{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q6DSLZUZMSHWPUADGCYVLHIGWY","short_pith_number":"pith:Q6DSLZUZ","canonical_record":{"source":{"id":"2403.10459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T16:51:24Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"16f2a2ceec7e30327d68f414864c201df20fca8dd012d563c5a5959e54b2940d","abstract_canon_sha256":"8d59fbe28b7b90965dcd0b8fd65fa4d6b59a5d613f2511651afb3bc97059de91"},"schema_version":"1.0"},"canonical_sha256":"878725e699648f67d00330b1559d06b60bde97a75d092f12a6a633210abf339d","source":{"kind":"arxiv","id":"2403.10459","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10459","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10459v1","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10459","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"pith_short_12","alias_value":"Q6DSLZUZMSHW","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"pith_short_16","alias_value":"Q6DSLZUZMSHWPUAD","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"pith_short_8","alias_value":"Q6DSLZUZ","created_at":"2026-07-05T07:56:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q6DSLZUZMSHWPUADGCYVLHIGWY","target":"record","payload":{"canonical_record":{"source":{"id":"2403.10459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T16:51:24Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"16f2a2ceec7e30327d68f414864c201df20fca8dd012d563c5a5959e54b2940d","abstract_canon_sha256":"8d59fbe28b7b90965dcd0b8fd65fa4d6b59a5d613f2511651afb3bc97059de91"},"schema_version":"1.0"},"canonical_sha256":"878725e699648f67d00330b1559d06b60bde97a75d092f12a6a633210abf339d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:41.754807Z","signature_b64":"JVwiVSA02YVE6V8WFiBACtKvFea389JQDJP2faYZ0gnorUD4kg3+hWYbXAPeO5agc0LekPziC7G8tROtGGzFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"878725e699648f67d00330b1559d06b60bde97a75d092f12a6a633210abf339d","last_reissued_at":"2026-07-05T07:56:41.754276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:41.754276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.10459","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":"2026-07-05T07:56:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQB/+uvsb9Ftsy2fGuliyqrxGnzY8l+S+BN2rR8j5nkNjcY6DRbpVu0TyYSMAHmSNQWRIWZyUlhaTEU61L8EDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:43:21.145144Z"},"content_sha256":"56d0228e639422106ad8df88b838db13dd1e32bc7d2afcbe52f8d91d9803af31","schema_version":"1.0","event_id":"sha256:56d0228e639422106ad8df88b838db13dd1e32bc7d2afcbe52f8d91d9803af31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q6DSLZUZMSHWPUADGCYVLHIGWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the Double Descent Phenomenon in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Thomas, Marc Lafon","submitted_at":"2024-03-15T16:51:24Z","abstract_excerpt":"Combining empirical risk minimization with capacity control is a classical strategy in machine learning when trying to control the generalization gap and avoid overfitting, as the model class capacity gets larger. Yet, in modern deep learning practice, very large over-parameterized models (e.g. neural networks) are optimized to fit perfectly the training data and still obtain great generalization performance. Past the interpolation point, increasing model complexity seems to actually lower the test error.\n  In this tutorial, we explain the concept of double descent and its mechanisms. The firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10459","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.10459/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":"2026-07-05T07:56:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7bnoAlSwvZ2tPqq4Ej0SEmBHpjCJ9iHeuvds7yImJCozsIuEgmPvqZTN3vCk2Qe5easfEQRKV8GlfQb00UJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:43:21.145531Z"},"content_sha256":"cdc53f54c9177bdaf3cc3afd9f0195ef8cc7f635337054c7295a87394b7b238a","schema_version":"1.0","event_id":"sha256:cdc53f54c9177bdaf3cc3afd9f0195ef8cc7f635337054c7295a87394b7b238a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6DSLZUZMSHWPUADGCYVLHIGWY/bundle.json","state