{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:5BQZVHKD6DT23QOYWMDQRZAEMX","short_pith_number":"pith:5BQZVHKD","canonical_record":{"source":{"id":"1206.5533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-24T19:17:35Z","cross_cats_sorted":[],"title_canon_sha256":"007fcaeb6e78f3de8aded0a0fb16fb887753c0023fa6221a4da7c8420b60b246","abstract_canon_sha256":"914f43e3a29f42f4f4a0aad4b5e6551b71148293f0487a508ee3dbeaf9de77e0"},"schema_version":"1.0"},"canonical_sha256":"e8619a9d43f0e7adc1d8b30708e40465cb52579c24304aa8e53967ee88100fe0","source":{"kind":"arxiv","id":"1206.5533","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5533","created_at":"2026-05-18T03:45:31Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5533v2","created_at":"2026-05-18T03:45:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5533","created_at":"2026-05-18T03:45:31Z"},{"alias_kind":"pith_short_12","alias_value":"5BQZVHKD6DT2","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"5BQZVHKD6DT23QOY","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"5BQZVHKD","created_at":"2026-05-18T12:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:5BQZVHKD6DT23QOYWMDQRZAEMX","target":"record","payload":{"canonical_record":{"source":{"id":"1206.5533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-24T19:17:35Z","cross_cats_sorted":[],"title_canon_sha256":"007fcaeb6e78f3de8aded0a0fb16fb887753c0023fa6221a4da7c8420b60b246","abstract_canon_sha256":"914f43e3a29f42f4f4a0aad4b5e6551b71148293f0487a508ee3dbeaf9de77e0"},"schema_version":"1.0"},"canonical_sha256":"e8619a9d43f0e7adc1d8b30708e40465cb52579c24304aa8e53967ee88100fe0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:45:31.476226Z","signature_b64":"VcvorqSbwSw4rIUgGjfZgsyekoo+dpVq1WC7womtUR2aHlQLDFfWQo5tKsQ12awSRbo2Rr7mPQWK86FrgIwJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8619a9d43f0e7adc1d8b30708e40465cb52579c24304aa8e53967ee88100fe0","last_reissued_at":"2026-05-18T03:45:31.475782Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:45:31.475782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.5533","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":"2026-05-18T03:45:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYRFiEMCpGLIVsRRCCCF+gO/KZIwn7Ewur380lpY2dSXaYJ7TrgNsJssIQAviBy4bXumhEiN3te5LFGVcVhCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:56:55.388020Z"},"content_sha256":"a409f3fe2ddd25d775b356a8a28e569efdee294533450c0a26e6a0b3c8799a93","schema_version":"1.0","event_id":"sha256:a409f3fe2ddd25d775b356a8a28e569efdee294533450c0a26e6a0b3c8799a93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:5BQZVHKD6DT23QOYWMDQRZAEMX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical recommendations for gradient-based training of deep architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yoshua Bengio","submitted_at":"2012-06-24T19:17:35Z","abstract_excerpt":"Learning algorithms related to artificial neural networks and in particular for Deep Learning may seem to involve many bells and whistles, called hyper-parameters. This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on back-propagated gradient and gradient-based optimization. It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters. Overall, it describes elements of the practice used to succ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5533","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":"2026-05-18T03:45:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LbU+vasr+riYh+P0XlOPP3z6Z+bcOgWlhOMBAlva8yeyEBSb0G5sI3MgQBN/DHg7fvt+nT/ikTrXaRYcrKzzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:56:55.388684Z"},"content_sha256":"fa1cf586243f05d38d9c156cf22d5c4f600fa3e91d9193f5de26cc77fa2e9a05","schema_version":"1.0","event_id":"sha256:fa1cf586243f05d38d9c156cf22d5c4f600fa3e91d9193f5de26cc77fa2e9a05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BQZVHKD6DT23QOYWMDQRZAEMX/bundle.json","state_url":"https://pith.science/pith/5BQZVHKD6DT23QOYWMDQRZAEMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BQZVHKD6DT23QOYWMDQRZAEMX/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":"2026-06-10T13:56:55Z","links":{"resolver":"https://pith.science/pith/5BQZVHKD6DT23QOYWMDQRZAEMX","bundle":"https://pith.science/pith/5BQZVHKD6DT23QOYWMDQRZAEMX/bundle.json","state":"https://pith.science/pith/5BQZVHKD6DT23QOYWMDQRZAEMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BQZVHKD6DT23QOYWMDQRZAEMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:5BQZVHKD6DT23QOYWMDQRZAEMX","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":"914f43e3a29f42f4f4a0aad4b5e6551b71148293f0487a508ee3dbeaf9de77e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-24T19:17:35Z","title_canon_sha256":"007fcaeb6e78f3de8aded0a0fb16fb887753c0023fa6221a4da7c8420b60b246"},"schema_version":"1.0","source":{"id":"1206.5533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5533","created_at":"2026-05-18T03:45:31Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5533v2","created_at":"2026-05-18T03:45:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5533","created_at":"2026-05-18T03:45:31Z"},{"alias_kind":"pith_short_12","alias_value":"5BQZVHKD6DT2","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"5BQZVHKD6DT23QOY","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"5BQZVHKD","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:fa1cf586243f05d38d9c156cf22d5c4f600fa3e91d9193f5de26cc77fa2e9a05","target":"graph","created_at":"2026-05-18T03:45:31Z","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":"Learning algorithms related to artificial neural networks and in particular for Deep Learning may seem to involve many bells and whistles, called hyper-parameters. This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on back-propagated gradient and gradient-based optimization. It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters. Overall, it describes elements of the practice used to succ","authors_text":"Yoshua Bengio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-24T19:17:35Z","title":"Practical recommendations for gradient-based training of deep architectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5533","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:a409f3fe2ddd25d775b356a8a28e569efdee294533450c0a26e6a0b3c8799a93","target":"record","created_at":"2026-05-18T03:45:31Z","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":"914f43e3a29f42f4f4a0aad4b5e6551b71148293f0487a508ee3dbeaf9de77e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-24T19:17:35Z","title_canon_sha256":"007fcaeb6e78f3de8aded0a0fb16fb887753c0023fa6221a4da7c8420b60b246"},"schema_version":"1.0","source":{"id":"1206.5533","kind":"arxiv","version":2}},"canonical_sha256":"e8619a9d43f0e7adc1d8b30708e40465cb52579c24304aa8e53967ee88100fe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8619a9d43f0e7adc1d8b30708e40465cb52579c24304aa8e53967ee88100fe0","first_computed_at":"2026-05-18T03:45:31.475782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:45:31.475782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VcvorqSbwSw4rIUgGjfZgsyekoo+dpVq1WC7womtUR2aHlQLDFfWQo5tKsQ12awSRbo2Rr7mPQWK86FrgIwJAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:45:31.476226Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.5533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a409f3fe2ddd25d775b356a8a28e569efdee294533450c0a26e6a0b3c8799a93","sha256:fa1cf586243f05d38d9c156cf22d5c4f600fa3e91d9193f5de26cc77fa2e9a05"],"state_sha256":"a5530d02c4a55002f83c3b4afb9a78ab4acb5fa406ba3477fc71f12d825935f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEvqG4qLuFvdZ1Zmhxe5ZqgIi+J0fGvYwO/IPAQE5BLepT2ilL7z6pxxwEAweBzFmy+zoSrfzAye/UtSvuQXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T13:56:55.393449Z","bundle_sha256":"e27ba0406635cd5f9b1f243ec4be62f7eb320154386252417cad99891a5f0209"}}