{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:W7HFBG7WTVKPPJLPWS4BZIOH5C","short_pith_number":"pith:W7HFBG7W","canonical_record":{"source":{"id":"1907.07287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T23:22:14Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"a23271ec8e32b0dbf86a72f769ae2d4458d1a3be739a929cd21ad3a437920b46","abstract_canon_sha256":"69bd0d046f8caf1919f394a102e58d1d1e989541115f28413b0c23fdcfffdfde"},"schema_version":"1.0"},"canonical_sha256":"b7ce509bf69d54f7a56fb4b81ca1c7e88a1437b5ab9790bb0f40c01565dd5474","source":{"kind":"arxiv","id":"1907.07287","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07287","created_at":"2026-05-17T23:40:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07287v1","created_at":"2026-05-17T23:40:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07287","created_at":"2026-05-17T23:40:22Z"},{"alias_kind":"pith_short_12","alias_value":"W7HFBG7WTVKP","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"W7HFBG7WTVKPPJLP","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"W7HFBG7W","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:W7HFBG7WTVKPPJLPWS4BZIOH5C","target":"record","payload":{"canonical_record":{"source":{"id":"1907.07287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T23:22:14Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"a23271ec8e32b0dbf86a72f769ae2d4458d1a3be739a929cd21ad3a437920b46","abstract_canon_sha256":"69bd0d046f8caf1919f394a102e58d1d1e989541115f28413b0c23fdcfffdfde"},"schema_version":"1.0"},"canonical_sha256":"b7ce509bf69d54f7a56fb4b81ca1c7e88a1437b5ab9790bb0f40c01565dd5474","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:22.793653Z","signature_b64":"UOXQmgkX+oQ5B04/k7ltoo5rztxpzTB5auAhgyCc+8DI9VtBUXGXY9uNgDxbztQfTYYIuwwJIv1BzCtJmn10CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7ce509bf69d54f7a56fb4b81ca1c7e88a1437b5ab9790bb0f40c01565dd5474","last_reissued_at":"2026-05-17T23:40:22.792978Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:22.792978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.07287","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":"2026-05-17T23:40:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjslSwThfa+WMPDKIjD0tNNSKLeDw+P1DPg421ASJjYLqEQ9JPYcYl5+CPhLVb2emh/sNnBOZcZajpvurXPVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:04:13.009772Z"},"content_sha256":"b047e7b6fcd4b9196912c9d7d63c52f88ec4626ba55896e454e0907db6b40221","schema_version":"1.0","event_id":"sha256:b047e7b6fcd4b9196912c9d7d63c52f88ec4626ba55896e454e0907db6b40221"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:W7HFBG7WTVKPPJLPWS4BZIOH5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding Generalization in Gradient-Based Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Pal, Simon Guiroy, Vikas Verma","submitted_at":"2019-07-16T23:22:14Z","abstract_excerpt":"In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions, obtained after adapting the meta-train solution of the model, to new tasks via few steps of gradient-based fine-tuning, become flatter, lower in loss, and further away from the meta-train solution. We also show that those meta-test solutions become flatter even as generalization starts to degrade, thus providing an experimental evidence against the correlation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07287","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":""},"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":"2026-05-17T23:40:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4exskIIRxCvIFiupfQzbwbjYlYlcXhxa9xaa9uIlmaM5s4XakYtjwsX1p1dbt8m6w9HveCSnns1TvAk47KWyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:04:13.010416Z"},"content_sha256":"373f1e910ec8c01f661333b31a337bbbee6395c584c577ebb083179fb424dfaf","schema_version":"1.0","event_id":"sha256:373f1e910ec8c01f661333b31a337bbbee6395c584c577ebb083179fb424dfaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W7HFBG7WTVKPPJLPWS4BZIOH5C/bundle.json","state_url":"https://pith.science/pith/W7HFBG7WTVKPPJLPWS4BZIOH5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W7HFBG7WTVKPPJLPWS4BZIOH5C/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":"2026-05-25T15:04:13Z","links":{"resolver":"https://pith.science/pith/W7HFBG7WTVKPPJLPWS4BZIOH5C","bundle":"https://pith.science/pith/W7HFBG7WTVKPPJLPWS4BZIOH5C/bundle.json","state":"https://pith.science/pith/W7HFBG7WTVKPPJLPWS4BZIOH5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W7HFBG7WTVKPPJLPWS4BZIOH5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:W7HFBG7WTVKPPJLPWS4BZIOH5C","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":"69bd0d046f8caf1919f394a102e58d1d1e989541115f28413b0c23fdcfffdfde","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T23:22:14Z","title_canon_sha256":"a23271ec8e32b0dbf86a72f769ae2d4458d1a3be739a929cd21ad3a437920b46"},"schema_version":"1.0","source":{"id":"1907.07287","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07287","created_at":"2026-05-17T23:40:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07287v1","created_at":"2026-05-17T23:40:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07287","created_at":"2026-05-17T23:40:22Z"},{"alias_kind":"pith_short_12","alias_value":"W7HFBG7WTVKP","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"W7HFBG7WTVKPPJLP","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"W7HFBG7W","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:373f1e910ec8c01f661333b31a337bbbee6395c584c577ebb083179fb424dfaf","target":"graph","created_at":"2026-05-17T23:40:22Z","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"},"paper":{"abstract_excerpt":"In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions, obtained after adapting the meta-train solution of the model, to new tasks via few steps of gradient-based fine-tuning, become flatter, lower in loss, and further away from the meta-train solution. We also show that those meta-test solutions become flatter even as generalization starts to degrade, thus providing an experimental evidence against the correlation","authors_text":"Christopher Pal, Simon Guiroy, Vikas Verma","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T23:22:14Z","title":"Towards Understanding Generalization in Gradient-Based Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07287","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:b047e7b6fcd4b9196912c9d7d63c52f88ec4626ba55896e454e0907db6b40221","target":"record","created_at":"2026-05-17T23:40:22Z","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":"69bd0d046f8caf1919f394a102e58d1d1e989541115f28413b0c23fdcfffdfde","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T23:22:14Z","title_canon_sha256":"a23271ec8e32b0dbf86a72f769ae2d4458d1a3be739a929cd21ad3a437920b46"},"schema_version":"1.0","source":{"id":"1907.07287","kind":"arxiv","version":1}},"canonical_sha256":"b7ce509bf69d54f7a56fb4b81ca1c7e88a1437b5ab9790bb0f40c01565dd5474","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7ce509bf69d54f7a56fb4b81ca1c7e88a1437b5ab9790bb0f40c01565dd5474","first_computed_at":"2026-05-17T23:40:22.792978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:22.792978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UOXQmgkX+oQ5B04/k7ltoo5rztxpzTB5auAhgyCc+8DI9VtBUXGXY9uNgDxbztQfTYYIuwwJIv1BzCtJmn10CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:22.793653Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.07287","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b047e7b6fcd4b9196912c9d7d63c52f88ec4626ba55896e454e0907db6b40221","sha256:373f1e910ec8c01f661333b31a337bbbee6395c584c577ebb083179fb424dfaf"],"state_sha256":"69310a37ecc432e768fc42cb1f12d3f599d843e03d20be21ec1e8b1de3dc91c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MshfROWxlG71FZHk7M3mLTe+GUOD2us6HWfE7fk/0m4m53o7f4EjD9sbk8L/PGxZpcCs92uKwNWkbSFX3vd+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:04:13.013956Z","bundle_sha256":"c6640811ef4e87b6f041eeffc17632c64b9509774e869b4e23449efe5642278d"}}