{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:UKUD2T5NNOGW2FCP363LPQDZ6W","short_pith_number":"pith:UKUD2T5N","canonical_record":{"source":{"id":"1611.01353","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-04T12:46:37Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"135e8df82b3f2ea592a36e0097a81403f0fd7a51bbbc3ad35f2d5c39dd08ae56","abstract_canon_sha256":"c78f2b5651629a0105bcbeaf4695cc9ed38996d84fece688a341e5c669aff839"},"schema_version":"1.0"},"canonical_sha256":"a2a83d4fad6b8d6d144fdfb6b7c079f58ee266cfd0924bdbdb0936f859fd6799","source":{"kind":"arxiv","id":"1611.01353","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01353","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01353v3","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01353","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"pith_short_12","alias_value":"UKUD2T5NNOGW","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UKUD2T5NNOGW2FCP","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UKUD2T5N","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:UKUD2T5NNOGW2FCP363LPQDZ6W","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01353","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-04T12:46:37Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"135e8df82b3f2ea592a36e0097a81403f0fd7a51bbbc3ad35f2d5c39dd08ae56","abstract_canon_sha256":"c78f2b5651629a0105bcbeaf4695cc9ed38996d84fece688a341e5c669aff839"},"schema_version":"1.0"},"canonical_sha256":"a2a83d4fad6b8d6d144fdfb6b7c079f58ee266cfd0924bdbdb0936f859fd6799","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:56.417302Z","signature_b64":"ecI0ZYTW+wmEKZYsvoGJ0Ihvt6VVHeb/PiL3ciOLmay8ZS2Vpl9H8fb1UzZ/IJ5QTe3bbbMyF2SSodKxayisCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2a83d4fad6b8d6d144fdfb6b7c079f58ee266cfd0924bdbdb0936f859fd6799","last_reissued_at":"2026-05-18T00:50:56.416671Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:56.416671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01353","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1q6iShrABJF2ChIOK+hL73gPTO51LORK0GfEC9crqmfuka/gUIKuNp+k1xPL95IbYGdboAs3y31g+DtqUkb/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T08:41:36.679597Z"},"content_sha256":"5d84c7ed9798a4000623aeed3ed080d0b37b631f9c84b20bea4938f6dda6148e","schema_version":"1.0","event_id":"sha256:5d84c7ed9798a4000623aeed3ed080d0b37b631f9c84b20bea4938f6dda6148e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:UKUD2T5NNOGW2FCP363LPQDZ6W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information Dropout: Learning Optimal Representations Through Noisy Computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Alessandro Achille, Stefano Soatto","submitted_at":"2016-11-04T12:46:37Z","abstract_excerpt":"The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization term, which is in turn related to injecting multiplicative noise in the activations of a Deep Neural Network, a special case of which is the common practice of dropout. We show that our regularized loss function can be efficiently minimized using Information Dropout, a generalization of dropout rooted in information theoretic principles that automatically adapts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01353","kind":"arxiv","version":3},"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":"2026-05-18T00:50:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzX0mnYTVG1kOCfGSfuvvg2fvLuw2MBeKKQzXdazirBR4YzAUkB1ns5oppN7aU1bFozsabLnhDI7nvbLUYSOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T08:41:36.680355Z"},"content_sha256":"89843c43bb108fd7b69283dd8a2360d0b67dc7d868c7bf492a76b936436c6727","schema_version":"1.0","event_id":"sha256:89843c43bb108fd7b69283dd8a2360d0b67dc7d868c7bf492a76b936436c6727"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKUD2T5NNOGW2FCP363LPQDZ6W/bundle.json","state_url":"https://pith.science/pith/UKUD2T5NNOGW2FCP363LPQDZ6W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKUD2T5NNOGW2FCP363LPQDZ6W/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":"2026-05-19T08:41:36Z","links":{"resolver":"https://pith.science/pith/UKUD2T5NNOGW2FCP363LPQDZ6W","bundle":"https://pith.science/pith/UKUD2T5NNOGW2FCP363LPQDZ6W/bundle.json","state":"https://pith.science/pith/UKUD2T5NNOGW2FCP363LPQDZ6W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKUD2T5NNOGW2FCP363LPQDZ6W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:UKUD2T5NNOGW2FCP363LPQDZ6W","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":"c78f2b5651629a0105bcbeaf4695cc9ed38996d84fece688a341e5c669aff839","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-04T12:46:37Z","title_canon_sha256":"135e8df82b3f2ea592a36e0097a81403f0fd7a51bbbc3ad35f2d5c39dd08ae56"},"schema_version":"1.0","source":{"id":"1611.01353","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01353","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01353v3","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01353","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"pith_short_12","alias_value":"UKUD2T5NNOGW","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UKUD2T5NNOGW2FCP","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UKUD2T5N","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:89843c43bb108fd7b69283dd8a2360d0b67dc7d868c7bf492a76b936436c6727","target":"graph","created_at":"2026-05-18T00:50:56Z","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":"The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization term, which is in turn related to injecting multiplicative noise in the activations of a Deep Neural Network, a special case of which is the common practice of dropout. We show that our regularized loss function can be efficiently minimized using Information Dropout, a generalization of dropout rooted in information theoretic principles that automatically adapts","authors_text":"Alessandro Achille, Stefano Soatto","cross_cats":["cs.LG","stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-04T12:46:37Z","title":"Information Dropout: Learning Optimal Representations Through Noisy Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01353","kind":"arxiv","version":3},"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":"sha256:5d84c7ed9798a4000623aeed3ed080d0b37b631f9c84b20bea4938f6dda6148e","target":"record","created_at":"2026-05-18T00:50:56Z","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":"c78f2b5651629a0105bcbeaf4695cc9ed38996d84fece688a341e5c669aff839","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-04T12:46:37Z","title_canon_sha256":"135e8df82b3f2ea592a36e0097a81403f0fd7a51bbbc3ad35f2d5c39dd08ae56"},"schema_version":"1.0","source":{"id":"1611.01353","kind":"arxiv","version":3}},"canonical_sha256":"a2a83d4fad6b8d6d144fdfb6b7c079f58ee266cfd0924bdbdb0936f859fd6799","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2a83d4fad6b8d6d144fdfb6b7c079f58ee266cfd0924bdbdb0936f859fd6799","first_computed_at":"2026-05-18T00:50:56.416671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:56.416671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ecI0ZYTW+wmEKZYsvoGJ0Ihvt6VVHeb/PiL3ciOLmay8ZS2Vpl9H8fb1UzZ/IJ5QTe3bbbMyF2SSodKxayisCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:56.417302Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01353","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d84c7ed9798a4000623aeed3ed080d0b37b631f9c84b20bea4938f6dda6148e","sha256:89843c43bb108fd7b69283dd8a2360d0b67dc7d868c7bf492a76b936436c6727"],"state_sha256":"11ea06a83efd5f00de877a8b46212ad7c89c860823154045ce5344fe77a668fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"44/MFqFWX179EISjoSmMizB3snTa5d2GMWRqFwDxTdYuR9YlUwjRO+tja/Yao5NwSyTFh2HdTrwFnYQyv8GIAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T08:41:36.683709Z","bundle_sha256":"9171d1a10c60b88c217bdd9cd76ee882d2ef83fadbc727db2e5d842571f5e485"}}