{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZBIEPXEVGFCJTT2OSWWZIJI6TW","short_pith_number":"pith:ZBIEPXEV","canonical_record":{"source":{"id":"1709.01894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-06T16:59:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b06297c8bf0898d321b5669eb141a9084ca9e6580629a44a64e5f0a26adfc72","abstract_canon_sha256":"6784576d0e3b17280e94d51967e48a099da3dd53ede5a9f9554d7e35a73e40a1"},"schema_version":"1.0"},"canonical_sha256":"c85047dc95314499cf4e95ad94251e9d8eba7aeb2a143993b621888f28452a02","source":{"kind":"arxiv","id":"1709.01894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01894","created_at":"2026-05-18T00:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01894v1","created_at":"2026-05-18T00:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01894","created_at":"2026-05-18T00:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZBIEPXEVGFCJ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZBIEPXEVGFCJTT2O","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZBIEPXEV","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZBIEPXEVGFCJTT2OSWWZIJI6TW","target":"record","payload":{"canonical_record":{"source":{"id":"1709.01894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-06T16:59:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b06297c8bf0898d321b5669eb141a9084ca9e6580629a44a64e5f0a26adfc72","abstract_canon_sha256":"6784576d0e3b17280e94d51967e48a099da3dd53ede5a9f9554d7e35a73e40a1"},"schema_version":"1.0"},"canonical_sha256":"c85047dc95314499cf4e95ad94251e9d8eba7aeb2a143993b621888f28452a02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:54.107158Z","signature_b64":"wNpOL5TWlzJuvjs7PWj2l9G4tDp+ctSxYIpiCrPIiiiYDTBDkoR7YNeqWYi4niI60jtkZxaMyTHMWkVifrx1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c85047dc95314499cf4e95ad94251e9d8eba7aeb2a143993b621888f28452a02","last_reissued_at":"2026-05-18T00:35:54.106586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:54.106586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.01894","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":"2026-05-18T00:35:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZs02k/mSENeJiLs0Cqm4uPkAnQJe0UilpsyiS32670wvRYDHlsbeEFOnPB9WfanG4zMh6mYQvXew/MskRewAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:04:17.462191Z"},"content_sha256":"e60b8792550059f2406e0db506c1befe4ba4c269ae76b21bef520d4e24da4991","schema_version":"1.0","event_id":"sha256:e60b8792550059f2406e0db506c1befe4ba4c269ae76b21bef520d4e24da4991"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZBIEPXEVGFCJTT2OSWWZIJI6TW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convolutional Gaussian Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Carl Edward Rasmussen, James Hensman, Mark van der Wilk","submitted_at":"2017-09-06T16:59:02Z","abstract_excerpt":"We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional kernel. This allows us to gain the generalisation benefit of a convolutional kernel, together with fast but accurate posterior inference. We investigate several variations of the convolutional kernel, and apply it to MNIST and CIFAR-10, which have both been known to be challenging for Gaussian proce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01894","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":""},"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":"2026-05-18T00:35:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2oA9ZcvNuwOmVl72QGZdXnLSsKKYc/EgAR4XkBuSnvWv09fzAJE3dqk5730oMuMCWZL8b1+teYifi/JUbqADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:04:17.462909Z"},"content_sha256":"01f558746ac007302e784992af0eef7aa06ceaafd5cedbb278f3ca27afb857bc","schema_version":"1.0","event_id":"sha256:01f558746ac007302e784992af0eef7aa06ceaafd5cedbb278f3ca27afb857bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBIEPXEVGFCJTT2OSWWZIJI6TW/bundle.json","state_url":"https://pith.science/pith/ZBIEPXEVGFCJTT2OSWWZIJI6TW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBIEPXEVGFCJTT2OSWWZIJI6TW/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":"2026-05-25T22:04:17Z","links":{"resolver":"https://pith.science/pith/ZBIEPXEVGFCJTT2OSWWZIJI6TW","bundle":"https://pith.science/pith/ZBIEPXEVGFCJTT2OSWWZIJI6TW/bundle.json","state":"https://pith.science/pith/ZBIEPXEVGFCJTT2OSWWZIJI6TW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBIEPXEVGFCJTT2OSWWZIJI6TW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZBIEPXEVGFCJTT2OSWWZIJI6TW","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":"6784576d0e3b17280e94d51967e48a099da3dd53ede5a9f9554d7e35a73e40a1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-06T16:59:02Z","title_canon_sha256":"3b06297c8bf0898d321b5669eb141a9084ca9e6580629a44a64e5f0a26adfc72"},"schema_version":"1.0","source":{"id":"1709.01894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01894","created_at":"2026-05-18T00:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01894v1","created_at":"2026-05-18T00:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01894","created_at":"2026-05-18T00:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZBIEPXEVGFCJ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZBIEPXEVGFCJTT2O","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZBIEPXEV","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:01f558746ac007302e784992af0eef7aa06ceaafd5cedbb278f3ca27afb857bc","target":"graph","created_at":"2026-05-18T00:35:54Z","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":"We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional kernel. This allows us to gain the generalisation benefit of a convolutional kernel, together with fast but accurate posterior inference. We investigate several variations of the convolutional kernel, and apply it to MNIST and CIFAR-10, which have both been known to be challenging for Gaussian proce","authors_text":"Carl Edward Rasmussen, James Hensman, Mark van der Wilk","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-06T16:59:02Z","title":"Convolutional Gaussian Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01894","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:e60b8792550059f2406e0db506c1befe4ba4c269ae76b21bef520d4e24da4991","target":"record","created_at":"2026-05-18T00:35:54Z","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":"6784576d0e3b17280e94d51967e48a099da3dd53ede5a9f9554d7e35a73e40a1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-06T16:59:02Z","title_canon_sha256":"3b06297c8bf0898d321b5669eb141a9084ca9e6580629a44a64e5f0a26adfc72"},"schema_version":"1.0","source":{"id":"1709.01894","kind":"arxiv","version":1}},"canonical_sha256":"c85047dc95314499cf4e95ad94251e9d8eba7aeb2a143993b621888f28452a02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c85047dc95314499cf4e95ad94251e9d8eba7aeb2a143993b621888f28452a02","first_computed_at":"2026-05-18T00:35:54.106586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:54.106586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wNpOL5TWlzJuvjs7PWj2l9G4tDp+ctSxYIpiCrPIiiiYDTBDkoR7YNeqWYi4niI60jtkZxaMyTHMWkVifrx1CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:54.107158Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.01894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e60b8792550059f2406e0db506c1befe4ba4c269ae76b21bef520d4e24da4991","sha256:01f558746ac007302e784992af0eef7aa06ceaafd5cedbb278f3ca27afb857bc"],"state_sha256":"d726f35afa990231b755fb79fa6f8e98eb171905bf5814c893a1dad0b7b6238c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1cxT7KCjkV/6zRoRPlPRG0Xregeh+xxMp/lmlIBnoMmuepthj/TkXBt7s1V4fpKP1Y9T83q2hkvUafxPiymBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:04:17.466924Z","bundle_sha256":"8618225e010f4dc834a19443fcff5b1760773a1e51d5095331d75c2105fba119"}}