{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:37Y7BHDOCCLHDJ5Q5NFVVH2KB5","short_pith_number":"pith:37Y7BHDO","canonical_record":{"source":{"id":"1501.07645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-01-30T02:08:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"28b24d984027f7bf1ae1ab921f5d8a8e10767dbbabc7fe123d2d4a7104b45a3a","abstract_canon_sha256":"6bfc143f1e67379ad3f2f57f3426b318b6e2def8c83fb24ecd76dca85764a3f2"},"schema_version":"1.0"},"canonical_sha256":"dff1f09c6e109671a7b0eb4b5a9f4a0f70a0fc28508e968737b720e2c88d354f","source":{"kind":"arxiv","id":"1501.07645","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.07645","created_at":"2026-05-18T02:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"1501.07645v2","created_at":"2026-05-18T02:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.07645","created_at":"2026-05-18T02:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"37Y7BHDOCCLH","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"37Y7BHDOCCLHDJ5Q","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"37Y7BHDO","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:37Y7BHDOCCLHDJ5Q5NFVVH2KB5","target":"record","payload":{"canonical_record":{"source":{"id":"1501.07645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-01-30T02:08:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"28b24d984027f7bf1ae1ab921f5d8a8e10767dbbabc7fe123d2d4a7104b45a3a","abstract_canon_sha256":"6bfc143f1e67379ad3f2f57f3426b318b6e2def8c83fb24ecd76dca85764a3f2"},"schema_version":"1.0"},"canonical_sha256":"dff1f09c6e109671a7b0eb4b5a9f4a0f70a0fc28508e968737b720e2c88d354f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:07:26.531871Z","signature_b64":"qXXagwpGOG8jlzCx4/J6s/kKS24Xt+gVHIo7FTa1IgyD92c0Hww4OFuCa1Sp+6lQIF9DYxHy/HlndzBU3ZdxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dff1f09c6e109671a7b0eb4b5a9f4a0f70a0fc28508e968737b720e2c88d354f","last_reissued_at":"2026-05-18T02:07:26.531405Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:07:26.531405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1501.07645","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":"2026-05-18T02:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XlQoWSVyD9zkNxzC9l7xq6pkhAB6vu+s9kUbZYtEkaibRKZC3hNxv5/ieEPbznt1vcUDAlTDpIDVpN8jE9cDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T15:31:40.193654Z"},"content_sha256":"e236b6eccb7d998934f831133754e66e9f22c6bbbb06874a0347c40df39d0e36","schema_version":"1.0","event_id":"sha256:e236b6eccb7d998934f831133754e66e9f22c6bbbb06874a0347c40df39d0e36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:37Y7BHDOCCLHDJ5Q5NFVVH2KB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyper-parameter optimization of Deep Convolutional Networks for object recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Sachin S. Talathi","submitted_at":"2015-01-30T02:08:51Z","abstract_excerpt":"Recently sequential model based optimization (SMBO) has emerged as a promising hyper-parameter optimization strategy in machine learning. In this work, we investigate SMBO to identify architecture hyper-parameters of deep convolution networks (DCNs) object recognition. We propose a simple SMBO strategy that starts from a set of random initial DCN architectures to generate new architectures, which on training perform well on a given dataset. Using the proposed SMBO strategy we are able to identify a number of DCN architectures that produce results that are comparable to state-of-the-art results"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.07645","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":"2026-05-18T02:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yut4w7WjcyWwVietwS19CmBxaZMcSyRsQsr6SVj9ukY5ozVsOS/DLmRunlZd4Do2t5NKW/kdCt8Z+0kqAQlIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T15:31:40.194024Z"},"content_sha256":"4ac124a0dc895e086800e9ce243174fd535ea24733dd0d2a08b3bc03ab8e2726","schema_version":"1.0","event_id":"sha256:4ac124a0dc895e086800e9ce243174fd535ea24733dd0d2a08b3bc03ab8e2726"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37Y7BHDOCCLHDJ5Q5NFVVH2KB5/bundle.json","state_url":"https://pith.science