{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TQ3LW63UC7L25OJEXZEXB5QUMH","short_pith_number":"pith:TQ3LW63U","canonical_record":{"source":{"id":"1810.06049","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-14T15:50:21Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"d91a745c1a03d35d7799a2ad229d855e387c05d361ff72fbba0767ac3f633e9a","abstract_canon_sha256":"1b8aa54d2242fecdaa13cdcc73c6d7e36eac4bea6dca1b404ebde276bf0b8e74"},"schema_version":"1.0"},"canonical_sha256":"9c36bb7b7417d7aeb924be4970f61461c024ed9d3315f1e9c7c678e75fa2d87a","source":{"kind":"arxiv","id":"1810.06049","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06049","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06049v4","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06049","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"TQ3LW63UC7L2","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"TQ3LW63UC7L25OJE","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"TQ3LW63U","created_at":"2026-07-05T01:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TQ3LW63UC7L25OJEXZEXB5QUMH","target":"record","payload":{"canonical_record":{"source":{"id":"1810.06049","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-14T15:50:21Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"d91a745c1a03d35d7799a2ad229d855e387c05d361ff72fbba0767ac3f633e9a","abstract_canon_sha256":"1b8aa54d2242fecdaa13cdcc73c6d7e36eac4bea6dca1b404ebde276bf0b8e74"},"schema_version":"1.0"},"canonical_sha256":"9c36bb7b7417d7aeb924be4970f61461c024ed9d3315f1e9c7c678e75fa2d87a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:16.762896Z","signature_b64":"M+gs2f4wUp2qxvTYjyZzfZNg4K9WPmELdpc9UpcOqR0NFJUNzqQds2PxNForihRRLIRE+mL9Nz/7dJRhXGs9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c36bb7b7417d7aeb924be4970f61461c024ed9d3315f1e9c7c678e75fa2d87a","last_reissued_at":"2026-07-05T01:28:16.762536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:16.762536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.06049","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3GHX9Qnnz/Ies5W2iYCtZzdufZGL1zALaFqBYAGfPBnpx92L0VhorQEjaRw7HtRenUX6hjqfv3aNHa2V8mPoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:13:24.596876Z"},"content_sha256":"a6e7b35edfafc016517a39a2ae6c891ad4606529df2376d81efeed4f81cb6f14","schema_version":"1.0","event_id":"sha256:a6e7b35edfafc016517a39a2ae6c891ad4606529df2376d81efeed4f81cb6f14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TQ3LW63UC7L25OJEXZEXB5QUMH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An ETF view of Dropout regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dor Bank, Raja Giryes","submitted_at":"2018-10-14T15:50:21Z","abstract_excerpt":"Dropout is a popular regularization technique in deep learning. Yet, the reason for its success is still not fully understood. This paper provides a new interpretation of Dropout from a frame theory perspective. By drawing a connection to recent developments in analog channel coding, we suggest that for a certain family of autoencoders with a linear encoder, optimizing the encoder with dropout regularization leads to an equiangular tight frame (ETF). Since this optimization is non-convex, we add another regularization that promotes such structures by minimizing the cross-correlation between fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06049","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.06049/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GhoHLFAs3PbKJhR9Mku1R+jcbOIBkqSiiEzDqRCaCZwyBih8K5DTRr/X3imediRUED90x4tgfQSw7z3jrLXlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:13:24.597255Z"},"content_sha256":"e8711953288e2caf55b75322a30540b717fc689a4c75d4c4091fe95302d3ae6b","schema_version":"1.0","event_id":"sha256:e8711953288e2caf55b75322a30540b717fc689a4c75d4c4091fe95302d3ae6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQ3LW63UC7L25OJEXZEXB5QUMH/bundle.json","state_url":"https://pith.science/pith/TQ3LW63UC7L25OJEXZEXB5QUMH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQ3LW63UC7L25OJEXZEXB5QUMH/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":"2026-07-06T09:13:24Z","links":{"resolver":"https://pith.science/pith/TQ3LW63UC7L25OJEXZEXB5QUMH","bundle":"https://pith.science/pith/TQ3LW63UC7L25OJEXZEXB5QUMH/bundle.json","state":"https://pith.science/pith/TQ3LW63UC7L25OJEXZEXB5QUMH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQ3LW63UC7L25OJEXZEXB5QUMH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TQ3LW63UC7L25OJEXZEXB5QUMH","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":"1b8aa54d2242fecdaa13cdcc73c6d7e36eac4bea6dca1b404ebde276bf0b8e74","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-14T15:50:21Z","title_canon_sha256":"d91a745c1a03d35d7799a2ad229d855e387c05d361ff72fbba0767ac3f633e9a"},"schema_version":"1.0","source":{"id":"1810.06049","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06049","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06049v4","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06049","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"TQ3LW63UC7L2","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"TQ3LW63UC7L25OJE","created_at":"2026-07-05T01:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"TQ3LW63U","created_at":"2026-07-05T01:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:e8711953288e2caf55b75322a30540b717fc689a4c75d4c4091fe95302d3ae6b","target":"graph","created_at":"2026-07-05T01:28:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1810.06049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dropout is a popular regularization technique in deep learning. Yet, the reason for its success is still not fully understood. This paper provides a new interpretation of Dropout from a frame theory perspective. By drawing a connection to recent developments in analog channel coding, we suggest that for a certain family of autoencoders with a linear encoder, optimizing the encoder with dropout regularization leads to an equiangular tight frame (ETF). Since this optimization is non-convex, we add another regularization that promotes such structures by minimizing the cross-correlation between fi","authors_text":"Dor Bank, Raja Giryes","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-14T15:50:21Z","title":"An ETF view of Dropout regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06049","kind":"arxiv","version":4},"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:a6e7b35edfafc016517a39a2ae6c891ad4606529df2376d81efeed4f81cb6f14","target":"record","created_at":"2026-07-05T01:28:16Z","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":"1b8aa54d2242fecdaa13cdcc73c6d7e36eac4bea6dca1b404ebde276bf0b8e74","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-14T15:50:21Z","title_canon_sha256":"d91a745c1a03d35d7799a2ad229d855e387c05d361ff72fbba0767ac3f633e9a"},"schema_version":"1.0","source":{"id":"1810.06049","kind":"arxiv","version":4}},"canonical_sha256":"9c36bb7b7417d7aeb924be4970f61461c024ed9d3315f1e9c7c678e75fa2d87a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c36bb7b7417d7aeb924be4970f61461c024ed9d3315f1e9c7c678e75fa2d87a","first_computed_at":"2026-07-05T01:28:16.762536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:16.762536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M+gs2f4wUp2qxvTYjyZzfZNg4K9WPmELdpc9UpcOqR0NFJUNzqQds2PxNForihRRLIRE+mL9Nz/7dJRhXGs9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:16.762896Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06049","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6e7b35edfafc016517a39a2ae6c891ad4606529df2376d81efeed4f81cb6f14","sha256:e8711953288e2caf55b75322a30540b717fc689a4c75d4c4091fe95302d3ae6b"],"state_sha256":"bb9686b8f17a6f6d6f82d4bd2ab96c9bde4dbc455e9dd72601c1187ede608068"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iDsY3cin/Ss8O5QGz1N6D5J26mR+TGTR3Z1PxiJvOisegxoPPeYw9PBkH2I/ZikAEdk4tojVRQRDOYQQjFmKDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T09:13:24.599183Z","bundle_sha256":"c18b8391a21d837a11aa7b9c1cec183dbda09e2dc4c5ae3f353649d79e5fbf01"}}