{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UM24OJY7KOGQFQP5ODY4O76THO","short_pith_number":"pith:UM24OJY7","canonical_record":{"source":{"id":"2501.18530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-01-30T17:56:52Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"79cee65dc493565966c7b1d3566acd8e33e32d6769d29ee7dd868a2ddfde0310","abstract_canon_sha256":"c6c64ac85d26aa615ea3fe9e7f6fc70b648cdd46fbd544daedafefe77f0a0938"},"schema_version":"1.0"},"canonical_sha256":"a335c7271f538d02c1fd70f1c77fd33b854a0b23c81a01f0c30aca2812883045","source":{"kind":"arxiv","id":"2501.18530","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18530","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18530v2","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18530","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"pith_short_12","alias_value":"UM24OJY7KOGQ","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"pith_short_16","alias_value":"UM24OJY7KOGQFQP5","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"pith_short_8","alias_value":"UM24OJY7","created_at":"2026-07-05T10:42:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UM24OJY7KOGQFQP5ODY4O76THO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-01-30T17:56:52Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"79cee65dc493565966c7b1d3566acd8e33e32d6769d29ee7dd868a2ddfde0310","abstract_canon_sha256":"c6c64ac85d26aa615ea3fe9e7f6fc70b648cdd46fbd544daedafefe77f0a0938"},"schema_version":"1.0"},"canonical_sha256":"a335c7271f538d02c1fd70f1c77fd33b854a0b23c81a01f0c30aca2812883045","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:42.827553Z","signature_b64":"Zd9lCfyU3toTLexlvva+0FT1v+t9LDCQtg67rhvxwlpAEw4JSeoINnl7e0r9eeZNSadYHtQaCvg/hLO3p335Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a335c7271f538d02c1fd70f1c77fd33b854a0b23c81a01f0c30aca2812883045","last_reissued_at":"2026-07-05T10:42:42.827033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:42.827033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18530","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":"2026-07-05T10:42:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C14UTcI8OR981oLWg0idnKjqsx+CoK1pLN/s/D5dW1SNdHfjTmNUwd3sJHh0izLxnuT63hcyxnr+X1M7D+kPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:48:09.297294Z"},"content_sha256":"717c13379bdf42f0132f3f40d4c1d9ed9fc7bbb49fc412fff486afbab4f44e7c","schema_version":"1.0","event_id":"sha256:717c13379bdf42f0132f3f40d4c1d9ed9fc7bbb49fc412fff486afbab4f44e7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UM24OJY7KOGQFQP5ODY4O76THO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Francesco Camilli, Jean Barbier, Mauro Pastore, Minh-Toan Nguyen, Rudy Skerk","submitted_at":"2025-01-30T17:56:52Z","abstract_excerpt":"We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width $k$ and input dimension $d$ are large and proportional. We provide an effective theory for approximating the Bayes-optimal generalisation error of the network for any activation function in the regime of sample size $n$ scaling quadratically with the input dimension, i.e., around the interpolation threshold where the number of trainable parameters $kd+k$ and of data $n$ are comparable. Our analysis tackles generic weight distributions. We uncover a discontinuous phase transition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18530","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/2501.18530/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":"2026-07-05T10:42:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HvnjO4JjgoGS5xtEoVXYVOU+KKrasuOny+HJJFIZEoAWu1MObzCrhZZF9SUr5TBV7V1zNtQBbvhHbNqKwl5IAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:48:09.297847Z"},"content_sha256":"f4979015d2f1bb022544c40d636947ee64810ffb45ebe49c9c78151beefed7cd","schema_version":"1.0","event_id":"sha256:f4979015d2f1bb022544c40d636947ee64810ffb45ebe49c9c78151beefed7cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UM24OJY7KOGQFQP5ODY4O76THO/bundle.json","state_url":"https://pith.science/pith/UM24OJY7KOGQFQP5ODY4O76THO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