{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AA5BG66W4HNPUQC4WUC532I3MJ","short_pith_number":"pith:AA5BG66W","canonical_record":{"source":{"id":"1902.08673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-02-07T02:21:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"97e4b02dbb1d1ac05ca7767edd4cce740cebfdf414a67b64e68fa00976ab8d53","abstract_canon_sha256":"1e230660fe84b05a6ed48372878982398ec84736a703396aa3f77cee6815c7cd"},"schema_version":"1.0"},"canonical_sha256":"003a137bd6e1dafa405cb505dde91b625bd0661fed620506e1acab7d3992bc60","source":{"kind":"arxiv","id":"1902.08673","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08673","created_at":"2026-05-17T23:52:50Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08673v1","created_at":"2026-05-17T23:52:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08673","created_at":"2026-05-17T23:52:50Z"},{"alias_kind":"pith_short_12","alias_value":"AA5BG66W4HNP","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AA5BG66W4HNPUQC4","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AA5BG66W","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AA5BG66W4HNPUQC4WUC532I3MJ","target":"record","payload":{"canonical_record":{"source":{"id":"1902.08673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-02-07T02:21:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"97e4b02dbb1d1ac05ca7767edd4cce740cebfdf414a67b64e68fa00976ab8d53","abstract_canon_sha256":"1e230660fe84b05a6ed48372878982398ec84736a703396aa3f77cee6815c7cd"},"schema_version":"1.0"},"canonical_sha256":"003a137bd6e1dafa405cb505dde91b625bd0661fed620506e1acab7d3992bc60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:50.420262Z","signature_b64":"clt5Gh++1QyhVY9L1MLJ+nuNSDrDdTpG8TpTUDgH2ViOA6tBQ41k92M+BdiRPDLAJV+qiBgtVGx3sQmlnxX0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"003a137bd6e1dafa405cb505dde91b625bd0661fed620506e1acab7d3992bc60","last_reissued_at":"2026-05-17T23:52:50.419428Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:50.419428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.08673","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":"2026-05-17T23:52:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ous5bqPmGDrbe9Lv1aq8LUCIK1/nNMeOQ+yXttpgkzWNcXXW5eSdFjUMSj6IV3WnCXeFkNfhjG1M70/7d6NzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:06:59.226150Z"},"content_sha256":"cf2b0bc29b5b3c790e3769a9ced6defa3cd382e6ea18248c87ca0fb55855f1ab","schema_version":"1.0","event_id":"sha256:cf2b0bc29b5b3c790e3769a9ced6defa3cd382e6ea18248c87ca0fb55855f1ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AA5BG66W4HNPUQC4WUC532I3MJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ising-Dropout: A Regularization Method for Training and Compression of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Hojjat Salehinejad, Shahrokh Valaee","submitted_at":"2019-02-07T02:21:40Z","abstract_excerpt":"Overfitting is a major problem in training machine learning models, specifically deep neural networks. This problem may be caused by imbalanced datasets and initialization of the model parameters, which conforms the model too closely to the training data and negatively affects the generalization performance of the model for unseen data. The original dropout is a regularization technique to drop hidden units randomly during training. In this paper, we propose an adaptive technique to wisely drop the visible and hidden units in a deep neural network using Ising energy of the network. The prelimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08673","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":"2026-05-17T23:52:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"837qXibkXMS4PokMmtDdx3EQrr9OdQW3FPaa2fkw3odFwL4SFBNg3dsOKDJlg2NQdHK6jAwT8u3HQgJd77gHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:06:59.226509Z"},"content_sha256":"d24bf66d87cc5f3b723590d7cb395ed020579526d4d3041e18580eac5fd76388","schema_version":"1.0","event_id":"sha256:d24bf66d87cc5f3b723590d7cb395ed020579526d4d3041e18580eac5fd76388"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AA5BG66W4HNPUQC4WUC532I3MJ/bundle.json","state_url":"https://pith.science