db07ea9d707f7c4396ee18f222c0d3b715cb00d0d96964e1e4a5a7e0f"},"schema_version":"1.0","source":{"id":"1706.00074","kind":"arxiv","version":1}},"canonical_sha256":"ed2395bfa43bd245fd50c733377a51434ccf14a9cffab6dac44453c7a01b551d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed2395bfa43bd245fd50c733377a51434ccf14a9cffab6dac44453c7a01b551d","first_computed_at":"2026-05-18T00:43:15.109964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:15.109964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8OZXelBylLOM1Rci0gdRjW77I8Ou6dQJOVTYKgCmcSesKABwyniv9I/Jo09Gw1jIiEi5HasyisiPByk3LeMUCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:15.110640Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.00074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a70c42a6b59973d03f7b9d25d920e0c67dffd36b3afee771dbc84aaf25a79254","sha256:cf0108007f0ee9cd6861a29e413d5ffa09a93f876fc366aff49f9680b20186d1"],"state_sha256":"b49200b4dd320a56951961e360179e7d4fad4bdb0615c8d31662db161dfe9a38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vu14JhlIZyw7A5w31ZCbQXPUrsueLINcz0MIxTkMDqABolw6imT8lzcr55aS1nlULBPVWWIvNDTsDvWW8ZNYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:31:04.932339Z","bundle_sha256":"d84fd21d0fd66aa1d08b508257e00fee3bc06be2eb23786440930c6b34c941b8"}}