{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:3FJ65TFF4FTWVKJIBYBQ7KLWGX","short_pith_number":"pith:3FJ65TFF","canonical_record":{"source":{"id":"1410.0123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-01T06:55:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ab3ccbcd9131064d912c4dd64d636a439965452ceaeb420357300725a220e2e7","abstract_canon_sha256":"a5265ddb5484536d6fa651342b3a33ee8887ab99743566d10cf00cb80b5c8780"},"schema_version":"1.0"},"canonical_sha256":"d953eecca5e1676aa9280e030fa97635f10c5caf65bfb58da884f2da5e712576","source":{"kind":"arxiv","id":"1410.0123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.0123","created_at":"2026-05-18T02:41:17Z"},{"alias_kind":"arxiv_version","alias_value":"1410.0123v1","created_at":"2026-05-18T02:41:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.0123","created_at":"2026-05-18T02:41:17Z"},{"alias_kind":"pith_short_12","alias_value":"3FJ65TFF4FTW","created_at":"2026-05-18T12:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"3FJ65TFF4FTWVKJI","created_at":"2026-05-18T12:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"3FJ65TFF","created_at":"2026-05-18T12:28:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:3FJ65TFF4FTWVKJIBYBQ7KLWGX","target":"record","payload":{"canonical_record":{"source":{"id":"1410.0123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-01T06:55:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ab3ccbcd9131064d912c4dd64d636a439965452ceaeb420357300725a220e2e7","abstract_canon_sha256":"a5265ddb5484536d6fa651342b3a33ee8887ab99743566d10cf00cb80b5c8780"},"schema_version":"1.0"},"canonical_sha256":"d953eecca5e1676aa9280e030fa97635f10c5caf65bfb58da884f2da5e712576","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:41:17.959415Z","signature_b64":"/umpUOu2RMT7b70opO2RDdIrimbsuik6h1PQTqOltVifTb9JLbK56ZFdVtybNzU3CovE3hSUHIcOivQRuX6qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d953eecca5e1676aa9280e030fa97635f10c5caf65bfb58da884f2da5e712576","last_reissued_at":"2026-05-18T02:41:17.958883Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:41:17.958883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1410.0123","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":"2026-05-18T02:41:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AR9KKG6JHMUvJutJuHIx59j84SB+PUYIuqHZtDDSwZBojFZOrhte8ywMwvrFkobYzNrgN81azYXa5tWrdL7ABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:29:58.082353Z"},"content_sha256":"d6760617f305b556d2f3b8b546eaebeb4e7756c3613a142dbad3a798a83e1927","schema_version":"1.0","event_id":"sha256:d6760617f305b556d2f3b8b546eaebeb4e7756c3613a142dbad3a798a83e1927"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:3FJ65TFF4FTWVKJIBYBQ7KLWGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Tempering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Guillaume Desjardins, Heng Luo, Yoshua Bengio","submitted_at":"2014-10-01T06:55:11Z","abstract_excerpt":"Restricted Boltzmann Machines (RBMs) are one of the fundamental building blocks of deep learning. Approximate maximum likelihood training of RBMs typically necessitates sampling from these models. In many training scenarios, computationally efficient Gibbs sampling procedures are crippled by poor mixing. In this work we propose a novel method of sampling from Boltzmann machines that demonstrates a computationally efficient way to promote mixing. Our approach leverages an under-appreciated property of deep generative models such as the Deep Belief Network (DBN), where Gibbs sampling from deeper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.0123","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":"2026-05-18T02:41:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rVLU64+spd74BXPv+xd3eI9X62jDv0bZVGIteXzC8cpM+9IyHBmnX+bEPfUZG55Qyexkd2jDBg2YOV6grc95CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:29:58.083069Z"},"content_sha256":"268a368e6562b4e55f973c998a85b194268324da65495906c73bf37dd4f75a19","schema_version":"1.0","event_id":"sha256:268a368e6562b4e55f973c998a85b194268324da65495906c73bf37dd4f75a19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FJ65TFF4FTWVKJIBYBQ7KLWGX/bundle.json","state_url":"https://pith.science