/pith/AA5BG66W4HNPUQC4WUC532I3MJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AA5BG66W4HNPUQC4WUC532I3MJ/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":"2026-06-02T07:06:59Z","links":{"resolver":"https://pith.science/pith/AA5BG66W4HNPUQC4WUC532I3MJ","bundle":"https://pith.science/pith/AA5BG66W4HNPUQC4WUC532I3MJ/bundle.json","state":"https://pith.science/pith/AA5BG66W4HNPUQC4WUC532I3MJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AA5BG66W4HNPUQC4WUC532I3MJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AA5BG66W4HNPUQC4WUC532I3MJ","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":"1e230660fe84b05a6ed48372878982398ec84736a703396aa3f77cee6815c7cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-02-07T02:21:40Z","title_canon_sha256":"97e4b02dbb1d1ac05ca7767edd4cce740cebfdf414a67b64e68fa00976ab8d53"},"schema_version":"1.0","source":{"id":"1902.08673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08673","created_at":"2026-05-17T23:52:50Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08673v1","created_at":"2026-05-17T23:52:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08673","created_at":"2026-05-17T23:52:50Z"},{"alias_kind":"pith_short_12","alias_value":"AA5BG66W4HNP","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AA5BG66W4HNPUQC4","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AA5BG66W","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:d24bf66d87cc5f3b723590d7cb395ed020579526d4d3041e18580eac5fd76388","target":"graph","created_at":"2026-05-17T23:52:50Z","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":"Overfitting is a major problem in training machine learning models, specifically deep neural networks. This problem may be caused by imbalanced datasets and initialization of the model parameters, which conforms the model too closely to the training data and negatively affects the generalization performance of the model for unseen data. The original dropout is a regularization technique to drop hidden units randomly during training. In this paper, we propose an adaptive technique to wisely drop the visible and hidden units in a deep neural network using Ising energy of the network. The prelimi","authors_text":"Hojjat Salehinejad, Shahrokh Valaee","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-02-07T02:21:40Z","title":"Ising-Dropout: A Regularization Method for Training and Compression of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08673","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:cf2b0bc29b5b3c790e3769a9ced6defa3cd382e6ea18248c87ca0fb55855f1ab","target":"record","created_at":"2026-05-17T23:52:50Z","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":"1e230660fe84b05a6ed48372878982398ec84736a703396aa3f77cee6815c7cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-02-07T02:21:40Z","title_canon_sha256":"97e4b02dbb1d1ac05ca7767edd4cce740cebfdf414a67b64e68fa00976ab8d53"},"schema_version":"1.0","source":{"id":"1902.08673","kind":"arxiv","version":1}},"canonical_sha256":"003a137bd6e1dafa405cb505dde91b625bd0661fed620506e1acab7d3992bc60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"003a137bd6e1dafa405cb505dde91b625bd0661fed620506e1acab7d3992bc60","first_computed_at":"2026-05-17T23:52:50.419428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:50.419428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"clt5Gh++1QyhVY9L1MLJ+nuNSDrDdTpG8TpTUDgH2ViOA6tBQ41k92M+BdiRPDLAJV+qiBgtVGx3sQmlnxX0AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:50.420262Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.08673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf2b0bc29b5b3c790e3769a9ced6defa3cd382e6ea18248c87ca0fb55855f1ab","sha256:d24bf66d87cc5f3b723590d7cb395ed020579526d4d3041e18580eac5fd76388"],"state_sha256":"8017159f2235f021c9b25494de1f9f1a06006cab94b6f699af14cfa8d05a51f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qK3M56D0mcMTkcbUPmFUZa2kj/3Mr1t2rOtlHQzYKYsYgywNOzMVljI//yB2M8rRAgN/8Go0iKOY3MjsBFYGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T07:06:59.228503Z","bundle_sha256":"b07a61eab4594ebb4e3579441190cc4906f87156f5b476acc8e51278804740a5"}}