{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:N5ZJ2DJ5QR43WZUTGY2GW4KSXV","short_pith_number":"pith:N5ZJ2DJ5","canonical_record":{"source":{"id":"2305.01143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-02T01:17:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e3a0ecc5b05590aaa4509b08aae4cfe771b29016687f8724ce7d736b079979f","abstract_canon_sha256":"b3ef55b8b9c0f337ee0faa61f91eba6ddc12975454a8ccd33f4652b6d6fd0769"},"schema_version":"1.0"},"canonical_sha256":"6f729d0d3d8479bb669336346b7152bd6608ca72e9a6d40ef5209ef23a0face7","source":{"kind":"arxiv","id":"2305.01143","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01143","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01143v1","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01143","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"N5ZJ2DJ5QR43","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"N5ZJ2DJ5QR43WZUT","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"N5ZJ2DJ5","created_at":"2026-07-05T06:06:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:N5ZJ2DJ5QR43WZUTGY2GW4KSXV","target":"record","payload":{"canonical_record":{"source":{"id":"2305.01143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-02T01:17:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e3a0ecc5b05590aaa4509b08aae4cfe771b29016687f8724ce7d736b079979f","abstract_canon_sha256":"b3ef55b8b9c0f337ee0faa61f91eba6ddc12975454a8ccd33f4652b6d6fd0769"},"schema_version":"1.0"},"canonical_sha256":"6f729d0d3d8479bb669336346b7152bd6608ca72e9a6d40ef5209ef23a0face7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:21.970600Z","signature_b64":"T0Lsplwxql/whAkl7pUY6nzlJLopdoVNzGCfg19LNHW55DgMZamTxnf3DdIuM78drkQCpqxovIvu1q/VkWnVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f729d0d3d8479bb669336346b7152bd6608ca72e9a6d40ef5209ef23a0face7","last_reissued_at":"2026-07-05T06:06:21.970196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:21.970196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.01143","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":"2026-07-05T06:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HlANrYACoXvgtIsCbw5wpH5cLTRiSoUy9i25tW/XRvKtZSEkGnmlhbv81ejDQggR2tRiSaKFDtOcR6Uyx9vKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:23:32.183130Z"},"content_sha256":"acbc0900f182d4eb218b8928102df94bcb569789704a192819b350b9cfb3210b","schema_version":"1.0","event_id":"sha256:acbc0900f182d4eb218b8928102df94bcb569789704a192819b350b9cfb3210b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:N5ZJ2DJ5QR43WZUTGY2GW4KSXV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chen Li, Hong Chen, Tieliang Gong, Yuxin Dong","submitted_at":"2023-05-02T01:17:15Z","abstract_excerpt":"Recently, information theoretic analysis has become a popular framework for understanding the generalization behavior of deep neural networks. It allows a direct analysis for stochastic gradient/Langevin descent (SGD/SGLD) learning algorithms without strong assumptions such as Lipschitz or convexity conditions. However, the current generalization error bounds within this framework are still far from optimal, while substantial improvements on these bounds are quite challenging due to the intractability of high-dimensional information quantities. To address this issue, we first propose a novel i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01143","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/2305.01143/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":"2026-07-05T06:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbzHZ+8SJOmXH22pnP5B8NEhW0pUmo6bZ2HShVyoueO/czpQPb8zYPJxuqBplC9IJO61J9Q8tt1SwkCkmI4hCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:23:32.184288Z"},"content_sha256":"55ac23b6136740bd1626b6449844f0c471d5ea088dfd28a108fe9d65c26d284b","schema_version":"1.0","event_id":"sha256:55ac23b6136740bd1626b6449844f0c471d5ea088dfd28a108fe9d65c26d284b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5ZJ2DJ5QR43WZUTGY2GW4KSXV/bundle.json","state_url":"https://pith.science/pith/N5ZJ2DJ5QR43WZUTGY2GW4KSXV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5ZJ2DJ5QR43WZUTGY2GW4KSXV/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":"2026-08-13T15:23:32Z","links":{"resolver":"https://pith.science/pith/N5ZJ2DJ5QR43WZUTGY2GW4KSXV","bundle":"https://pith.science/pith/N5ZJ2DJ5QR43WZUTGY2GW4KSXV/bundle.json","state":"https://pith.science/pith/N5ZJ2DJ5QR43WZUTGY2GW4KSXV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5ZJ2DJ5QR43WZUTGY2GW4KSXV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:N5ZJ2DJ5QR43WZUTGY2GW4KSXV","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":"b3ef55b8b9c0f337ee0faa61f91eba6ddc12975454a8ccd33f4652b6d6fd0769","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-02T01:17:15Z","title_canon_sha256":"4e3a0ecc5b05590aaa4509b08aae4cfe771b29016687f8724ce7d736b079979f"},"schema_version":"1.0","source":{"id":"2305.01143","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01143","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01143v1","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01143","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"N5ZJ2DJ5QR43","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"N5ZJ2DJ5QR43WZUT","created_at":"2026-07-05T06:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"N5ZJ2DJ5","created_at":"2026-07-05T06:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:55ac23b6136740bd1626b6449844f0c471d5ea088dfd28a108fe9d65c26d284b","target":"graph","created_at":"2026-07-05T06:06:21Z","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/2305.01143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, information theoretic analysis has become a popular framework for understanding the generalization behavior of deep neural networks. It allows a direct analysis for stochastic gradient/Langevin descent (SGD/SGLD) learning algorithms without strong assumptions such as Lipschitz or convexity conditions. However, the current generalization error bounds within this framework are still far from optimal, while substantial improvements on these bounds are quite challenging due to the intractability of high-dimensional information quantities. To address this issue, we first propose a novel i","authors_text":"Chen Li, Hong Chen, Tieliang Gong, Yuxin Dong","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-02T01:17:15Z","title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01143","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:acbc0900f182d4eb218b8928102df94bcb569789704a192819b350b9cfb3210b","target":"record","created_at":"2026-07-05T06:06:21Z","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":"b3ef55b8b9c0f337ee0faa61f91eba6ddc12975454a8ccd33f4652b6d6fd0769","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-02T01:17:15Z","title_canon_sha256":"4e3a0ecc5b05590aaa4509b08aae4cfe771b29016687f8724ce7d736b079979f"},"schema_version":"1.0","source":{"id":"2305.01143","kind":"arxiv","version":1}},"canonical_sha256":"6f729d0d3d8479bb669336346b7152bd6608ca72e9a6d40ef5209ef23a0face7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f729d0d3d8479bb669336346b7152bd6608ca72e9a6d40ef5209ef23a0face7","first_computed_at":"2026-07-05T06:06:21.970196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:06:21.970196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T0Lsplwxql/whAkl7pUY6nzlJLopdoVNzGCfg19LNHW55DgMZamTxnf3DdIuM78drkQCpqxovIvu1q/VkWnVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:06:21.970600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01143","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acbc0900f182d4eb218b8928102df94bcb569789704a192819b350b9cfb3210b","sha256:55ac23b6136740bd1626b6449844f0c471d5ea088dfd28a108fe9d65c26d284b"],"state_sha256":"45d2dfdc1e514a871a86f090728c31385a53c001edeffc075d4726bfcdd1e073"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WGgd5IkSp2qKyp75XRq3FVfpMuLCFf7WcvR6xKkNv5RCuPDSS3tS+RucrkqCaY3hLyuQHVUpMQwdGOXMngnpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:23:32.212045Z","bundle_sha256":"235e044e077e75caf645ac011b4b2dff785e8854c7711b041cf1cfb78af0b3bb"}}