/pith/3FJ65TFF4FTWVKJIBYBQ7KLWGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FJ65TFF4FTWVKJIBYBQ7KLWGX/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":"2026-05-28T18:29:58Z","links":{"resolver":"https://pith.science/pith/3FJ65TFF4FTWVKJIBYBQ7KLWGX","bundle":"https://pith.science/pith/3FJ65TFF4FTWVKJIBYBQ7KLWGX/bundle.json","state":"https://pith.science/pith/3FJ65TFF4FTWVKJIBYBQ7KLWGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FJ65TFF4FTWVKJIBYBQ7KLWGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:3FJ65TFF4FTWVKJIBYBQ7KLWGX","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":"a5265ddb5484536d6fa651342b3a33ee8887ab99743566d10cf00cb80b5c8780","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-01T06:55:11Z","title_canon_sha256":"ab3ccbcd9131064d912c4dd64d636a439965452ceaeb420357300725a220e2e7"},"schema_version":"1.0","source":{"id":"1410.0123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.0123","created_at":"2026-05-18T02:41:17Z"},{"alias_kind":"arxiv_version","alias_value":"1410.0123v1","created_at":"2026-05-18T02:41:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.0123","created_at":"2026-05-18T02:41:17Z"},{"alias_kind":"pith_short_12","alias_value":"3FJ65TFF4FTW","created_at":"2026-05-18T12:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"3FJ65TFF4FTWVKJI","created_at":"2026-05-18T12:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"3FJ65TFF","created_at":"2026-05-18T12:28:11Z"}],"graph_snapshots":[{"event_id":"sha256:268a368e6562b4e55f973c998a85b194268324da65495906c73bf37dd4f75a19","target":"graph","created_at":"2026-05-18T02:41:17Z","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":"Restricted Boltzmann Machines (RBMs) are one of the fundamental building blocks of deep learning. Approximate maximum likelihood training of RBMs typically necessitates sampling from these models. In many training scenarios, computationally efficient Gibbs sampling procedures are crippled by poor mixing. In this work we propose a novel method of sampling from Boltzmann machines that demonstrates a computationally efficient way to promote mixing. Our approach leverages an under-appreciated property of deep generative models such as the Deep Belief Network (DBN), where Gibbs sampling from deeper","authors_text":"Aaron Courville, Guillaume Desjardins, Heng Luo, Yoshua Bengio","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-01T06:55:11Z","title":"Deep Tempering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.0123","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:d6760617f305b556d2f3b8b546eaebeb4e7756c3613a142dbad3a798a83e1927","target":"record","created_at":"2026-05-18T02:41:17Z","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":"a5265ddb5484536d6fa651342b3a33ee8887ab99743566d10cf00cb80b5c8780","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-01T06:55:11Z","title_canon_sha256":"ab3ccbcd9131064d912c4dd64d636a439965452ceaeb420357300725a220e2e7"},"schema_version":"1.0","source":{"id":"1410.0123","kind":"arxiv","version":1}},"canonical_sha256":"d953eecca5e1676aa9280e030fa97635f10c5caf65bfb58da884f2da5e712576","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d953eecca5e1676aa9280e030fa97635f10c5caf65bfb58da884f2da5e712576","first_computed_at":"2026-05-18T02:41:17.958883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:41:17.958883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/umpUOu2RMT7b70opO2RDdIrimbsuik6h1PQTqOltVifTb9JLbK56ZFdVtybNzU3CovE3hSUHIcOivQRuX6qCw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:41:17.959415Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.0123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6760617f305b556d2f3b8b546eaebeb4e7756c3613a142dbad3a798a83e1927","sha256:268a368e6562b4e55f973c998a85b194268324da65495906c73bf37dd4f75a19"],"state_sha256":"312c45d42e7907fe7cc3e3005c31933d7edc2a837c9760bb074ccf8c9e6744e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HE4GyBJS3aDS1f5+kr0R8OdjvKgpvo+tIuj7uW0qi86zlYYRjz9pk9H9VpdfRboRnxhzcNQrIQ9y/Iu47RCPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:29:58.087146Z","bundle_sha256":"810ca7a5f61d49574bf1f2c7a82febfa831ce29fcfe4eb388c29be5c6cc04103"}}