{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GKKYPBQBNEZDFUOVQEPBRX4ZLA","short_pith_number":"pith:GKKYPBQB","canonical_record":{"source":{"id":"2202.08232","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-02-16T18:24:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0d94d9db937de8997a223642314a087912c75d222071c0d2908acbd40a1c944f","abstract_canon_sha256":"852cc15fffb199a311f15552e31304b8262e2f95430d6f9952ac8378e5063050"},"schema_version":"1.0"},"canonical_sha256":"3295878601693232d1d5811e18df99581b128a5a48418a50a0d0beb6ffbd13e0","source":{"kind":"arxiv","id":"2202.08232","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.08232","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2202.08232v7","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08232","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"GKKYPBQBNEZD","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"GKKYPBQBNEZDFUOV","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"GKKYPBQB","created_at":"2026-07-05T06:05:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GKKYPBQBNEZDFUOVQEPBRX4ZLA","target":"record","payload":{"canonical_record":{"source":{"id":"2202.08232","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-02-16T18:24:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0d94d9db937de8997a223642314a087912c75d222071c0d2908acbd40a1c944f","abstract_canon_sha256":"852cc15fffb199a311f15552e31304b8262e2f95430d6f9952ac8378e5063050"},"schema_version":"1.0"},"canonical_sha256":"3295878601693232d1d5811e18df99581b128a5a48418a50a0d0beb6ffbd13e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:56.596588Z","signature_b64":"Cl9XvYSbfVL2iQ8wWK1+DTFfN8mrb0HZT2XUHJaGCw9812ynHlno6Xn+p5b8mIAovjm1v6Wnh/YxL9jmPnpWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3295878601693232d1d5811e18df99581b128a5a48418a50a0d0beb6ffbd13e0","last_reissued_at":"2026-07-05T06:05:56.596121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:56.596121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.08232","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmxNa8TXSpz6fTCx6ZzDByyhF2CM2Fp2RGYh2nPsGcfPksHULVO5nKvhGnAorEhhD4caYujnRUqyNECQqM8SDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:17:47.915123Z"},"content_sha256":"0c1ae5bb3c9ac28669762b5bdeff0819ab0b0a460f33ab19baa80043bca02e0f","schema_version":"1.0","event_id":"sha256:0c1ae5bb3c9ac28669762b5bdeff0819ab0b0a460f33ab19baa80043bca02e0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GKKYPBQBNEZDFUOVQEPBRX4ZLA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantum Lazy Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Erfan Abedi, Leila Taghavi, Salman Beigi","submitted_at":"2022-02-16T18:24:37Z","abstract_excerpt":"In the training of over-parameterized model functions via gradient descent, sometimes the parameters do not change significantly and remain close to their initial values. This phenomenon is called lazy training, and motivates consideration of the linear approximation of the model function around the initial parameters. In the lazy regime, this linear approximation imitates the behavior of the parameterized function whose associated kernel, called the tangent kernel, specifies the training performance of the model. Lazy training is known to occur in the case of (classical) neural networks with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08232","kind":"arxiv","version":7},"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/2202.08232/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":"2026-07-05T06:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DlheSniDizTEQIbshHGGnURZ3DQ22ZmLitnlRzAqgjOEeX5g366rcDYWfXkFFMRCCJkniJQPaogb2fBJA7rHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:17:47.916140Z"},"content_sha256":"3ee3961f625edff6ed25aa952acdea2342611e47dfa336dae8adcf27d428653b","schema_version":"1.0","event_id":"sha256:3ee3961f625edff6ed25aa952acdea2342611e47dfa336dae8adcf27d428653b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKKYPBQBNEZDFUOVQEPBRX4ZLA/bundle.json","state_url":"https://pith.science/pith/GKKYPBQBNEZDFUOVQEPBRX4ZLA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKKYPBQBNEZDFUOVQEPBRX4ZLA/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":"2026-08-08T16:17:47Z","links":{"resolver":"https://pith.science/pith/GKKYPBQBNEZDFUOVQEPBRX4ZLA","bundle":"https://pith.science/pith/GKKYPBQBNEZDFUOVQEPBRX4ZLA/bundle.json","state":"https://pith.science/pith/GKKYPBQBNEZDFUOVQEPBRX4ZLA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKKYPBQBNEZDFUOVQEPBRX4ZLA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GKKYPBQBNEZDFUOVQEPBRX4ZLA","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":"852cc15fffb199a311f15552e31304b8262e2f95430d6f9952ac8378e5063050","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-02-16T18:24:37Z","title_canon_sha256":"0d94d9db937de8997a223642314a087912c75d222071c0d2908acbd40a1c944f"},"schema_version":"1.0","source":{"id":"2202.08232","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.08232","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2202.08232v7","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08232","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"GKKYPBQBNEZD","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"GKKYPBQBNEZDFUOV","created_at":"2026-07-05T06:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"GKKYPBQB","created_at":"2026-07-05T06:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:3ee3961f625edff6ed25aa952acdea2342611e47dfa336dae8adcf27d428653b","target":"graph","created_at":"2026-07-05T06:05:56Z","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/2202.08232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the training of over-parameterized model functions via gradient descent, sometimes the parameters do not change significantly and remain close to their initial values. This phenomenon is called lazy training, and motivates consideration of the linear approximation of the model function around the initial parameters. In the lazy regime, this linear approximation imitates the behavior of the parameterized function whose associated kernel, called the tangent kernel, specifies the training performance of the model. Lazy training is known to occur in the case of (classical) neural networks with ","authors_text":"Erfan Abedi, Leila Taghavi, Salman Beigi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-02-16T18:24:37Z","title":"Quantum Lazy Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08232","kind":"arxiv","version":7},"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":"sha256:0c1ae5bb3c9ac28669762b5bdeff0819ab0b0a460f33ab19baa80043bca02e0f","target":"record","created_at":"2026-07-05T06:05:56Z","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":"852cc15fffb199a311f15552e31304b8262e2f95430d6f9952ac8378e5063050","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-02-16T18:24:37Z","title_canon_sha256":"0d94d9db937de8997a223642314a087912c75d222071c0d2908acbd40a1c944f"},"schema_version":"1.0","source":{"id":"2202.08232","kind":"arxiv","version":7}},"canonical_sha256":"3295878601693232d1d5811e18df99581b128a5a48418a50a0d0beb6ffbd13e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3295878601693232d1d5811e18df99581b128a5a48418a50a0d0beb6ffbd13e0","first_computed_at":"2026-07-05T06:05:56.596121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:56.596121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cl9XvYSbfVL2iQ8wWK1+DTFfN8mrb0HZT2XUHJaGCw9812ynHlno6Xn+p5b8mIAovjm1v6Wnh/YxL9jmPnpWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:56.596588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.08232","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c1ae5bb3c9ac28669762b5bdeff0819ab0b0a460f33ab19baa80043bca02e0f","sha256:3ee3961f625edff6ed25aa952acdea2342611e47dfa336dae8adcf27d428653b"],"state_sha256":"e1bf8c4721fb9bde66c5387382324a709caa8553f3ba5e939d944dba3a7eda66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yJFbUGlDonPPzGLX4kCNwC8Elz8x/E6FV6PWOyWR8Ss2vQHYeff3m56eQ77W7dl3M0p2012hl7xSQhRJty8KDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:17:47.929231Z","bundle_sha256":"fbe5c2bb777e3cffe5eb6764cbca7a0caa8be2185ef01a4cf3699ae019b6897e"}}