{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GMIBWGVIZAQGMTHTP73YRRB2RB","short_pith_number":"pith:GMIBWGVI","canonical_record":{"source":{"id":"2211.15180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T09:47:13Z","cross_cats_sorted":[],"title_canon_sha256":"92ec8d6fa83b9ff47fa6d770e48c007ef7b68d6fcd30375c141dbb195ca55687","abstract_canon_sha256":"83cf51bd21ab23410ae4258bfb0b0240eae2aa154d1bb2601175d62392b768ad"},"schema_version":"1.0"},"canonical_sha256":"33101b1aa8c820664cf37ff788c43a887d3dbad4c29fb89e43a916583278af55","source":{"kind":"arxiv","id":"2211.15180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15180","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15180v1","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15180","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"pith_short_12","alias_value":"GMIBWGVIZAQG","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"pith_short_16","alias_value":"GMIBWGVIZAQGMTHT","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"pith_short_8","alias_value":"GMIBWGVI","created_at":"2026-07-05T05:20:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GMIBWGVIZAQGMTHTP73YRRB2RB","target":"record","payload":{"canonical_record":{"source":{"id":"2211.15180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T09:47:13Z","cross_cats_sorted":[],"title_canon_sha256":"92ec8d6fa83b9ff47fa6d770e48c007ef7b68d6fcd30375c141dbb195ca55687","abstract_canon_sha256":"83cf51bd21ab23410ae4258bfb0b0240eae2aa154d1bb2601175d62392b768ad"},"schema_version":"1.0"},"canonical_sha256":"33101b1aa8c820664cf37ff788c43a887d3dbad4c29fb89e43a916583278af55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:00.473415Z","signature_b64":"wkbSKPIjwyRGKtfewIrGXTLU/PjcY+A9h09g/mrVeJdK/ELaUjFTRBw/v4QF3O5h7j8ILUAMN1PgzCWKC6TmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33101b1aa8c820664cf37ff788c43a887d3dbad4c29fb89e43a916583278af55","last_reissued_at":"2026-07-05T05:20:00.473022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:00.473022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.15180","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":"2026-07-05T05:20:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yUUBzZNAVx6P7Uc1CbtHUKcwBZcr1Xesjh8p+E9O7vuxRe5kBg8fWNUiK66ksmLWHrgDfp5kPu6K3pBEsYr+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:45:52.876093Z"},"content_sha256":"475301a15992bbeadd4d63486efe56d1b94b0d0ace3c6761b92e6d912a824a57","schema_version":"1.0","event_id":"sha256:475301a15992bbeadd4d63486efe56d1b94b0d0ace3c6761b92e6d912a824a57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GMIBWGVIZAQGMTHTP73YRRB2RB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Guoliang Kang, Runqi Wang, Shumin Han, Song Xue, Tian Wang, Xiaoyue Duan","submitted_at":"2022-11-28T09:47:13Z","abstract_excerpt":"Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a meta-model which may fast adapt to novel classes with only a few exemplars and meanwhile remain robust to adversarial attacks. The conventional solution for robust MAML is to introduce robustness-promoting regularization during meta-training stage. With such a regularization, previous robust MAML methods simply follow the typical MAML practice that the number of training shots should match with the number of test shots to achieve an optimal adaptation performance. However, although the robustness can be largely improved, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15180","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/2211.15180/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":"2026-07-05T05:20:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXAe7dJyqkZsnZGZ3ZWU2X47ZxvUbst6CmX6jZ8MsP3YevrsNErMqtp9t09KW69/uU31h5TjahAfeYxi4FqXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:45:52.876494Z"},"content_sha256":"07d6f19a2e5f899f068409c602e53bfd479d609b8d3c4ad1451918c24baf9cdf","schema_version":"1.0","event_id":"sha256:07d6f19a2e5f899f068409c602e53bfd479d609b8d3c4ad1451918c24baf9cdf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GMIBWGVIZAQGMTHTP73YRRB2RB/bundle.json","state_url":"https://pith.science/pith