{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R3C6GEGVB4QN5ICKZP5A5GPVM4","short_pith_number":"pith:R3C6GEGV","schema_version":"1.0","canonical_sha256":"8ec5e310d50f20dea04acbfa0e99f5671bf95aa5e2ddb0d36592b64cc717a92a","source":{"kind":"arxiv","id":"2205.07408","version":2},"attestation_state":"computed","paper":{"title":"Training neural networks using Metropolis Monte Carlo and an adaptive variant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.NE"],"primary_cat":"cs.LG","authors_text":"Corneel Casert, Ian Benlolo, Isaac Tamblyn, Stephen Whitelam, Viktor Selin","submitted_at":"2022-05-16T01:01:55Z","abstract_excerpt":"We examine the zero-temperature Metropolis Monte Carlo algorithm as a tool for training a neural network by minimizing a loss function. We find that, as expected on theoretical grounds and shown empirically by other authors, Metropolis Monte Carlo can train a neural net with an accuracy comparable to that of gradient descent, if not necessarily as quickly. The Metropolis algorithm does not fail automatically when the number of parameters of a neural network is large. It can fail when a neural network's structure or neuron activations are strongly heterogenous, and we introduce an adaptive Mont"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.07408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T01:01:55Z","cross_cats_sorted":["cond-mat.stat-mech","cs.NE"],"title_canon_sha256":"b4db11fd906babe6875cd141d82f2d55bb89b21454e9607da39f98a2e60937e3","abstract_canon_sha256":"5578ce7330a6a1610bf87a8b634adae8fe8fb47643d501fe3aca003211b42476"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:28.432297Z","signature_b64":"dlN2atvyXKqihNv743nRVbfLhnoyaCmOaOscGPTMGbn/UPc8ictG/OTH83vGsXgp1YQ99lYSMnWEJcCcTMPfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ec5e310d50f20dea04acbfa0e99f5671bf95aa5e2ddb0d36592b64cc717a92a","last_reissued_at":"2026-07-05T04:47:28.431870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:28.431870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training neural networks using Metropolis Monte Carlo and an adaptive variant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.NE"],"primary_cat":"cs.LG","authors_text":"Corneel Casert, Ian Benlolo, Isaac Tamblyn, Stephen Whitelam, Viktor Selin","submitted_at":"2022-05-16T01:01:55Z","abstract_excerpt":"We examine the zero-temperature Metropolis Monte Carlo algorithm as a tool for training a neural network by minimizing a loss function. We find that, as expected on theoretical grounds and shown empirically by other authors, Metropolis Monte Carlo can train a neural net with an accuracy comparable to that of gradient descent, if not necessarily as quickly. The Metropolis algorithm does not fail automatically when the number of parameters of a neural network is large. It can fail when a neural network's structure or neuron activations are strongly heterogenous, and we introduce an adaptive Mont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07408","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.07408/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.07408","created_at":"2026-07-05T04:47:28.431929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07408v2","created_at":"2026-07-05T04:47:28.431929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07408","created_at":"2026-07-05T04:47:28.431929+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3C6GEGVB4QN","created_at":"2026-07-05T04:47:28.431929+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3C6GEGVB4QN5ICK","created_at":"2026-07-05T04:47:28.431929+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3C6GEGV","created_at":"2026-07-05T04:47:28.431929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08341","citing_title":"Dissecting a Small Artificial Neural Network","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4","json":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4.json","graph_json":"https://pith.science/api/pith-number/R3C6GEGVB4QN5ICKZP5A5GPVM4/graph.json","events_json":"https://pith.science/api/pith-number/R3C6GEGVB4QN5ICKZP5A5GPVM4/events.json","paper":"https://pith.science/paper/R3C6GEGV"},"agent_actions":{"view_html":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4","download_json":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4.json","view_paper":"https://pith.science/paper/R3C6GEGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07408&json=true","fetch_graph":"https://pith.science/api/pith-number/R3C6GEGVB4QN5ICKZP5A5GPVM4/graph.json","fetch_events":"https://pith.science/api/pith-number/R3C6GEGVB4QN5ICKZP5A5GPVM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4/action/storage_attestation","attest_author":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4/action/author_attestation","sign_citation":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4/action/citation_signature","submit_replication":"https://pith.science/pith/R3C6GEGVB4QN5ICKZP5A5GPVM4/action/replication_record"}},"created_at":"2026-07-05T04:47:28.431929+00:00","updated_at":"2026-07-05T04:47:28.431929+00:00"}