{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NUQMBH4DBYYX46NJFBK4NVUOQW","short_pith_number":"pith:NUQMBH4D","canonical_record":{"source":{"id":"2505.07792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T17:45:02Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"1aa4debef8a3827feb771afbdbeea1943bc20b51e0fd63085935dfe0c739290e","abstract_canon_sha256":"ec131baa5a0d21348b7f12acd9fcde09d680d7cb32436cfa648b66d2b686fcc1"},"schema_version":"1.0"},"canonical_sha256":"6d20c09f830e317e79a92855c6d68e85a5c798ac21db2b042833d956f6cf6f4b","source":{"kind":"arxiv","id":"2505.07792","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07792","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07792v2","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07792","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"NUQMBH4DBYYX","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"NUQMBH4DBYYX46NJ","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"NUQMBH4D","created_at":"2026-07-05T12:07:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NUQMBH4DBYYX46NJFBK4NVUOQW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T17:45:02Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"1aa4debef8a3827feb771afbdbeea1943bc20b51e0fd63085935dfe0c739290e","abstract_canon_sha256":"ec131baa5a0d21348b7f12acd9fcde09d680d7cb32436cfa648b66d2b686fcc1"},"schema_version":"1.0"},"canonical_sha256":"6d20c09f830e317e79a92855c6d68e85a5c798ac21db2b042833d956f6cf6f4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:07.053218Z","signature_b64":"+x6na8mrl36Pmz9gsjtodkpBKqq+bFOcFvv8zdGLJlmy1KGmAxfh/93vnY2ndtH35vaoPlWpi/nxxQqL32y5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d20c09f830e317e79a92855c6d68e85a5c798ac21db2b042833d956f6cf6f4b","last_reissued_at":"2026-07-05T12:07:07.052695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:07.052695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07792","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":"2026-07-05T12:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LdqDT5ffTJArGobkYv/ug5svDq20m/eE2E2E2/Y1eN/2czesPhoYdX1zgIRGcsB8Y5+8GqC5I4QvEkehAMC+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:22:12.249611Z"},"content_sha256":"212b7fca3c104ba4922a7840389fb5825129bcde29651375a59021b71b090c86","schema_version":"1.0","event_id":"sha256:212b7fca3c104ba4922a7840389fb5825129bcde29651375a59021b71b090c86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NUQMBH4DBYYX46NJFBK4NVUOQW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analytic theory of dropout regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"primary_cat":"stat.ML","authors_text":"Francesca Mignacco, Francesco Mori","submitted_at":"2025-05-12T17:45:02Z","abstract_excerpt":"Dropout is a regularization technique widely used in training artificial neural networks to mitigate overfitting. It consists of dynamically deactivating subsets of the network during training to promote more robust representations. Despite its widespread adoption, dropout probabilities are often selected heuristically, and theoretical explanations of its success remain sparse. Here, we analytically study dropout in two-layer neural networks trained with online stochastic gradient descent. In the high-dimensional limit, we derive a set of ordinary differential equations that fully characterize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07792","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.07792/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":"2026-07-05T12:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fYaOrRsHqwx8Hc3v0lb2zY+PKw09QPxCQpF4y2zWB9amniwJ8MXQ1VpWpY7KjzoVEOw+tti4JORMPaIT1jhMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:22:12.250122Z"},"content_sha256":"1cb79a56142c98c5c99cb2d52184fbb5602638b93246d700dfb902faf1c3b278","schema_version":"1.0","event_id":"sha256:1cb79a56142c98c5c99cb2d52184fbb5602638b93246d700dfb902faf1c3b278"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NUQMBH4DBYYX46NJFBK4NVUOQW/bundle.json","state_url":"https://pith.science/pith/NUQMBH4DBYYX46NJFBK4NVUOQW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NUQMBH4DBYYX46NJFBK4NVUOQW/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":"2026-08-04T09:22:12Z","links":{"resolver":"https://pith.science/pith/NUQMBH4DBYYX46NJFBK4NVUOQW","bundle":"https://pith.science/pith/NUQMBH4DBYYX46NJFBK4NVUOQW/bundle.json","state":"https://pith.science/pith/NUQMBH4DBYYX46NJFBK4NVUOQW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NUQMBH4DBYYX46NJFBK4NVUOQW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NUQMBH4DBYYX46NJFBK4NVUOQW","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":"ec131baa5a0d21348b7f12acd9fcde09d680d7cb32436cfa648b66d2b686fcc1","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T17:45:02Z","title_canon_sha256":"1aa4debef8a3827feb771afbdbeea1943bc20b51e0fd63085935dfe0c739290e"},"schema_version":"1.0","source":{"id":"2505.07792","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07792","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07792v2","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07792","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"NUQMBH4DBYYX","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"NUQMBH4DBYYX46NJ","created_at":"2026-07-05T12:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"NUQMBH4D","created_at":"2026-07-05T12:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:1cb79a56142c98c5c99cb2d52184fbb5602638b93246d700dfb902faf1c3b278","target":"graph","created_at":"2026-07-05T12:07:07Z","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/2505.07792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dropout is a regularization technique widely used in training artificial neural networks to mitigate overfitting. It consists of dynamically deactivating subsets of the network during training to promote more robust representations. Despite its widespread adoption, dropout probabilities are often selected heuristically, and theoretical explanations of its success remain sparse. Here, we analytically study dropout in two-layer neural networks trained with online stochastic gradient descent. In the high-dimensional limit, we derive a set of ordinary differential equations that fully characterize","authors_text":"Francesca Mignacco, Francesco Mori","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07792","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":"sha256:212b7fca3c104ba4922a7840389fb5825129bcde29651375a59021b71b090c86","target":"record","created_at":"2026-07-05T12:07:07Z","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":"ec131baa5a0d21348b7f12acd9fcde09d680d7cb32436cfa648b66d2b686fcc1","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T17:45:02Z","title_canon_sha256":"1aa4debef8a3827feb771afbdbeea1943bc20b51e0fd63085935dfe0c739290e"},"schema_version":"1.0","source":{"id":"2505.07792","kind":"arxiv","version":2}},"canonical_sha256":"6d20c09f830e317e79a92855c6d68e85a5c798ac21db2b042833d956f6cf6f4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d20c09f830e317e79a92855c6d68e85a5c798ac21db2b042833d956f6cf6f4b","first_computed_at":"2026-07-05T12:07:07.052695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:07.052695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+x6na8mrl36Pmz9gsjtodkpBKqq+bFOcFvv8zdGLJlmy1KGmAxfh/93vnY2ndtH35vaoPlWpi/nxxQqL32y5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:07.053218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07792","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:212b7fca3c104ba4922a7840389fb5825129bcde29651375a59021b71b090c86","sha256:1cb79a56142c98c5c99cb2d52184fbb5602638b93246d700dfb902faf1c3b278"],"state_sha256":"b731ae342ae492a80127de484c034ee7878f1db0cab4639638eaf740c83504e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duiBldx8/wp4xn5DzwIKBiyqHCA4FuZJHb/tgGEzhiGYUPc7Y3WkhkI35GiT7Ao+svUmsUXbyF/ge5dJfFHUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:22:12.253947Z","bundle_sha256":"a997c5c407bf1ce6c343a44738dbfd7e9161159dd81d34718ea53d56391f5569"}}