{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BNOXS7MZ4OQFWKSY56GTCO5P6B","short_pith_number":"pith:BNOXS7MZ","canonical_record":{"source":{"id":"2305.14585","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T23:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"f7cb9abcf7c1c5bfecec97ddfbe2d8cf8a4edd55b7bad99a5ace8e8d6a490ac2","abstract_canon_sha256":"01c4728ae70fa5fc38e663e27934af018c2ea5ea73649cca013c5f7a1f9a4779"},"schema_version":"1.0"},"canonical_sha256":"0b5d797d99e3a05b2a58ef8d313baff06497530486dd73dab46b3af1bc259968","source":{"kind":"arxiv","id":"2305.14585","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14585","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14585v5","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14585","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"pith_short_12","alias_value":"BNOXS7MZ4OQF","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"pith_short_16","alias_value":"BNOXS7MZ4OQFWKSY","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"pith_short_8","alias_value":"BNOXS7MZ","created_at":"2026-07-05T07:54:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BNOXS7MZ4OQFWKSY56GTCO5P6B","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14585","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T23:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"f7cb9abcf7c1c5bfecec97ddfbe2d8cf8a4edd55b7bad99a5ace8e8d6a490ac2","abstract_canon_sha256":"01c4728ae70fa5fc38e663e27934af018c2ea5ea73649cca013c5f7a1f9a4779"},"schema_version":"1.0"},"canonical_sha256":"0b5d797d99e3a05b2a58ef8d313baff06497530486dd73dab46b3af1bc259968","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:48.917025Z","signature_b64":"rDNpW/XtCX+YDjHXJV+7xwpEnkp3wTXOZGlASqD9ntkmeKCxpYFPLSGMM+P/809hczTlQsgcQUd2ilSxmNOrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b5d797d99e3a05b2a58ef8d313baff06497530486dd73dab46b3af1bc259968","last_reissued_at":"2026-07-05T07:54:48.916608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:48.916608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14585","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":"2026-07-05T07:54:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jio6+9yt1SuH2J7J70vaW6/Mqcd+G9VPBZBbBKTc8n4FhbGBKyXSG37ldsFiE7Sz/TtslC8/M6t4eSiK27WTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:53:22.425785Z"},"content_sha256":"4d48cdb7505ca85c9c8ec8115652c2e88883255e946519a00ebc87479465f12a","schema_version":"1.0","event_id":"sha256:4d48cdb7505ca85c9c8ec8115652c2e88883255e946519a00ebc87479465f12a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BNOXS7MZ4OQFWKSY56GTCO5P6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anand Sarwate, Andrew Engel, Ioana Dumitriu, Natalie S. Frank, Sutanay Choudhury, Tony Chiang, Zhichao Wang","submitted_at":"2023-05-23T23:51:53Z","abstract_excerpt":"A recent trend in explainable AI research has focused on surrogate modeling, where neural networks are approximated as simpler ML algorithms such as kernel machines. A second trend has been to utilize kernel functions in various explain-by-example or data attribution tasks. In this work, we combine these two trends to analyze approximate empirical neural tangent kernels (eNTK) for data attribution. Approximation is critical for eNTK analysis due to the high computational cost to compute the eNTK. We define new approximate eNTK and perform novel analysis on how well the resulting kernel machine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14585","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/2305.14585/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":"2026-07-05T07:54:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NKbblRKtHTSuxn9/EtwMzLTLUpPidqlAIfFH9ifTBqSjki/70wwbfxXRFd7n5mMFxekDStVU0g4qgtpVE5n1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:53:22.426291Z"},"content_sha256":"d7ba60ddba4cb3c9bbf13935c124b49e71a863d1d24236a6643dba9cbf60a4ac","schema_version":"1.0","event_id":"sha256:d7ba60ddba4cb3c9bbf13935c124b49e71a863d1d24236a6643dba9cbf60a4ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNOXS7MZ4OQFWKSY56GTCO5P6B/bundle.json","state_url":"https://pith.science/pith/BNOXS7MZ4OQFWKSY56GTCO5P6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNOXS7MZ4OQFWKSY56GTCO5P6B/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":"2026-08-05T18:53:22Z","links":{"resolver":"https://pith.science/pith/BNOXS7MZ4OQFWKSY56GTCO5P6B","bundle":"https://pith.science/pith/BNOXS7MZ4OQFWKSY56GTCO5P6B/bundle.json","state":"https://pith.science/pith/BNOXS7MZ4OQFWKSY56GTCO5P6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNOXS7MZ4OQFWKSY56GTCO5P6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BNOXS7MZ4OQFWKSY56GTCO5P6B","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":"01c4728ae70fa5fc38e663e27934af018c2ea5ea73649cca013c5f7a1f9a4779","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T23:51:53Z","title_canon_sha256":"f7cb9abcf7c1c5bfecec97ddfbe2d8cf8a4edd55b7bad99a5ace8e8d6a490ac2"},"schema_version":"1.0","source":{"id":"2305.14585","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14585","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14585v5","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14585","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"pith_short_12","alias_value":"BNOXS7MZ4OQF","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"pith_short_16","alias_value":"BNOXS7MZ4OQFWKSY","created_at":"2026-07-05T07:54:48Z"},{"alias_kind":"pith_short_8","alias_value":"BNOXS7MZ","created_at":"2026-07-05T07:54:48Z"}],"graph_snapshots":[{"event_id":"sha256:d7ba60ddba4cb3c9bbf13935c124b49e71a863d1d24236a6643dba9cbf60a4ac","target":"graph","created_at":"2026-07-05T07:54:48Z","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/2305.14585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A recent trend in explainable AI research has focused on surrogate modeling, where neural networks are approximated as simpler ML algorithms such as kernel machines. A second trend has been to utilize kernel functions in various explain-by-example or data attribution tasks. In this work, we combine these two trends to analyze approximate empirical neural tangent kernels (eNTK) for data attribution. Approximation is critical for eNTK analysis due to the high computational cost to compute the eNTK. We define new approximate eNTK and perform novel analysis on how well the resulting kernel machine","authors_text":"Anand Sarwate, Andrew Engel, Ioana Dumitriu, Natalie S. Frank, Sutanay Choudhury, Tony Chiang, Zhichao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T23:51:53Z","title":"Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14585","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":"sha256:4d48cdb7505ca85c9c8ec8115652c2e88883255e946519a00ebc87479465f12a","target":"record","created_at":"2026-07-05T07:54:48Z","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":"01c4728ae70fa5fc38e663e27934af018c2ea5ea73649cca013c5f7a1f9a4779","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T23:51:53Z","title_canon_sha256":"f7cb9abcf7c1c5bfecec97ddfbe2d8cf8a4edd55b7bad99a5ace8e8d6a490ac2"},"schema_version":"1.0","source":{"id":"2305.14585","kind":"arxiv","version":5}},"canonical_sha256":"0b5d797d99e3a05b2a58ef8d313baff06497530486dd73dab46b3af1bc259968","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b5d797d99e3a05b2a58ef8d313baff06497530486dd73dab46b3af1bc259968","first_computed_at":"2026-07-05T07:54:48.916608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:48.916608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rDNpW/XtCX+YDjHXJV+7xwpEnkp3wTXOZGlASqD9ntkmeKCxpYFPLSGMM+P/809hczTlQsgcQUd2ilSxmNOrAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:48.917025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14585","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d48cdb7505ca85c9c8ec8115652c2e88883255e946519a00ebc87479465f12a","sha256:d7ba60ddba4cb3c9bbf13935c124b49e71a863d1d24236a6643dba9cbf60a4ac"],"state_sha256":"761ba0f9d527162b90c718ab1281324a94f464502edff359e8bfd837d31f8352"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gNliwXEnbIGf/y82ZQJy8BmZwEXCDTtNTstR9RbnkYsmrLttGl27cygFehXwetLHfKJXvHsyDjoQheyeq3/tDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:53:22.430498Z","bundle_sha256":"49f039c411277b8fceaf255c8d0fedb5da22d3ec2cf3a6e2e5a7d54f16f9eb98"}}