{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:G2D5WVOAL57QYWREIOHJ5BE47L","short_pith_number":"pith:G2D5WVOA","canonical_record":{"source":{"id":"2205.02708","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T15:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"80061b2fa45d8ea6e104246cbd86647d457ef1bc763b32ceb9e026e61178a610","abstract_canon_sha256":"1565c7e4fd6419d8f6cfa5ad51fda0513e1ed1d5d2150a2814f5b6fce344ed04"},"schema_version":"1.0"},"canonical_sha256":"3687db55c05f7f0c5a24438e9e849cfad7264f9020c69c8d8f229eb014dae611","source":{"kind":"arxiv","id":"2205.02708","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02708","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02708v5","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02708","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"pith_short_12","alias_value":"G2D5WVOAL57Q","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"pith_short_16","alias_value":"G2D5WVOAL57QYWRE","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"pith_short_8","alias_value":"G2D5WVOA","created_at":"2026-07-05T05:42:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:G2D5WVOAL57QYWREIOHJ5BE47L","target":"record","payload":{"canonical_record":{"source":{"id":"2205.02708","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T15:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"80061b2fa45d8ea6e104246cbd86647d457ef1bc763b32ceb9e026e61178a610","abstract_canon_sha256":"1565c7e4fd6419d8f6cfa5ad51fda0513e1ed1d5d2150a2814f5b6fce344ed04"},"schema_version":"1.0"},"canonical_sha256":"3687db55c05f7f0c5a24438e9e849cfad7264f9020c69c8d8f229eb014dae611","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:47.806287Z","signature_b64":"ww3cJpP9uWvt9rPDnMkEnO5DQ6v7hEy22XZez0PgZh53SE8s6unfE9IryR8NQIw7Qc/jGfGwZq1PJS/GAP72Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3687db55c05f7f0c5a24438e9e849cfad7264f9020c69c8d8f229eb014dae611","last_reissued_at":"2026-07-05T05:42:47.805782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:47.805782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.02708","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:42:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tv7iHHs4u9ufFM6wuzzZTiMI6VKNincBjwg3owr6ciZ+ZQmKBOwx+2qby6q2YTZlYr5QXz4PoC5XiWMJ4pveDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:19:43.720697Z"},"content_sha256":"ec791ec741ead06fc24d6de66734143b4a535c9057df7eefb91bde1d0e693d60","schema_version":"1.0","event_id":"sha256:ec791ec741ead06fc24d6de66734143b4a535c9057df7eefb91bde1d0e693d60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:G2D5WVOAL57QYWREIOHJ5BE47L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Austin Tripp, Jos\\'e Miguel Hern\\'andez-Lobato, Wenlin Chen","submitted_at":"2022-05-05T15:26:53Z","abstract_excerpt":"We propose Adaptive Deep Kernel Fitting with Implicit Function Theorem (ADKF-IFT), a novel framework for learning deep kernel Gaussian processes (GPs) by interpolating between meta-learning and conventional deep kernel learning. Our approach employs a bilevel optimization objective where we meta-learn generally useful feature representations across tasks, in the sense that task-specific GP models estimated on top of such features achieve the lowest possible predictive loss on average. We solve the resulting nested optimization problem using the implicit function theorem (IFT). We show that our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02708","kind":"arxiv","version":5},"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/2205.02708/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":"2026-07-05T05:42:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QSCRXYGrBZT6oosmS9WHxxoaQphOsL0gNyk5w/lXPIqA0o185J84wP00S2yfTNrVD9denML+JUEi6QMsHtxBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:19:43.721212Z"},"content_sha256":"85984672e656f05c617ad210520dfffca10b026090b52c202d0efaf78ffd1276","schema_version":"1.0","event_id":"sha256:85984672e656f05c617ad210520dfffca10b026090b52c202d0efaf78ffd1276"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2D5WVOAL57QYWREIOHJ5BE47L/bundle.json","state_url":"https://pith.science/pith/G2