{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:K65QSWEO2HBCWVW3VMBM3G2LM4","short_pith_number":"pith:K65QSWEO","canonical_record":{"source":{"id":"1611.06148","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-18T16:20:41Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"3dba8fe25acec9ac75e0b38d712ed94609c86704a12235b86a4cbe0b980f63c8","abstract_canon_sha256":"484963e340eac8d722ea922044652ee39f1d18ec20962cc08cd2590c98745369"},"schema_version":"1.0"},"canonical_sha256":"57bb09588ed1c22b56dbab02cd9b4b672bc5481ac0333a06f25dd422112c84e3","source":{"kind":"arxiv","id":"1611.06148","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06148","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06148v2","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06148","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"K65QSWEO2HBC","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K65QSWEO2HBCWVW3","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K65QSWEO","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:K65QSWEO2HBCWVW3VMBM3G2LM4","target":"record","payload":{"canonical_record":{"source":{"id":"1611.06148","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-18T16:20:41Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"3dba8fe25acec9ac75e0b38d712ed94609c86704a12235b86a4cbe0b980f63c8","abstract_canon_sha256":"484963e340eac8d722ea922044652ee39f1d18ec20962cc08cd2590c98745369"},"schema_version":"1.0"},"canonical_sha256":"57bb09588ed1c22b56dbab02cd9b4b672bc5481ac0333a06f25dd422112c84e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:45.229168Z","signature_b64":"zCgrdxfnLBxH8rwnK3IovUTEyNh60IuXmIFkBIr67f+0WaaHxsziSWf3CPE2YuNmQtf9ZaOO3sS8G9v+WkllCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57bb09588ed1c22b56dbab02cd9b4b672bc5481ac0333a06f25dd422112c84e3","last_reissued_at":"2026-05-18T00:43:45.228355Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:45.228355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.06148","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":"2026-05-18T00:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GjZIwJe70t6XWAGuWl0Jj1uanxsZAP/qhvJ/Sy74YUrrV4J0C8RkCp5AnTWc038KoGzVUCSKpwPo8h9sDpKPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:54:50.240501Z"},"content_sha256":"e702a08fcb37e93a855040f3a6f20ac31dce987dc862e5424b537fcfbba8abc6","schema_version":"1.0","event_id":"sha256:e702a08fcb37e93a855040f3a6f20ac31dce987dc862e5424b537fcfbba8abc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:K65QSWEO2HBCWVW3VMBM3G2LM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compacting Neural Network Classifiers via Dropout Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"George Tucker, Simon Wiesler, Yotaro Kubo","submitted_at":"2016-11-18T16:20:41Z","abstract_excerpt":"We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network for run-time efficiency. In the proposed method, we introduce a sparsity-inducing prior on the per unit dropout retention probability so that the optimizer can effectively prune hidden units during training. By changing the prior hyperparameters, we can control the size of the resulting network. We performed a systematic comparison of dropout compaction and competing methods on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06148","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":"2026-05-18T00:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FWAA9KUfwV01p6L3FZNJ3y3XB6H0YeQtujJVGqFCkteBr8pS+KEV9Tum4TFE3K71gOKxzo0kTt3T7M2I/eJzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:54:50.241209Z"},"content_sha256":"405922b1ef013d32333f3389d2083b64a63a6d9d930312f53c06e50128e593ac","schema_version":"1.0","event_id":"sha256:405922b1ef013d32333f3389d2083b64a63a6d9d930312f53c06e50128e593ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K65QSWEO2HBCWVW3VMBM3G2LM4/bundle.json","state_url":"https://pith.science/pith/K65QSWEO2HBCWVW3VMBM3G2LM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K65QSWEO2HBCWVW3VMBM3G2LM4/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":"2026-05-26T20:54:50Z","links":{"resolver":"https://pith.science/pith/K65QSWEO2HBCWVW3VMBM3G2LM4","bundle":"https://pith.science/pith/K65QSWEO2HBCWVW3VMBM3G2LM4/bundle.json","state":"https://pith.science/pith/K65QSWEO2HBCWVW3VMBM3G2LM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K65QSWEO2HBCWVW3VMBM3G2LM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:K65QSWEO2HBCWVW3VMBM3G2LM4","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":"484963e340eac8d722ea922044652ee39f1d18ec20962cc08cd2590c98745369","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-18T16:20:41Z","title_canon_sha256":"3dba8fe25acec9ac75e0b38d712ed94609c86704a12235b86a4cbe0b980f63c8"},"schema_version":"1.0","source":{"id":"1611.06148","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06148","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06148v2","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06148","created_at":"2026-05-18T00:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"K65QSWEO2HBC","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K65QSWEO2HBCWVW3","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K65QSWEO","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:405922b1ef013d32333f3389d2083b64a63a6d9d930312f53c06e50128e593ac","target":"graph","created_at":"2026-05-18T00:43:45Z","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":"We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network for run-time efficiency. In the proposed method, we introduce a sparsity-inducing prior on the per unit dropout retention probability so that the optimizer can effectively prune hidden units during training. By changing the prior hyperparameters, we can control the size of the resulting network. We performed a systematic comparison of dropout compaction and competing methods on","authors_text":"George Tucker, Simon Wiesler, Yotaro Kubo","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-18T16:20:41Z","title":"Compacting Neural Network Classifiers via Dropout Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06148","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:e702a08fcb37e93a855040f3a6f20ac31dce987dc862e5424b537fcfbba8abc6","target":"record","created_at":"2026-05-18T00:43:45Z","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":"484963e340eac8d722ea922044652ee39f1d18ec20962cc08cd2590c98745369","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-18T16:20:41Z","title_canon_sha256":"3dba8fe25acec9ac75e0b38d712ed94609c86704a12235b86a4cbe0b980f63c8"},"schema_version":"1.0","source":{"id":"1611.06148","kind":"arxiv","version":2}},"canonical_sha256":"57bb09588ed1c22b56dbab02cd9b4b672bc5481ac0333a06f25dd422112c84e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57bb09588ed1c22b56dbab02cd9b4b672bc5481ac0333a06f25dd422112c84e3","first_computed_at":"2026-05-18T00:43:45.228355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:45.228355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zCgrdxfnLBxH8rwnK3IovUTEyNh60IuXmIFkBIr67f+0WaaHxsziSWf3CPE2YuNmQtf9ZaOO3sS8G9v+WkllCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:45.229168Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.06148","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e702a08fcb37e93a855040f3a6f20ac31dce987dc862e5424b537fcfbba8abc6","sha256:405922b1ef013d32333f3389d2083b64a63a6d9d930312f53c06e50128e593ac"],"state_sha256":"314c9e462174d46f5cd71d261edf87b999dd8aeb1331249b34de015763ce2fb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qpb83WfByrkk/zTDItZ/x/VroEMaOW8cjpT/EbFkCK4irZImmKq90jYfyRK0wIasaNTDVSaejg3SPs97rlPwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:54:50.244705Z","bundle_sha256":"66d2fec1fc920d9745665b5694df2b86594b1fe45215afbda59702141f01eee4"}}