_url":"https://pith.science/pith/Q6DSLZUZMSHWPUADGCYVLHIGWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6DSLZUZMSHWPUADGCYVLHIGWY/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":"2026-08-17T16:43:21Z","links":{"resolver":"https://pith.science/pith/Q6DSLZUZMSHWPUADGCYVLHIGWY","bundle":"https://pith.science/pith/Q6DSLZUZMSHWPUADGCYVLHIGWY/bundle.json","state":"https://pith.science/pith/Q6DSLZUZMSHWPUADGCYVLHIGWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6DSLZUZMSHWPUADGCYVLHIGWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q6DSLZUZMSHWPUADGCYVLHIGWY","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":"8d59fbe28b7b90965dcd0b8fd65fa4d6b59a5d613f2511651afb3bc97059de91","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T16:51:24Z","title_canon_sha256":"16f2a2ceec7e30327d68f414864c201df20fca8dd012d563c5a5959e54b2940d"},"schema_version":"1.0","source":{"id":"2403.10459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10459","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10459v1","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10459","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"pith_short_12","alias_value":"Q6DSLZUZMSHW","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"pith_short_16","alias_value":"Q6DSLZUZMSHWPUAD","created_at":"2026-07-05T07:56:41Z"},{"alias_kind":"pith_short_8","alias_value":"Q6DSLZUZ","created_at":"2026-07-05T07:56:41Z"}],"graph_snapshots":[{"event_id":"sha256:cdc53f54c9177bdaf3cc3afd9f0195ef8cc7f635337054c7295a87394b7b238a","target":"graph","created_at":"2026-07-05T07:56:41Z","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/2403.10459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Combining empirical risk minimization with capacity control is a classical strategy in machine learning when trying to control the generalization gap and avoid overfitting, as the model class capacity gets larger. Yet, in modern deep learning practice, very large over-parameterized models (e.g. neural networks) are optimized to fit perfectly the training data and still obtain great generalization performance. Past the interpolation point, increasing model complexity seems to actually lower the test error.\n  In this tutorial, we explain the concept of double descent and its mechanisms. The firs","authors_text":"Alexandre Thomas, Marc Lafon","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T16:51:24Z","title":"Understanding the Double Descent Phenomenon in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10459","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":"sha256:56d0228e639422106ad8df88b838db13dd1e32bc7d2afcbe52f8d91d9803af31","target":"record","created_at":"2026-07-05T07:56:41Z","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":"8d59fbe28b7b90965dcd0b8fd65fa4d6b59a5d613f2511651afb3bc97059de91","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T16:51:24Z","title_canon_sha256":"16f2a2ceec7e30327d68f414864c201df20fca8dd012d563c5a5959e54b2940d"},"schema_version":"1.0","source":{"id":"2403.10459","kind":"arxiv","version":1}},"canonical_sha256":"878725e699648f67d00330b1559d06b60bde97a75d092f12a6a633210abf339d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"878725e699648f67d00330b1559d06b60bde97a75d092f12a6a633210abf339d","first_computed_at":"2026-07-05T07:56:41.754276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:41.754276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JVwiVSA02YVE6V8WFiBACtKvFea389JQDJP2faYZ0gnorUD4kg3+hWYbXAPeO5agc0LekPziC7G8tROtGGzFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:41.754807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56d0228e639422106ad8df88b838db13dd1e32bc7d2afcbe52f8d91d9803af31","sha256:cdc53f54c9177bdaf3cc3afd9f0195ef8cc7f635337054c7295a87394b7b238a"],"state_sha256":"d66ed5116b4ad50b086455933e0cd239e02a6598f5a6aafd9e282a67a007e2ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TQRokK0iZdScMY1pe4DwcEj2LsQqDv3VUA+K2gpgAtJvsiFTpkplSARKl3KJE/lsyGDhhzgAiFpUJ/XglWnmAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:43:21.148205Z","bundle_sha256":"f56223f963f332f397ecbe335d977b5b2c5c070f01230c3f78245bb4075ac247"}}