D5WVOAL57QYWREIOHJ5BE47L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2D5WVOAL57QYWREIOHJ5BE47L/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":"2026-08-03T16:19:43Z","links":{"resolver":"https://pith.science/pith/G2D5WVOAL57QYWREIOHJ5BE47L","bundle":"https://pith.science/pith/G2D5WVOAL57QYWREIOHJ5BE47L/bundle.json","state":"https://pith.science/pith/G2D5WVOAL57QYWREIOHJ5BE47L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2D5WVOAL57QYWREIOHJ5BE47L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G2D5WVOAL57QYWREIOHJ5BE47L","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":"1565c7e4fd6419d8f6cfa5ad51fda0513e1ed1d5d2150a2814f5b6fce344ed04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T15:26:53Z","title_canon_sha256":"80061b2fa45d8ea6e104246cbd86647d457ef1bc763b32ceb9e026e61178a610"},"schema_version":"1.0","source":{"id":"2205.02708","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02708","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02708v5","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02708","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"pith_short_12","alias_value":"G2D5WVOAL57Q","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"pith_short_16","alias_value":"G2D5WVOAL57QYWRE","created_at":"2026-07-05T05:42:47Z"},{"alias_kind":"pith_short_8","alias_value":"G2D5WVOA","created_at":"2026-07-05T05:42:47Z"}],"graph_snapshots":[{"event_id":"sha256:85984672e656f05c617ad210520dfffca10b026090b52c202d0efaf78ffd1276","target":"graph","created_at":"2026-07-05T05:42:47Z","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/2205.02708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Adaptive Deep Kernel Fitting with Implicit Function Theorem (ADKF-IFT), a novel framework for learning deep kernel Gaussian processes (GPs) by interpolating between meta-learning and conventional deep kernel learning. Our approach employs a bilevel optimization objective where we meta-learn generally useful feature representations across tasks, in the sense that task-specific GP models estimated on top of such features achieve the lowest possible predictive loss on average. We solve the resulting nested optimization problem using the implicit function theorem (IFT). We show that our","authors_text":"Austin Tripp, Jos\\'e Miguel Hern\\'andez-Lobato, Wenlin Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T15:26:53Z","title":"Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02708","kind":"arxiv","version":5},"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:ec791ec741ead06fc24d6de66734143b4a535c9057df7eefb91bde1d0e693d60","target":"record","created_at":"2026-07-05T05:42:47Z","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":"1565c7e4fd6419d8f6cfa5ad51fda0513e1ed1d5d2150a2814f5b6fce344ed04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T15:26:53Z","title_canon_sha256":"80061b2fa45d8ea6e104246cbd86647d457ef1bc763b32ceb9e026e61178a610"},"schema_version":"1.0","source":{"id":"2205.02708","kind":"arxiv","version":5}},"canonical_sha256":"3687db55c05f7f0c5a24438e9e849cfad7264f9020c69c8d8f229eb014dae611","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3687db55c05f7f0c5a24438e9e849cfad7264f9020c69c8d8f229eb014dae611","first_computed_at":"2026-07-05T05:42:47.805782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:47.805782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ww3cJpP9uWvt9rPDnMkEnO5DQ6v7hEy22XZez0PgZh53SE8s6unfE9IryR8NQIw7Qc/jGfGwZq1PJS/GAP72Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:47.806287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02708","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec791ec741ead06fc24d6de66734143b4a535c9057df7eefb91bde1d0e693d60","sha256:85984672e656f05c617ad210520dfffca10b026090b52c202d0efaf78ffd1276"],"state_sha256":"c197c05c94b1151a1275f2b6fba9b51b91a8a6cf83b53cff6c59b1bda0bae030"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPeWTcsLrTiFxzDdQc040dSbOmDa0WV4nzjfg9n5XnIGuVfg5EvIfiXOck9HfUQDxqrAwosQ49yUWz6UpOtWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:19:43.726767Z","bundle_sha256":"011b95324f467e4727cac3dee75b3a24e147fce4fc09a35431d006bde48844c0"}}