{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4WG4V3PZ2XH4L3TE7RDON6LM5I","short_pith_number":"pith:4WG4V3PZ","canonical_record":{"source":{"id":"2406.03260","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-05T13:37:42Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"e14729f48e583a7dd6c81b6b3ae61bcbfca0f921168b7e134b153cb7d2f85b42","abstract_canon_sha256":"6ccd8583ecb7fb9bc8bcbc69b5f10386e26e152e3b852b40ddba043c6d4b03d8"},"schema_version":"1.0"},"canonical_sha256":"e58dcaedf9d5cfc5ee64fc46e6f96cea3f074fba0bd483fc835c52ee998986be","source":{"kind":"arxiv","id":"2406.03260","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03260","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03260v3","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03260","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"4WG4V3PZ2XH4","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"4WG4V3PZ2XH4L3TE","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"4WG4V3PZ","created_at":"2026-07-05T11:26:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4WG4V3PZ2XH4L3TE7RDON6LM5I","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03260","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-05T13:37:42Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"e14729f48e583a7dd6c81b6b3ae61bcbfca0f921168b7e134b153cb7d2f85b42","abstract_canon_sha256":"6ccd8583ecb7fb9bc8bcbc69b5f10386e26e152e3b852b40ddba043c6d4b03d8"},"schema_version":"1.0"},"canonical_sha256":"e58dcaedf9d5cfc5ee64fc46e6f96cea3f074fba0bd483fc835c52ee998986be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:42.737870Z","signature_b64":"Yqtg29eeBXKkbiYvhsveAtJjiVr8XZIXlJP+/8+6HF/XdkBhasgdZrSX72faaMoqSqKpF6uPIFi9yUtHdYAkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e58dcaedf9d5cfc5ee64fc46e6f96cea3f074fba0bd483fc835c52ee998986be","last_reissued_at":"2026-07-05T11:26:42.737388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:42.737388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03260","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":"2026-07-05T11:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r8pnix8OYdCZhXzZYzPrDt2co2H9ZiH1ISD9kvUO4SLY/0GdWg9GSMRHvOvoAqCOA+Un0myDLaFeTCBYw8RBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:26:10.959763Z"},"content_sha256":"017b328b4ca7e59508776c4ecdb5e333e3ab1f289fafc4c2dcbd78d693ab3f37","schema_version":"1.0","event_id":"sha256:017b328b4ca7e59508776c4ecdb5e333e3ab1f289fafc4c2dcbd78d693ab3f37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4WG4V3PZ2XH4L3TE7RDON6LM5I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alessandro Ingrosso, Federico Bassetti, Marco Gherardi, Mauro Pastore, Pietro Rotondo","submitted_at":"2024-06-05T13:37:42Z","abstract_excerpt":"Deep linear networks have been extensively studied, as they provide simplified models of deep learning. However, little is known in the case of finite-width architectures with multiple outputs and convolutional layers. In this manuscript, we provide rigorous results for the statistics of functions implemented by the aforementioned class of networks, thus moving closer to a complete characterization of feature learning in the Bayesian setting. Our results include: (i) an exact and elementary non-asymptotic integral representation for the joint prior distribution over the outputs, given in terms"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03260","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.03260/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":"2026-07-05T11:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cULETmk9YBl9F2bAmi2CmGvc9bM9rLZLsPA7aYkW1UL1MiORUeMrLykYgV1B+nE1v0mkct7y1sT/l/02aBYuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:26:10.960271Z"},"content_sha256":"bcd18efe63f1db2de68747aa819074143d9c3f4b72d8f1d8d06ea01d68a48ac3","schema_version":"1.0","event_id":"sha256:bcd18efe63f1db2de68747aa819074143d9c3f4b72d8f1d8d06ea01d68a48ac3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WG4V3PZ2XH4L3TE7RDON6LM5I/bundle.json","state_url":"https://pith.science/pith/4WG4V3PZ2XH4L3TE7RDON6LM5I