{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HPZANO3G6E2HVTWOZY6KWILZUL","short_pith_number":"pith:HPZANO3G","canonical_record":{"source":{"id":"2011.06006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T19:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"e1716ffb3faec73f8921523c58db3d5dce34ef3ca1b94abbe682ef0aac3c639e","abstract_canon_sha256":"a7a50b8696a50be7c510642c4bbed8d00eb567783659539d6aef81c446465c51"},"schema_version":"1.0"},"canonical_sha256":"3bf206bb66f1347acecece3cab2179a2e8d0e19dd590bdec7964770fb539cbd8","source":{"kind":"arxiv","id":"2011.06006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06006","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06006v1","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06006","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"pith_short_12","alias_value":"HPZANO3G6E2H","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"pith_short_16","alias_value":"HPZANO3G6E2HVTWO","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"pith_short_8","alias_value":"HPZANO3G","created_at":"2026-07-05T01:51:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HPZANO3G6E2HVTWOZY6KWILZUL","target":"record","payload":{"canonical_record":{"source":{"id":"2011.06006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T19:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"e1716ffb3faec73f8921523c58db3d5dce34ef3ca1b94abbe682ef0aac3c639e","abstract_canon_sha256":"a7a50b8696a50be7c510642c4bbed8d00eb567783659539d6aef81c446465c51"},"schema_version":"1.0"},"canonical_sha256":"3bf206bb66f1347acecece3cab2179a2e8d0e19dd590bdec7964770fb539cbd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:10.873724Z","signature_b64":"3PnjAYir6zsmwQeKPnuS7Y8ALDxljZQnHfpE1Kw1JtXAV5eJBkorydbOEBhlSXt1iYvVRp8nuIR2TCDqHKu7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf206bb66f1347acecece3cab2179a2e8d0e19dd590bdec7964770fb539cbd8","last_reissued_at":"2026-07-05T01:51:10.873253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:10.873253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.06006","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":"2026-07-05T01:51:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HeYoRPVkOpNqlKjAnE+DKy0cd64qKkZ1SkHsmqZ2oCaRW29Tqn6oPWSLpJmRed/YTgJNrYFL3NjcFp9u4/jRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:38:56.865086Z"},"content_sha256":"9b6980a9ab8219ea03778c433b6cff4be43e57504087e0c7287d43910c6bd5a2","schema_version":"1.0","event_id":"sha256:9b6980a9ab8219ea03778c433b6cff4be43e57504087e0c7287d43910c6bd5a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HPZANO3G6E2HVTWOZY6KWILZUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards NNGP-guided Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daiyi Peng, Daniel S. Park, Jaehoon Lee, Jascha Sohl-Dickstein, Yuan Cao","submitted_at":"2020-11-11T19:00:06Z","abstract_excerpt":"The predictions of wide Bayesian neural networks are described by a Gaussian process, known as the Neural Network Gaussian Process (NNGP). Analytic forms for NNGP kernels are known for many models, but computing the exact kernel for convolutional architectures is prohibitively expensive. One can obtain effective approximations of these kernels through Monte-Carlo estimation using finite networks at initialization. Monte-Carlo NNGP inference is orders-of-magnitude cheaper in FLOPs compared to gradient descent training when the dataset size is small. Since NNGP inference provides a cheap measure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06006","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/2011.06006/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":"2026-07-05T01:51:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5J7IsJ2wC+m0h7pYZUvOOfBC+ifwLyTkxh6hlkdB3y1PXwiuf2PJXIKfTWYNw0uVWRaSx+2oPJeseqfsSCmlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:38:56.865663Z"},"content_sha256":"b051d2b9f53ca1b9ad6ed4f75961b9310e5e5b1e70de814b4c56e67df81caa78","schema_version":"1.0","event_id":"sha256:b051d2b9f53ca1b9ad6ed4f75961b9310e5e5b1e70de814b4c56e67df81caa78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HPZANO3G6E2HVTWOZY6KWILZUL/bundle.json","state_url":"https://pith.science/pith/HPZANO3G6E2HVTWOZY6KWILZUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HPZANO3G6E2HVTWOZY6KWILZUL/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":"2026-08-20T12:38:56Z","links":{"resolver":"https://pith.science/pith/HPZANO3G6E2HVTWOZY6KWILZUL","bundle":"https://pith.science/pith/HPZANO3G6E2HVTWOZY6KWILZUL/bundle.json","state":"https://pith.science/pith/HPZANO3G6E2HVTWOZY6KWILZUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HPZANO3G6E2HVTWOZY6KWILZUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HPZANO3G6E2HVTWOZY6KWILZUL","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":"a7a50b8696a50be7c510642c4bbed8d00eb567783659539d6aef81c446465c51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T19:00:06Z","title_canon_sha256":"e1716ffb3faec73f8921523c58db3d5dce34ef3ca1b94abbe682ef0aac3c639e"},"schema_version":"1.0","source":{"id":"2011.06006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06006","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06006v1","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06006","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"pith_short_12","alias_value":"HPZANO3G6E2H","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"pith_short_16","alias_value":"HPZANO3G6E2HVTWO","created_at":"2026-07-05T01:51:10Z"},{"alias_kind":"pith_short_8","alias_value":"HPZANO3G","created_at":"2026-07-05T01:51:10Z"}],"graph_snapshots":[{"event_id":"sha256:b051d2b9f53ca1b9ad6ed4f75961b9310e5e5b1e70de814b4c56e67df81caa78","target":"graph","created_at":"2026-07-05T01:51:10Z","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/2011.06006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The predictions of wide Bayesian neural networks are described by a Gaussian process, known as the Neural Network Gaussian Process (NNGP). Analytic forms for NNGP kernels are known for many models, but computing the exact kernel for convolutional architectures is prohibitively expensive. One can obtain effective approximations of these kernels through Monte-Carlo estimation using finite networks at initialization. Monte-Carlo NNGP inference is orders-of-magnitude cheaper in FLOPs compared to gradient descent training when the dataset size is small. Since NNGP inference provides a cheap measure","authors_text":"Daiyi Peng, Daniel S. Park, Jaehoon Lee, Jascha Sohl-Dickstein, Yuan Cao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T19:00:06Z","title":"Towards NNGP-guided Neural Architecture Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06006","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":"sha256:9b6980a9ab8219ea03778c433b6cff4be43e57504087e0c7287d43910c6bd5a2","target":"record","created_at":"2026-07-05T01:51:10Z","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":"a7a50b8696a50be7c510642c4bbed8d00eb567783659539d6aef81c446465c51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T19:00:06Z","title_canon_sha256":"e1716ffb3faec73f8921523c58db3d5dce34ef3ca1b94abbe682ef0aac3c639e"},"schema_version":"1.0","source":{"id":"2011.06006","kind":"arxiv","version":1}},"canonical_sha256":"3bf206bb66f1347acecece3cab2179a2e8d0e19dd590bdec7964770fb539cbd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bf206bb66f1347acecece3cab2179a2e8d0e19dd590bdec7964770fb539cbd8","first_computed_at":"2026-07-05T01:51:10.873253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:10.873253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3PnjAYir6zsmwQeKPnuS7Y8ALDxljZQnHfpE1Kw1JtXAV5eJBkorydbOEBhlSXt1iYvVRp8nuIR2TCDqHKu7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:10.873724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.06006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b6980a9ab8219ea03778c433b6cff4be43e57504087e0c7287d43910c6bd5a2","sha256:b051d2b9f53ca1b9ad6ed4f75961b9310e5e5b1e70de814b4c56e67df81caa78"],"state_sha256":"97d7ea67f7e2937ebc404f051e529a76fd8d37e9ee3a1caed31fcd5258a10496"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8lo99oWXFAMR8bh3aGn2OvXI3nJ7SQhIR/yOAoEM46kTiTMBMvdswm0Sx4M7n2sCtpLJy0XDUCRrQn9T1g1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:38:56.874617Z","bundle_sha256":"d4a1e39835ca13d3165ce8fbf15d84216954866c60da7483c8a0f8f8f8ab6803"}}