UM24OJY7KOGQFQP5ODY4O76THO/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":"2026-08-08T21:48:09Z","links":{"resolver":"https://pith.science/pith/UM24OJY7KOGQFQP5ODY4O76THO","bundle":"https://pith.science/pith/UM24OJY7KOGQFQP5ODY4O76THO/bundle.json","state":"https://pith.science/pith/UM24OJY7KOGQFQP5ODY4O76THO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UM24OJY7KOGQFQP5ODY4O76THO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UM24OJY7KOGQFQP5ODY4O76THO","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":"c6c64ac85d26aa615ea3fe9e7f6fc70b648cdd46fbd544daedafefe77f0a0938","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-01-30T17:56:52Z","title_canon_sha256":"79cee65dc493565966c7b1d3566acd8e33e32d6769d29ee7dd868a2ddfde0310"},"schema_version":"1.0","source":{"id":"2501.18530","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18530","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18530v2","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18530","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"pith_short_12","alias_value":"UM24OJY7KOGQ","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"pith_short_16","alias_value":"UM24OJY7KOGQFQP5","created_at":"2026-07-05T10:42:42Z"},{"alias_kind":"pith_short_8","alias_value":"UM24OJY7","created_at":"2026-07-05T10:42:42Z"}],"graph_snapshots":[{"event_id":"sha256:f4979015d2f1bb022544c40d636947ee64810ffb45ebe49c9c78151beefed7cd","target":"graph","created_at":"2026-07-05T10:42:42Z","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/2501.18530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width $k$ and input dimension $d$ are large and proportional. We provide an effective theory for approximating the Bayes-optimal generalisation error of the network for any activation function in the regime of sample size $n$ scaling quadratically with the input dimension, i.e., around the interpolation threshold where the number of trainable parameters $kd+k$ and of data $n$ are comparable. Our analysis tackles generic weight distributions. We uncover a discontinuous phase transition","authors_text":"Francesco Camilli, Jean Barbier, Mauro Pastore, Minh-Toan Nguyen, Rudy Skerk","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.IT","cs.LG","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-01-30T17:56:52Z","title":"Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18530","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":"sha256:717c13379bdf42f0132f3f40d4c1d9ed9fc7bbb49fc412fff486afbab4f44e7c","target":"record","created_at":"2026-07-05T10:42:42Z","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":"c6c64ac85d26aa615ea3fe9e7f6fc70b648cdd46fbd544daedafefe77f0a0938","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-01-30T17:56:52Z","title_canon_sha256":"79cee65dc493565966c7b1d3566acd8e33e32d6769d29ee7dd868a2ddfde0310"},"schema_version":"1.0","source":{"id":"2501.18530","kind":"arxiv","version":2}},"canonical_sha256":"a335c7271f538d02c1fd70f1c77fd33b854a0b23c81a01f0c30aca2812883045","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a335c7271f538d02c1fd70f1c77fd33b854a0b23c81a01f0c30aca2812883045","first_computed_at":"2026-07-05T10:42:42.827033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:42.827033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zd9lCfyU3toTLexlvva+0FT1v+t9LDCQtg67rhvxwlpAEw4JSeoINnl7e0r9eeZNSadYHtQaCvg/hLO3p335Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:42.827553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18530","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:717c13379bdf42f0132f3f40d4c1d9ed9fc7bbb49fc412fff486afbab4f44e7c","sha256:f4979015d2f1bb022544c40d636947ee64810ffb45ebe49c9c78151beefed7cd"],"state_sha256":"a769c4ab029a8533b144577867949f4f4dfe6ca1694e61a5004770578b2dfeee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3GGe/bQqD0d8poDA8o4H1DQEbT1CPoLJLGHPVf+BQ3yGljNrfuHR1rPBMSVRX6ISIBQyvw0UqMD335gGKLfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:48:09.303614Z","bundle_sha256":"d25fa55e4f596e7742ab07e839521195299ce348f1b5af8cdc2dbb853659df4c"}}