{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DNAI4QNODYW4BPB2DZMVRWYUZV","short_pith_number":"pith:DNAI4QNO","canonical_record":{"source":{"id":"2606.07495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:49:19Z","cross_cats_sorted":[],"title_canon_sha256":"a760896e6c273bd131957b12f6366b39e26172de417fdb7ad4d454141277665e","abstract_canon_sha256":"35fd2005fad8e4c3c89bdd56ba6e097b0d0c9834ac78cc3341bd4eb3731cb33c"},"schema_version":"1.0"},"canonical_sha256":"1b408e41ae1e2dc0bc3a1e5958db14cd5567b46133f24d534848ea0723e91cd4","source":{"kind":"arxiv","id":"2606.07495","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07495","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07495v1","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07495","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"DNAI4QNODYW4","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"DNAI4QNODYW4BPB2","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"DNAI4QNO","created_at":"2026-06-08T01:05:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DNAI4QNODYW4BPB2DZMVRWYUZV","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:49:19Z","cross_cats_sorted":[],"title_canon_sha256":"a760896e6c273bd131957b12f6366b39e26172de417fdb7ad4d454141277665e","abstract_canon_sha256":"35fd2005fad8e4c3c89bdd56ba6e097b0d0c9834ac78cc3341bd4eb3731cb33c"},"schema_version":"1.0"},"canonical_sha256":"1b408e41ae1e2dc0bc3a1e5958db14cd5567b46133f24d534848ea0723e91cd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:30.346239Z","signature_b64":"iPbZSefT8cZUJ9Zq1hHcbmj2jASyPeUvp1bsychuf7U9zA6Tz1Re3lEb9zUyCKWrIq73coGALiSFrmIzJ0RTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b408e41ae1e2dc0bc3a1e5958db14cd5567b46133f24d534848ea0723e91cd4","last_reissued_at":"2026-06-08T01:05:30.345504Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:30.345504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07495","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":"2026-06-08T01:05:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KONwactqx1tQu685UG+2VXyOhGlsdNybUqGceXU9OlBYQjZKF82EoGrPMbfPr53G44e+02c8bdvJtvPN7kVsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:39:56.235197Z"},"content_sha256":"b9c22c8d16ed81a39a3a0063ebd64488c043b38ed00fbaef223273932073b8ed","schema_version":"1.0","event_id":"sha256:b9c22c8d16ed81a39a3a0063ebd64488c043b38ed00fbaef223273932073b8ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DNAI4QNODYW4BPB2DZMVRWYUZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Second-Order Path Kernel Interpolation Formulas in Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jean-Michel Morel, Jin Guo, Roy Y. He","submitted_at":"2026-06-05T17:49:19Z","abstract_excerpt":"Understanding how training data shape neural network predictions is a central problem in modern learning theory. In 2020, Pedro Domingos proposed an interpolation formula valid for every model learned by deterministic gradient descent. It expresses the model's prediction as an integral, along the optimization path, of a data-dependent kernel that aligns the model's gradients at the test and training data. Such a first-order characterization remains valid for models trained with batch-based stochastic optimization. In this paper, we develop second-order forms of these interpolation formulas. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07495","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/2606.07495/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":"2026-06-08T01:05:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SBurPQBsG7qNt8Q+rfXf75rwIpsFCb3NKS6jVe7hrcIhHCwr3hULV91YQ9fqgCzArgOBNr4CszzcY/IwcYidDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:39:56.235570Z"},"content_sha256":"f3b0c348dca7377cf4834db2e5e2a27be860fa54c0552c6215ee659cb0e025be","schema_version":"1.0","event_id":"sha256:f3b0c348dca7377cf4834db2e5e2a27be860fa54c0552c6215ee659cb0e025be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DNAI4QNODYW4BPB2DZMVRWYUZV/bundle.json","state_url":"https://pith.science/pith/DNAI4QNODYW4BPB2DZMVRWYUZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DNAI4QNODYW4BPB2DZMVRWYUZV/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":"2026-06-28T04:39:56Z","links":{"resolver":"https://pith.science/pith/DNAI4QNODYW4BPB2DZMVRWYUZV","bundle":"https://pith.science/pith/DNAI4QNODYW4BPB2DZMVRWYUZV/bundle.json","state":"https://pith.science/pith/DNAI4QNODYW4BPB2DZMVRWYUZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DNAI4QNODYW4BPB2DZMVRWYUZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DNAI4QNODYW4BPB2DZMVRWYUZV","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":"35fd2005fad8e4c3c89bdd56ba6e097b0d0c9834ac78cc3341bd4eb3731cb33c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:49:19Z","title_canon_sha256":"a760896e6c273bd131957b12f6366b39e26172de417fdb7ad4d454141277665e"},"schema_version":"1.0","source":{"id":"2606.07495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07495","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07495v1","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07495","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"DNAI4QNODYW4","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"DNAI4QNODYW4BPB2","created_at":"2026-06-08T01:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"DNAI4QNO","created_at":"2026-06-08T01:05:30Z"}],"graph_snapshots":[{"event_id":"sha256:f3b0c348dca7377cf4834db2e5e2a27be860fa54c0552c6215ee659cb0e025be","target":"graph","created_at":"2026-06-08T01:05:30Z","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/2606.07495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding how training data shape neural network predictions is a central problem in modern learning theory. In 2020, Pedro Domingos proposed an interpolation formula valid for every model learned by deterministic gradient descent. It expresses the model's prediction as an integral, along the optimization path, of a data-dependent kernel that aligns the model's gradients at the test and training data. Such a first-order characterization remains valid for models trained with batch-based stochastic optimization. In this paper, we develop second-order forms of these interpolation formulas. We","authors_text":"Jean-Michel Morel, Jin Guo, Roy Y. He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:49:19Z","title":"Second-Order Path Kernel Interpolation Formulas in Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07495","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:b9c22c8d16ed81a39a3a0063ebd64488c043b38ed00fbaef223273932073b8ed","target":"record","created_at":"2026-06-08T01:05:30Z","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":"35fd2005fad8e4c3c89bdd56ba6e097b0d0c9834ac78cc3341bd4eb3731cb33c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T17:49:19Z","title_canon_sha256":"a760896e6c273bd131957b12f6366b39e26172de417fdb7ad4d454141277665e"},"schema_version":"1.0","source":{"id":"2606.07495","kind":"arxiv","version":1}},"canonical_sha256":"1b408e41ae1e2dc0bc3a1e5958db14cd5567b46133f24d534848ea0723e91cd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b408e41ae1e2dc0bc3a1e5958db14cd5567b46133f24d534848ea0723e91cd4","first_computed_at":"2026-06-08T01:05:30.345504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:30.345504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iPbZSefT8cZUJ9Zq1hHcbmj2jASyPeUvp1bsychuf7U9zA6Tz1Re3lEb9zUyCKWrIq73coGALiSFrmIzJ0RTCA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:30.346239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9c22c8d16ed81a39a3a0063ebd64488c043b38ed00fbaef223273932073b8ed","sha256:f3b0c348dca7377cf4834db2e5e2a27be860fa54c0552c6215ee659cb0e025be"],"state_sha256":"eb4ca973b99d9ae625b519f14e653a90ccd4e309ed5d5ec60d03804a30710a41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rq1p36nq1pYiT8byH52uc5/iQ9kt+znfyZ4ahRCkXsLfrUpEJ0JZ2fBSTDq4QyQdvpWbdhw7WtratSmmLuxoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T04:39:56.237337Z","bundle_sha256":"099361f2c444993fd5a164a360dd7ba1b76a8c639debf8fa4580e3e46f0a8671"}}