/pith/37Y7BHDOCCLHDJ5Q5NFVVH2KB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37Y7BHDOCCLHDJ5Q5NFVVH2KB5/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":"2026-06-07T15:31:40Z","links":{"resolver":"https://pith.science/pith/37Y7BHDOCCLHDJ5Q5NFVVH2KB5","bundle":"https://pith.science/pith/37Y7BHDOCCLHDJ5Q5NFVVH2KB5/bundle.json","state":"https://pith.science/pith/37Y7BHDOCCLHDJ5Q5NFVVH2KB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37Y7BHDOCCLHDJ5Q5NFVVH2KB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:37Y7BHDOCCLHDJ5Q5NFVVH2KB5","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":"6bfc143f1e67379ad3f2f57f3426b318b6e2def8c83fb24ecd76dca85764a3f2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-01-30T02:08:51Z","title_canon_sha256":"28b24d984027f7bf1ae1ab921f5d8a8e10767dbbabc7fe123d2d4a7104b45a3a"},"schema_version":"1.0","source":{"id":"1501.07645","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.07645","created_at":"2026-05-18T02:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"1501.07645v2","created_at":"2026-05-18T02:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.07645","created_at":"2026-05-18T02:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"37Y7BHDOCCLH","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"37Y7BHDOCCLHDJ5Q","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"37Y7BHDO","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:4ac124a0dc895e086800e9ce243174fd535ea24733dd0d2a08b3bc03ab8e2726","target":"graph","created_at":"2026-05-18T02:07:26Z","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":"Recently sequential model based optimization (SMBO) has emerged as a promising hyper-parameter optimization strategy in machine learning. In this work, we investigate SMBO to identify architecture hyper-parameters of deep convolution networks (DCNs) object recognition. We propose a simple SMBO strategy that starts from a set of random initial DCN architectures to generate new architectures, which on training perform well on a given dataset. Using the proposed SMBO strategy we are able to identify a number of DCN architectures that produce results that are comparable to state-of-the-art results","authors_text":"Sachin S. Talathi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-01-30T02:08:51Z","title":"Hyper-parameter optimization of Deep Convolutional Networks for object recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.07645","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:e236b6eccb7d998934f831133754e66e9f22c6bbbb06874a0347c40df39d0e36","target":"record","created_at":"2026-05-18T02:07:26Z","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":"6bfc143f1e67379ad3f2f57f3426b318b6e2def8c83fb24ecd76dca85764a3f2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-01-30T02:08:51Z","title_canon_sha256":"28b24d984027f7bf1ae1ab921f5d8a8e10767dbbabc7fe123d2d4a7104b45a3a"},"schema_version":"1.0","source":{"id":"1501.07645","kind":"arxiv","version":2}},"canonical_sha256":"dff1f09c6e109671a7b0eb4b5a9f4a0f70a0fc28508e968737b720e2c88d354f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dff1f09c6e109671a7b0eb4b5a9f4a0f70a0fc28508e968737b720e2c88d354f","first_computed_at":"2026-05-18T02:07:26.531405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:07:26.531405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qXXagwpGOG8jlzCx4/J6s/kKS24Xt+gVHIo7FTa1IgyD92c0Hww4OFuCa1Sp+6lQIF9DYxHy/HlndzBU3ZdxBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:07:26.531871Z","signed_message":"canonical_sha256_bytes"},"source_id":"1501.07645","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e236b6eccb7d998934f831133754e66e9f22c6bbbb06874a0347c40df39d0e36","sha256:4ac124a0dc895e086800e9ce243174fd535ea24733dd0d2a08b3bc03ab8e2726"],"state_sha256":"b6b48a8be23c44611423b13fb7dfeab5da5e845d2d71658edde66201b8532db6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/HNMEsyTPlVncVmueQTN9GdyqG990HyPfCYWRj8RlJNKifAFM9lkUZXOPiX8VCOFOSUeIlUZmkgOgHJV4LeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T15:31:40.196738Z","bundle_sha256":"2dd5e65b206dd81c9009cc8702696b221900573dedfbc6a90dc651b22ec80da3"}}