{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EBIS7FXVKNMDUNV5X2SMSKSNUK","short_pith_number":"pith:EBIS7FXV","canonical_record":{"source":{"id":"1712.00891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T03:29:38Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d8caa8281def5bb6a87da4e2cba0d9885fb7cfdc06015150c3f66c704b17a16c","abstract_canon_sha256":"f3db5ceeb248c220ba795ea68c2019890464c6445ef41458943d2f698f624cfb"},"schema_version":"1.0"},"canonical_sha256":"20512f96f553583a36bdbea4c92a4da2911dbe0bada16697e4ca5ff2fad6c447","source":{"kind":"arxiv","id":"1712.00891","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00891","created_at":"2026-05-18T00:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00891v2","created_at":"2026-05-18T00:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00891","created_at":"2026-05-18T00:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"EBIS7FXVKNMD","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EBIS7FXVKNMDUNV5","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EBIS7FXV","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EBIS7FXVKNMDUNV5X2SMSKSNUK","target":"record","payload":{"canonical_record":{"source":{"id":"1712.00891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T03:29:38Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d8caa8281def5bb6a87da4e2cba0d9885fb7cfdc06015150c3f66c704b17a16c","abstract_canon_sha256":"f3db5ceeb248c220ba795ea68c2019890464c6445ef41458943d2f698f624cfb"},"schema_version":"1.0"},"canonical_sha256":"20512f96f553583a36bdbea4c92a4da2911dbe0bada16697e4ca5ff2fad6c447","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:51.309734Z","signature_b64":"FMtSRlFU1OQgkM3KN2+VUSTFg5VMhiaquaYen+3nrdTzOErdaqJ5k1O5+c2KYwLrPnIAcOZn0i3EgIVT1tSeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20512f96f553583a36bdbea4c92a4da2911dbe0bada16697e4ca5ff2fad6c447","last_reissued_at":"2026-05-18T00:28:51.309231Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:51.309231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.00891","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":"2026-05-18T00:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"baZEX4ZjP3KYRpCtToCJ0bksAmMGfXRsms9eOtjZVjCUrIfpy8FbE9nm/ZH5oYZOhGgHgNu/j4Br/zdMaxlnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:44:57.299477Z"},"content_sha256":"a6d749d416b4948dd891441796739483673d4de433cace633a2e00b0501002de","schema_version":"1.0","event_id":"sha256:a6d749d416b4948dd891441796739483673d4de433cace633a2e00b0501002de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EBIS7FXVKNMDUNV5X2SMSKSNUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Dropout in Arbitrary Basis for Deep Network Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"George Atia, Mostafa Rahmani","submitted_at":"2017-12-04T03:29:38Z","abstract_excerpt":"An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset. Dropout is an effective regularization technique to boost the network generalization in which a random subset of the elements of the given data and the extracted features are set to zero during the training process. In this paper, a new randomized regularization technique in which we withhold a random part of the data without necessarily turning off the neurons/data-elements is proposed. In the proposed method, of which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00891","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":"2026-05-18T00:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qM2pV434lueHGdrHgNyeXo0eD3s/oNsy/Ibq1fi7AobmbrUT3Fq+UOCGY7j3VU1Doq0YtLY/Nz+niCCvlqh5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:44:57.299834Z"},"content_sha256":"9c8b4eabe8812a3682918093c000844a4d6609ca85bddec134e98a945b44356e","schema_version":"1.0","event_id":"sha256:9c8b4eabe8812a3682918093c000844a4d6609ca85bddec134e98a945b44356e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBIS7FXVKNMDUNV5X2SMSKSNUK/bundle.json","state_url":"https://pith.science/pith/EBIS7FXVKNMDUNV5X2SMSKSNUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBIS7FXVKNMDUNV5X2SMSKSNUK/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":"2026-06-01T16:44:57Z","links":{"resolver":"https://pith.science/pith/EBIS7FXVKNMDUNV5X2SMSKSNUK","bundle":"https://pith.science/pith/EBIS7FXVKNMDUNV5X2SMSKSNUK/bundle.json","state":"https://pith.science/pith/EBIS7FXVKNMDUNV5X2SMSKSNUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBIS7FXVKNMDUNV5X2SMSKSNUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EBIS7FXVKNMDUNV5X2SMSKSNUK","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":"f3db5ceeb248c220ba795ea68c2019890464c6445ef41458943d2f698f624cfb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T03:29:38Z","title_canon_sha256":"d8caa8281def5bb6a87da4e2cba0d9885fb7cfdc06015150c3f66c704b17a16c"},"schema_version":"1.0","source":{"id":"1712.00891","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00891","created_at":"2026-05-18T00:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00891v2","created_at":"2026-05-18T00:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00891","created_at":"2026-05-18T00:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"EBIS7FXVKNMD","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EBIS7FXVKNMDUNV5","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EBIS7FXV","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:9c8b4eabe8812a3682918093c000844a4d6609ca85bddec134e98a945b44356e","target":"graph","created_at":"2026-05-18T00:28:51Z","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":"An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset. Dropout is an effective regularization technique to boost the network generalization in which a random subset of the elements of the given data and the extracted features are set to zero during the training process. In this paper, a new randomized regularization technique in which we withhold a random part of the data without necessarily turning off the neurons/data-elements is proposed. In the proposed method, of which ","authors_text":"George Atia, Mostafa Rahmani","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T03:29:38Z","title":"Data Dropout in Arbitrary Basis for Deep Network Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00891","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:a6d749d416b4948dd891441796739483673d4de433cace633a2e00b0501002de","target":"record","created_at":"2026-05-18T00:28:51Z","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":"f3db5ceeb248c220ba795ea68c2019890464c6445ef41458943d2f698f624cfb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T03:29:38Z","title_canon_sha256":"d8caa8281def5bb6a87da4e2cba0d9885fb7cfdc06015150c3f66c704b17a16c"},"schema_version":"1.0","source":{"id":"1712.00891","kind":"arxiv","version":2}},"canonical_sha256":"20512f96f553583a36bdbea4c92a4da2911dbe0bada16697e4ca5ff2fad6c447","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20512f96f553583a36bdbea4c92a4da2911dbe0bada16697e4ca5ff2fad6c447","first_computed_at":"2026-05-18T00:28:51.309231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:51.309231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FMtSRlFU1OQgkM3KN2+VUSTFg5VMhiaquaYen+3nrdTzOErdaqJ5k1O5+c2KYwLrPnIAcOZn0i3EgIVT1tSeCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:51.309734Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00891","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6d749d416b4948dd891441796739483673d4de433cace633a2e00b0501002de","sha256:9c8b4eabe8812a3682918093c000844a4d6609ca85bddec134e98a945b44356e"],"state_sha256":"d9ae429e54e3dff7b0e1ddf3bfb5ff3d4024472c9085bc88d3d1a3de12eff7ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UK1NkOJYJ7P11k6O9h1WcwutmsHDOnRo5QzLxxl7gdcWtlsBBMLzltR/AgFxG9z03RxNj2P9rM16F/JYSM1UDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:44:57.302196Z","bundle_sha256":"d04d03af9358e3565d9b4d105cabcb02664ed91960fb9108d26f18e64a42a7f6"}}