{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:LTNGVW75KGKIAXZEQGAKCZPSU5","short_pith_number":"pith:LTNGVW75","canonical_record":{"source":{"id":"1402.5836","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2014-02-24T14:27:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae93d46bf188092340b3a5ce6ce3a040070610b92ae8fda5c571bba29b963d6d","abstract_canon_sha256":"23700f14b24f77ac1b0a6ecd409141cb89a50ca5f3ad92f2d29913770c4da4f8"},"schema_version":"1.0"},"canonical_sha256":"5cda6adbfd5194805f248180a165f2a7745b9c5fd0ada3241c07ea9880127c59","source":{"kind":"arxiv","id":"1402.5836","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.5836","created_at":"2026-05-18T01:11:18Z"},{"alias_kind":"arxiv_version","alias_value":"1402.5836v3","created_at":"2026-05-18T01:11:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.5836","created_at":"2026-05-18T01:11:18Z"},{"alias_kind":"pith_short_12","alias_value":"LTNGVW75KGKI","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"LTNGVW75KGKIAXZE","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"LTNGVW75","created_at":"2026-05-18T12:28:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:LTNGVW75KGKIAXZEQGAKCZPSU5","target":"record","payload":{"canonical_record":{"source":{"id":"1402.5836","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2014-02-24T14:27:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae93d46bf188092340b3a5ce6ce3a040070610b92ae8fda5c571bba29b963d6d","abstract_canon_sha256":"23700f14b24f77ac1b0a6ecd409141cb89a50ca5f3ad92f2d29913770c4da4f8"},"schema_version":"1.0"},"canonical_sha256":"5cda6adbfd5194805f248180a165f2a7745b9c5fd0ada3241c07ea9880127c59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:18.660578Z","signature_b64":"eLsIWDZarEV9XczitdQMc8fYSYuH/reIvSsMU+KfnqtAsnzBc7TBOn7lgiHCNARTaV9Gh4/nzoxROWJo4EdDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cda6adbfd5194805f248180a165f2a7745b9c5fd0ada3241c07ea9880127c59","last_reissued_at":"2026-05-18T01:11:18.660129Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:18.660129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1402.5836","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":"2026-05-18T01:11:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGp4xTdKAD0BAgegnhlD6Cy5SXeB6Ejhpbe4DUGNvpaUXXIAIpvLfQrI+1m77h0RgubI2QdIEtBLuOS4Gd4BDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:39:34.496881Z"},"content_sha256":"cc6c278fd15785dc2c921b9a570fcc602c1a99dca61d70f99525707b79908e8c","schema_version":"1.0","event_id":"sha256:cc6c278fd15785dc2c921b9a570fcc602c1a99dca61d70f99525707b79908e8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:LTNGVW75KGKIAXZEQGAKCZPSU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Avoiding pathologies in very deep networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David Duvenaud, Oren Rippel, Ryan P. Adams, Zoubin Ghahramani","submitted_at":"2014-02-24T14:27:40Z","abstract_excerpt":"Choosing appropriate architectures and regularization strategies for deep networks is crucial to good predictive performance. To shed light on this problem, we analyze the analogous problem of constructing useful priors on compositions of functions. Specifically, we study the deep Gaussian process, a type of infinitely-wide, deep neural network. We show that in standard architectures, the representational capacity of the network tends to capture fewer degrees of freedom as the number of layers increases, retaining only a single degree of freedom in the limit. We propose an alternate network ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.5836","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":"2026-05-18T01:11:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p3Cj5W/rlVqpmsSgBn9/AmJu58y0XtdLD6Tqumx7gdSPT9puyWNiGq76LUD0tCAUteI7plfNgLed+rv26/nUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:39:34.497222Z"},"content_sha256":"d5abe1703888d350b70e89d6af957fefe11ccf40966ca5e924f953510fa6b63b","schema_version":"1.0","event_id":"sha256:d5abe1703888d350b70e89d6af957fefe11ccf40966ca5e924f953510fa6b63b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTNGVW75KGKIAXZEQGAKCZPSU5/bundle.json","state_url":"https://pith.science