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WG4V3PZ2XH4L3TE7RDON6LM5I/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":"2026-08-10T03:26:10Z","links":{"resolver":"https://pith.science/pith/4WG4V3PZ2XH4L3TE7RDON6LM5I","bundle":"https://pith.science/pith/4WG4V3PZ2XH4L3TE7RDON6LM5I/bundle.json","state":"https://pith.science/pith/4WG4V3PZ2XH4L3TE7RDON6LM5I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WG4V3PZ2XH4L3TE7RDON6LM5I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4WG4V3PZ2XH4L3TE7RDON6LM5I","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":"6ccd8583ecb7fb9bc8bcbc69b5f10386e26e152e3b852b40ddba043c6d4b03d8","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-05T13:37:42Z","title_canon_sha256":"e14729f48e583a7dd6c81b6b3ae61bcbfca0f921168b7e134b153cb7d2f85b42"},"schema_version":"1.0","source":{"id":"2406.03260","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03260","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03260v3","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03260","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"4WG4V3PZ2XH4","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"4WG4V3PZ2XH4L3TE","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"4WG4V3PZ","created_at":"2026-07-05T11:26:42Z"}],"graph_snapshots":[{"event_id":"sha256:bcd18efe63f1db2de68747aa819074143d9c3f4b72d8f1d8d06ea01d68a48ac3","target":"graph","created_at":"2026-07-05T11:26:42Z","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/2406.03260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep linear networks have been extensively studied, as they provide simplified models of deep learning. However, little is known in the case of finite-width architectures with multiple outputs and convolutional layers. In this manuscript, we provide rigorous results for the statistics of functions implemented by the aforementioned class of networks, thus moving closer to a complete characterization of feature learning in the Bayesian setting. Our results include: (i) an exact and elementary non-asymptotic integral representation for the joint prior distribution over the outputs, given in terms","authors_text":"Alessandro Ingrosso, Federico Bassetti, Marco Gherardi, Mauro Pastore, Pietro Rotondo","cross_cats":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-05T13:37:42Z","title":"Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03260","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":"sha256:017b328b4ca7e59508776c4ecdb5e333e3ab1f289fafc4c2dcbd78d693ab3f37","target":"record","created_at":"2026-07-05T11:26:42Z","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":"6ccd8583ecb7fb9bc8bcbc69b5f10386e26e152e3b852b40ddba043c6d4b03d8","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-05T13:37:42Z","title_canon_sha256":"e14729f48e583a7dd6c81b6b3ae61bcbfca0f921168b7e134b153cb7d2f85b42"},"schema_version":"1.0","source":{"id":"2406.03260","kind":"arxiv","version":3}},"canonical_sha256":"e58dcaedf9d5cfc5ee64fc46e6f96cea3f074fba0bd483fc835c52ee998986be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e58dcaedf9d5cfc5ee64fc46e6f96cea3f074fba0bd483fc835c52ee998986be","first_computed_at":"2026-07-05T11:26:42.737388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:42.737388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yqtg29eeBXKkbiYvhsveAtJjiVr8XZIXlJP+/8+6HF/XdkBhasgdZrSX72faaMoqSqKpF6uPIFi9yUtHdYAkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:42.737870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03260","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:017b328b4ca7e59508776c4ecdb5e333e3ab1f289fafc4c2dcbd78d693ab3f37","sha256:bcd18efe63f1db2de68747aa819074143d9c3f4b72d8f1d8d06ea01d68a48ac3"],"state_sha256":"cc300770cef156ce990a85461d39322ee7ef6597c437ce9f2755ca7d04cbd855"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0p8rNUZobfPtniMUVXl9eQLXw6SVr7b0CC1x/pHWka7kmlZkf0g8Tsb38WJCTOZlJBwyNxfCLyo4rkHYLc+HCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:26:10.964360Z","bundle_sha256":"a9647763e60834bdbaa7bd437471bb430cc57eb400e18617acc5d643fff92385"}}