{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NHCTA2S2UJQWLSB3WG22LW6YOZ","short_pith_number":"pith:NHCTA2S2","canonical_record":{"source":{"id":"2102.03748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T09:03:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6115d58e225c096bc7f29917c035c045f60b6af00cbfeddef5f02358fc254915","abstract_canon_sha256":"722ba39b3ac43f5e0c2f08c06e37bcf910ece2c80041c1fe4f9be7d95f686986"},"schema_version":"1.0"},"canonical_sha256":"69c5306a5aa26165c83bb1b5a5dbd8765bbbcea6ebae61a9ec403bbf6cfac69f","source":{"kind":"arxiv","id":"2102.03748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03748","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03748v1","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03748","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"NHCTA2S2UJQW","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"NHCTA2S2UJQWLSB3","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"NHCTA2S2","created_at":"2026-07-05T02:13:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NHCTA2S2UJQWLSB3WG22LW6YOZ","target":"record","payload":{"canonical_record":{"source":{"id":"2102.03748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T09:03:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6115d58e225c096bc7f29917c035c045f60b6af00cbfeddef5f02358fc254915","abstract_canon_sha256":"722ba39b3ac43f5e0c2f08c06e37bcf910ece2c80041c1fe4f9be7d95f686986"},"schema_version":"1.0"},"canonical_sha256":"69c5306a5aa26165c83bb1b5a5dbd8765bbbcea6ebae61a9ec403bbf6cfac69f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:27.140506Z","signature_b64":"QdBYpO4TpCmXeHZc7ZQyecGPCiDb3pV0dMHLO0r/DJX4R58/xAJbNBeRO77Otw2USEDxJnutt/q9EsWoFV5WAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c5306a5aa26165c83bb1b5a5dbd8765bbbcea6ebae61a9ec403bbf6cfac69f","last_reissued_at":"2026-07-05T02:13:27.140098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:27.140098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.03748","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":"2026-07-05T02:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5vDl8bW8Xy01qbX9AV+yYy6IBOb528yXFNIqJK+9zCTrMDaGNbQf/7HW/IG/dj/1Q+ZdQtWfHozWOkpn6BoeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:12:33.706710Z"},"content_sha256":"cc63893269d1ce2e9ab379f5f4c616b860b3dd755eef8dc28c4403c142723dda","schema_version":"1.0","event_id":"sha256:cc63893269d1ce2e9ab379f5f4c616b860b3dd755eef8dc28c4403c142723dda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NHCTA2S2UJQWLSB3WG22LW6YOZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guangquan Zhang, Jie Lu, Tianyu Liu, Zheng Yan","submitted_at":"2021-02-07T09:03:43Z","abstract_excerpt":"By leveraging experience from previous tasks, meta-learning algorithms can achieve effective fast adaptation ability when encountering new tasks. However it is unclear how the generalization property applies to new tasks. Probably approximately correct (PAC) Bayes bound theory provides a theoretical framework to analyze the generalization performance for meta-learning. We derive three novel generalisation error bounds for meta-learning based on PAC-Bayes relative entropy bound. Furthermore, using the empirical risk minimization (ERM) method, a PAC-Bayes bound for meta-learning with data-depend"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03748","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/2102.03748/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":"2026-07-05T02:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QfItXittgpBNYDMJa3W20cUPD6pI0uXEht0fOYzKnx1KOaIahxBwHNUL+lcvnvawme0vvHJTjE8MfbQm941oAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:12:33.707349Z"},"content_sha256":"370b82b638a916d2cdae0232988c6f03d56219538faf86252b9fe71d59ca6767","schema_version":"1.0","event_id":"sha256:370b82b638a916d2cdae0232988c6f03d56219538faf86252b9fe71d59ca6767"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHCTA2S2UJQWLSB3WG22LW6YOZ/bundle.json","state_url":"https://pith.science/pith/NHCTA2S2UJQWLSB3WG22LW6YOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHCTA2S2UJQWLSB3WG22LW6YOZ/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":"2026-08-19T22:12:33Z","links":{"resolver":"https://pith.science/pith/NHCTA2S2UJQWLSB3WG22LW6YOZ","bundle":"https://pith.science/pith/NHCTA2S2UJQWLSB3WG22LW6YOZ/bundle.json","state":"https://pith.science/pith/NHCTA2S2UJQWLSB3WG22LW6YOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHCTA2S2UJQWLSB3WG22LW6YOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NHCTA2S2UJQWLSB3WG22LW6YOZ","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":"722ba39b3ac43f5e0c2f08c06e37bcf910ece2c80041c1fe4f9be7d95f686986","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T09:03:43Z","title_canon_sha256":"6115d58e225c096bc7f29917c035c045f60b6af00cbfeddef5f02358fc254915"},"schema_version":"1.0","source":{"id":"2102.03748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03748","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03748v1","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03748","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"NHCTA2S2UJQW","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"NHCTA2S2UJQWLSB3","created_at":"2026-07-05T02:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"NHCTA2S2","created_at":"2026-07-05T02:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:370b82b638a916d2cdae0232988c6f03d56219538faf86252b9fe71d59ca6767","target":"graph","created_at":"2026-07-05T02:13:27Z","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/2102.03748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By leveraging experience from previous tasks, meta-learning algorithms can achieve effective fast adaptation ability when encountering new tasks. However it is unclear how the generalization property applies to new tasks. Probably approximately correct (PAC) Bayes bound theory provides a theoretical framework to analyze the generalization performance for meta-learning. We derive three novel generalisation error bounds for meta-learning based on PAC-Bayes relative entropy bound. Furthermore, using the empirical risk minimization (ERM) method, a PAC-Bayes bound for meta-learning with data-depend","authors_text":"Guangquan Zhang, Jie Lu, Tianyu Liu, Zheng Yan","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T09:03:43Z","title":"PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03748","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:cc63893269d1ce2e9ab379f5f4c616b860b3dd755eef8dc28c4403c142723dda","target":"record","created_at":"2026-07-05T02:13:27Z","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":"722ba39b3ac43f5e0c2f08c06e37bcf910ece2c80041c1fe4f9be7d95f686986","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-07T09:03:43Z","title_canon_sha256":"6115d58e225c096bc7f29917c035c045f60b6af00cbfeddef5f02358fc254915"},"schema_version":"1.0","source":{"id":"2102.03748","kind":"arxiv","version":1}},"canonical_sha256":"69c5306a5aa26165c83bb1b5a5dbd8765bbbcea6ebae61a9ec403bbf6cfac69f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69c5306a5aa26165c83bb1b5a5dbd8765bbbcea6ebae61a9ec403bbf6cfac69f","first_computed_at":"2026-07-05T02:13:27.140098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:27.140098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QdBYpO4TpCmXeHZc7ZQyecGPCiDb3pV0dMHLO0r/DJX4R58/xAJbNBeRO77Otw2USEDxJnutt/q9EsWoFV5WAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:27.140506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.03748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc63893269d1ce2e9ab379f5f4c616b860b3dd755eef8dc28c4403c142723dda","sha256:370b82b638a916d2cdae0232988c6f03d56219538faf86252b9fe71d59ca6767"],"state_sha256":"6dfa3a69b75d1e26b6a215d1e30762bafb9d9ae82a4667491c762d37ab23f97e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dG0GNG7+8IbjzRBO27QFODRE8pHgothQoENhTk+QUNuMrzO0rjTRlTIY56Hbzr1Zq/Onr1lioF9LndRqivf9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:12:33.712609Z","bundle_sha256":"e71a956f452f73096143b7674a8fd1045da0b80a0913d0293d8a4ab3e8f7330e"}}