/pith/LTNGVW75KGKIAXZEQGAKCZPSU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTNGVW75KGKIAXZEQGAKCZPSU5/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":"2026-06-01T22:39:34Z","links":{"resolver":"https://pith.science/pith/LTNGVW75KGKIAXZEQGAKCZPSU5","bundle":"https://pith.science/pith/LTNGVW75KGKIAXZEQGAKCZPSU5/bundle.json","state":"https://pith.science/pith/LTNGVW75KGKIAXZEQGAKCZPSU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTNGVW75KGKIAXZEQGAKCZPSU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:LTNGVW75KGKIAXZEQGAKCZPSU5","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":"23700f14b24f77ac1b0a6ecd409141cb89a50ca5f3ad92f2d29913770c4da4f8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2014-02-24T14:27:40Z","title_canon_sha256":"ae93d46bf188092340b3a5ce6ce3a040070610b92ae8fda5c571bba29b963d6d"},"schema_version":"1.0","source":{"id":"1402.5836","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.5836","created_at":"2026-05-18T01:11:18Z"},{"alias_kind":"arxiv_version","alias_value":"1402.5836v3","created_at":"2026-05-18T01:11:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.5836","created_at":"2026-05-18T01:11:18Z"},{"alias_kind":"pith_short_12","alias_value":"LTNGVW75KGKI","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"LTNGVW75KGKIAXZE","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"LTNGVW75","created_at":"2026-05-18T12:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:d5abe1703888d350b70e89d6af957fefe11ccf40966ca5e924f953510fa6b63b","target":"graph","created_at":"2026-05-18T01:11:18Z","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":"Choosing appropriate architectures and regularization strategies for deep networks is crucial to good predictive performance. To shed light on this problem, we analyze the analogous problem of constructing useful priors on compositions of functions. Specifically, we study the deep Gaussian process, a type of infinitely-wide, deep neural network. We show that in standard architectures, the representational capacity of the network tends to capture fewer degrees of freedom as the number of layers increases, retaining only a single degree of freedom in the limit. We propose an alternate network ar","authors_text":"David Duvenaud, Oren Rippel, Ryan P. Adams, Zoubin Ghahramani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2014-02-24T14:27:40Z","title":"Avoiding pathologies in very deep networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.5836","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:cc6c278fd15785dc2c921b9a570fcc602c1a99dca61d70f99525707b79908e8c","target":"record","created_at":"2026-05-18T01:11:18Z","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":"23700f14b24f77ac1b0a6ecd409141cb89a50ca5f3ad92f2d29913770c4da4f8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2014-02-24T14:27:40Z","title_canon_sha256":"ae93d46bf188092340b3a5ce6ce3a040070610b92ae8fda5c571bba29b963d6d"},"schema_version":"1.0","source":{"id":"1402.5836","kind":"arxiv","version":3}},"canonical_sha256":"5cda6adbfd5194805f248180a165f2a7745b9c5fd0ada3241c07ea9880127c59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cda6adbfd5194805f248180a165f2a7745b9c5fd0ada3241c07ea9880127c59","first_computed_at":"2026-05-18T01:11:18.660129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:18.660129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eLsIWDZarEV9XczitdQMc8fYSYuH/reIvSsMU+KfnqtAsnzBc7TBOn7lgiHCNARTaV9Gh4/nzoxROWJo4EdDDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:18.660578Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.5836","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc6c278fd15785dc2c921b9a570fcc602c1a99dca61d70f99525707b79908e8c","sha256:d5abe1703888d350b70e89d6af957fefe11ccf40966ca5e924f953510fa6b63b"],"state_sha256":"c26846a13e5c7e0e91147f3eb113996c5cb20b39e2af5196d466df7fd398719c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yoNUK4aF1PMxjsRehgx5VbdiQ3cYZ85RA4++E1l9ucj6jsDhxMpK73wBUt+63NMieuc2AU/+nXtFv5AMu4fTAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T22:39:34.499120Z","bundle_sha256":"14950ebd2c8d92a15e9f7b5eda0fb1671efdc499ef9467d0752eb3674f0c81ae"}}