/GMIBWGVIZAQGMTHTP73YRRB2RB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GMIBWGVIZAQGMTHTP73YRRB2RB/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":"2026-07-06T08:45:52Z","links":{"resolver":"https://pith.science/pith/GMIBWGVIZAQGMTHTP73YRRB2RB","bundle":"https://pith.science/pith/GMIBWGVIZAQGMTHTP73YRRB2RB/bundle.json","state":"https://pith.science/pith/GMIBWGVIZAQGMTHTP73YRRB2RB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GMIBWGVIZAQGMTHTP73YRRB2RB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GMIBWGVIZAQGMTHTP73YRRB2RB","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":"83cf51bd21ab23410ae4258bfb0b0240eae2aa154d1bb2601175d62392b768ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T09:47:13Z","title_canon_sha256":"92ec8d6fa83b9ff47fa6d770e48c007ef7b68d6fcd30375c141dbb195ca55687"},"schema_version":"1.0","source":{"id":"2211.15180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15180","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15180v1","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15180","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"pith_short_12","alias_value":"GMIBWGVIZAQG","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"pith_short_16","alias_value":"GMIBWGVIZAQGMTHT","created_at":"2026-07-05T05:20:00Z"},{"alias_kind":"pith_short_8","alias_value":"GMIBWGVI","created_at":"2026-07-05T05:20:00Z"}],"graph_snapshots":[{"event_id":"sha256:07d6f19a2e5f899f068409c602e53bfd479d609b8d3c4ad1451918c24baf9cdf","target":"graph","created_at":"2026-07-05T05:20:00Z","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/2211.15180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a meta-model which may fast adapt to novel classes with only a few exemplars and meanwhile remain robust to adversarial attacks. The conventional solution for robust MAML is to introduce robustness-promoting regularization during meta-training stage. With such a regularization, previous robust MAML methods simply follow the typical MAML practice that the number of training shots should match with the number of test shots to achieve an optimal adaptation performance. However, although the robustness can be largely improved, ","authors_text":"Baochang Zhang, Guoliang Kang, Runqi Wang, Shumin Han, Song Xue, Tian Wang, Xiaoyue Duan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T09:47:13Z","title":"Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15180","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":"sha256:475301a15992bbeadd4d63486efe56d1b94b0d0ace3c6761b92e6d912a824a57","target":"record","created_at":"2026-07-05T05:20:00Z","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":"83cf51bd21ab23410ae4258bfb0b0240eae2aa154d1bb2601175d62392b768ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T09:47:13Z","title_canon_sha256":"92ec8d6fa83b9ff47fa6d770e48c007ef7b68d6fcd30375c141dbb195ca55687"},"schema_version":"1.0","source":{"id":"2211.15180","kind":"arxiv","version":1}},"canonical_sha256":"33101b1aa8c820664cf37ff788c43a887d3dbad4c29fb89e43a916583278af55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33101b1aa8c820664cf37ff788c43a887d3dbad4c29fb89e43a916583278af55","first_computed_at":"2026-07-05T05:20:00.473022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:20:00.473022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wkbSKPIjwyRGKtfewIrGXTLU/PjcY+A9h09g/mrVeJdK/ELaUjFTRBw/v4QF3O5h7j8ILUAMN1PgzCWKC6TmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:20:00.473415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.15180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:475301a15992bbeadd4d63486efe56d1b94b0d0ace3c6761b92e6d912a824a57","sha256:07d6f19a2e5f899f068409c602e53bfd479d609b8d3c4ad1451918c24baf9cdf"],"state_sha256":"1fa52a32cda7604fcb2175c1a2d319eaaeb6410a0ac4ff75306f59a6216b07da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIcDp7/QEoXXy4nV/wKZDQB5nqa4qKFV5kv/Ob7U7UmdaqkncHXdvH2lkKxL7yF0egUZjLTxJG20jWKeKRXdAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:45:52.878446Z","bundle_sha256":"82e02331a6b1ed395f19467f15b13422d95fd34730b46ed7f612b8303a24c302"}}