{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BUHSFSP6W3ZLVBVR4ZLZKDGUDL","short_pith_number":"pith:BUHSFSP6","canonical_record":{"source":{"id":"2010.14499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:56:14Z","cross_cats_sorted":[],"title_canon_sha256":"e93460937e8056647d160319154932f570d9c616b201cbe3768addb281651e93","abstract_canon_sha256":"671b84361680ba4569b76ae63bcc52cc74bb65428af9cfcee46c9acad20b68d8"},"schema_version":"1.0"},"canonical_sha256":"0d0f22c9feb6f2ba86b1e657950cd41ad78b85d8f2aad14b98e5e47fbd5372b2","source":{"kind":"arxiv","id":"2010.14499","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14499","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14499v1","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14499","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"pith_short_12","alias_value":"BUHSFSP6W3ZL","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"pith_short_16","alias_value":"BUHSFSP6W3ZLVBVR","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"pith_short_8","alias_value":"BUHSFSP6","created_at":"2026-07-05T01:46:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BUHSFSP6W3ZLVBVR4ZLZKDGUDL","target":"record","payload":{"canonical_record":{"source":{"id":"2010.14499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:56:14Z","cross_cats_sorted":[],"title_canon_sha256":"e93460937e8056647d160319154932f570d9c616b201cbe3768addb281651e93","abstract_canon_sha256":"671b84361680ba4569b76ae63bcc52cc74bb65428af9cfcee46c9acad20b68d8"},"schema_version":"1.0"},"canonical_sha256":"0d0f22c9feb6f2ba86b1e657950cd41ad78b85d8f2aad14b98e5e47fbd5372b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:35.147295Z","signature_b64":"ZMoAbX0jT3i3gKRUgpfWUMVm9BpX1WX6jZN79j0teH7nGIsOQZ2/qaVsCS9L6Dyy89ygACnBlgr0QX9jpnroBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d0f22c9feb6f2ba86b1e657950cd41ad78b85d8f2aad14b98e5e47fbd5372b2","last_reissued_at":"2026-07-05T01:46:35.146909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:35.146909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.14499","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":"2026-07-05T01:46:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aCsfdiaFhF76opOvQ2jfrmwYnQGNEUBMYsB+7cCtVh/dfVUwmqSWloaiFv6IXCV9Ht38pRYdHfYAKVHPAVv+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:16:39.626937Z"},"content_sha256":"eff549f1502fde7c88a77cda65980f005a97aff66d23f8d86cf430f2373194d0","schema_version":"1.0","event_id":"sha256:eff549f1502fde7c88a77cda65980f005a97aff66d23f8d86cf430f2373194d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BUHSFSP6W3ZLVBVR4ZLZKDGUDL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Bayesian Perspective on Training Speed and Model Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Binxin Ru, Clare Lyle, Lisa Schut, Mark van der Wilk, Yarin Gal","submitted_at":"2020-10-27T17:56:14Z","abstract_excerpt":"We take a Bayesian perspective to illustrate a connection between training speed and the marginal likelihood in linear models. This provides two major insights: first, that a measure of a model's training speed can be used to estimate its marginal likelihood. Second, that this measure, under certain conditions, predicts the relative weighting of models in linear model combinations trained to minimize a regression loss. We verify our results in model selection tasks for linear models and for the infinite-width limit of deep neural networks. We further provide encouraging empirical evidence that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14499","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/2010.14499/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":"2026-07-05T01:46:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCehk1kX81yEAY0RRbyGVETUCLnlOklYM09xRYKFfNlvU2STYihE9gi8JvYnGIpTjqi01hq34LwHwnfaT4gnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:16:39.627310Z"},"content_sha256":"0074f17216fafe1885274963683e77bf0ba5c640534789e8a536d6a4c08355ee","schema_version":"1.0","event_id":"sha256:0074f17216fafe1885274963683e77bf0ba5c640534789e8a536d6a4c08355ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUHSFSP6W3ZLVBVR4ZLZKDGUDL/bundle.json","state_url":"https://pith.science/pith/BUHSFSP6W3ZLVBVR4ZLZKDGUDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUHSFSP6W3ZLVBVR4ZLZKDGUDL/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":"2026-07-07T12:16:39Z","links":{"resolver":"https://pith.science/pith/BUHSFSP6W3ZLVBVR4ZLZKDGUDL","bundle":"https://pith.science/pith/BUHSFSP6W3ZLVBVR4ZLZKDGUDL/bundle.json","state":"https://pith.science/pith/BUHSFSP6W3ZLVBVR4ZLZKDGUDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUHSFSP6W3ZLVBVR4ZLZKDGUDL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BUHSFSP6W3ZLVBVR4ZLZKDGUDL","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":"671b84361680ba4569b76ae63bcc52cc74bb65428af9cfcee46c9acad20b68d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:56:14Z","title_canon_sha256":"e93460937e8056647d160319154932f570d9c616b201cbe3768addb281651e93"},"schema_version":"1.0","source":{"id":"2010.14499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14499","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14499v1","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14499","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"pith_short_12","alias_value":"BUHSFSP6W3ZL","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"pith_short_16","alias_value":"BUHSFSP6W3ZLVBVR","created_at":"2026-07-05T01:46:35Z"},{"alias_kind":"pith_short_8","alias_value":"BUHSFSP6","created_at":"2026-07-05T01:46:35Z"}],"graph_snapshots":[{"event_id":"sha256:0074f17216fafe1885274963683e77bf0ba5c640534789e8a536d6a4c08355ee","target":"graph","created_at":"2026-07-05T01:46:35Z","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/2010.14499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We take a Bayesian perspective to illustrate a connection between training speed and the marginal likelihood in linear models. This provides two major insights: first, that a measure of a model's training speed can be used to estimate its marginal likelihood. Second, that this measure, under certain conditions, predicts the relative weighting of models in linear model combinations trained to minimize a regression loss. We verify our results in model selection tasks for linear models and for the infinite-width limit of deep neural networks. We further provide encouraging empirical evidence that","authors_text":"Binxin Ru, Clare Lyle, Lisa Schut, Mark van der Wilk, Yarin Gal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:56:14Z","title":"A Bayesian Perspective on Training Speed and Model Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14499","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:eff549f1502fde7c88a77cda65980f005a97aff66d23f8d86cf430f2373194d0","target":"record","created_at":"2026-07-05T01:46:35Z","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":"671b84361680ba4569b76ae63bcc52cc74bb65428af9cfcee46c9acad20b68d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:56:14Z","title_canon_sha256":"e93460937e8056647d160319154932f570d9c616b201cbe3768addb281651e93"},"schema_version":"1.0","source":{"id":"2010.14499","kind":"arxiv","version":1}},"canonical_sha256":"0d0f22c9feb6f2ba86b1e657950cd41ad78b85d8f2aad14b98e5e47fbd5372b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d0f22c9feb6f2ba86b1e657950cd41ad78b85d8f2aad14b98e5e47fbd5372b2","first_computed_at":"2026-07-05T01:46:35.146909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:46:35.146909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZMoAbX0jT3i3gKRUgpfWUMVm9BpX1WX6jZN79j0teH7nGIsOQZ2/qaVsCS9L6Dyy89ygACnBlgr0QX9jpnroBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:46:35.147295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eff549f1502fde7c88a77cda65980f005a97aff66d23f8d86cf430f2373194d0","sha256:0074f17216fafe1885274963683e77bf0ba5c640534789e8a536d6a4c08355ee"],"state_sha256":"be31b4462f23d33ad487323525b1d5217b3892f311d57a0bda1225d4449ae63a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMOsZd2KODaCW98mYu1Ua/wYB0Zz3svs5433o/3qdHfIvqcp6q7Ths3tIcLlWuDv4ekYHCoQSyiXzFiI7RqiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:16:39.629386Z","bundle_sha256":"c2ef4df9926b5ba31da01f4b357af4ee066a4959f8b0c36c9d0e0b0bd4d13b36"}}