{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YX3IW4BWPLODF3ZRRVKWSDRVKV","short_pith_number":"pith:YX3IW4BW","canonical_record":{"source":{"id":"2306.09121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T13:29:09Z","cross_cats_sorted":[],"title_canon_sha256":"f6c41317119eca279d44e8933b638208591e9bcd1644eb5850553efed293362b","abstract_canon_sha256":"2284f3a8bcc672b0d950e667475f9d3793b7d3b8df1d7e90527f5feb805aa252"},"schema_version":"1.0"},"canonical_sha256":"c5f68b70367adc32ef318d55690e355546d8f26a93a9c44edd6bffe7772b6628","source":{"kind":"arxiv","id":"2306.09121","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09121","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09121v1","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09121","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"pith_short_12","alias_value":"YX3IW4BWPLOD","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"pith_short_16","alias_value":"YX3IW4BWPLODF3ZR","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"pith_short_8","alias_value":"YX3IW4BW","created_at":"2026-07-05T06:47:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YX3IW4BWPLODF3ZRRVKWSDRVKV","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T13:29:09Z","cross_cats_sorted":[],"title_canon_sha256":"f6c41317119eca279d44e8933b638208591e9bcd1644eb5850553efed293362b","abstract_canon_sha256":"2284f3a8bcc672b0d950e667475f9d3793b7d3b8df1d7e90527f5feb805aa252"},"schema_version":"1.0"},"canonical_sha256":"c5f68b70367adc32ef318d55690e355546d8f26a93a9c44edd6bffe7772b6628","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:22.981434Z","signature_b64":"K9Y1xOwwjd/kTTg3zLH8vCtLGFatynByEI0V8WtCr0SaWbvu1Pz85xzbtom2byqMlqbQRddYjmTN6PZOmWVCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5f68b70367adc32ef318d55690e355546d8f26a93a9c44edd6bffe7772b6628","last_reissued_at":"2026-07-05T06:47:22.980924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:22.980924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09121","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":"2026-07-05T06:47:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+rDQD9zFYF+km6QilQ2fFYPhy9lyRmxJSQ67TYdDxdoeOy/VetkBTt9iM/tLIOto24HjHJl7p0hBiyloJ8ZOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:13:58.852222Z"},"content_sha256":"9432d08b1476f6e58b061ed494f3d7b1a7acade271b5bbdffd1e773a45bc80dd","schema_version":"1.0","event_id":"sha256:9432d08b1476f6e58b061ed494f3d7b1a7acade271b5bbdffd1e773a45bc80dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YX3IW4BWPLODF3ZRRVKWSDRVKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ansgar Scherp, Nicolas Lell","submitted_at":"2023-06-15T13:29:09Z","abstract_excerpt":"When training a Neural Network, it is optimized using the available training data with the hope that it generalizes well to new or unseen testing data. At the same absolute value, a flat minimum in the loss landscape is presumed to generalize better than a sharp minimum. Methods for determining flat minima have been mostly researched for independent and identically distributed (i. i. d.) data such as images. Graphs are inherently non-i. i. d. since the vertices are edge-connected. We investigate flat minima methods and combinations of those methods for training graph neural networks (GNNs). We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09121","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/2306.09121/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":"2026-07-05T06:47:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jIlko6ygrY/Ltzq4T/m4Eb7a6vvbMJwzCiBixQy5Qcf1LwJh9bC9/AiaIZmxxU0ASiMvJMF59EyH+5pUiOhiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:13:58.852605Z"},"content_sha256":"d8716f9118ee52941cf183303fad99a5dc9d0abf38ddd6b7244255647e4e89e5","schema_version":"1.0","event_id":"sha256:d8716f9118ee52941cf183303fad99a5dc9d0abf38ddd6b7244255647e4e89e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YX3IW4BWPLODF3ZRRVKWSDRVKV/bundle.json","state_url":"https://pith.science/pith/YX3IW4BWPLODF3ZRRVKWSDRVKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YX3IW4BWPLODF3ZRRVKWSDRVKV/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":"2026-07-31T15:13:58Z","links":{"resolver":"https://pith.science/pith/YX3IW4BWPLODF3ZRRVKWSDRVKV","bundle":"https://pith.science/pith/YX3IW4BWPLODF3ZRRVKWSDRVKV/bundle.json","state":"https://pith.science/pith/YX3IW4BWPLODF3ZRRVKWSDRVKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YX3IW4BWPLODF3ZRRVKWSDRVKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YX3IW4BWPLODF3ZRRVKWSDRVKV","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":"2284f3a8bcc672b0d950e667475f9d3793b7d3b8df1d7e90527f5feb805aa252","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T13:29:09Z","title_canon_sha256":"f6c41317119eca279d44e8933b638208591e9bcd1644eb5850553efed293362b"},"schema_version":"1.0","source":{"id":"2306.09121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09121","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09121v1","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09121","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"pith_short_12","alias_value":"YX3IW4BWPLOD","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"pith_short_16","alias_value":"YX3IW4BWPLODF3ZR","created_at":"2026-07-05T06:47:22Z"},{"alias_kind":"pith_short_8","alias_value":"YX3IW4BW","created_at":"2026-07-05T06:47:22Z"}],"graph_snapshots":[{"event_id":"sha256:d8716f9118ee52941cf183303fad99a5dc9d0abf38ddd6b7244255647e4e89e5","target":"graph","created_at":"2026-07-05T06:47:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.09121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When training a Neural Network, it is optimized using the available training data with the hope that it generalizes well to new or unseen testing data. At the same absolute value, a flat minimum in the loss landscape is presumed to generalize better than a sharp minimum. Methods for determining flat minima have been mostly researched for independent and identically distributed (i. i. d.) data such as images. Graphs are inherently non-i. i. d. since the vertices are edge-connected. We investigate flat minima methods and combinations of those methods for training graph neural networks (GNNs). We","authors_text":"Ansgar Scherp, Nicolas Lell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T13:29:09Z","title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09121","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":"sha256:9432d08b1476f6e58b061ed494f3d7b1a7acade271b5bbdffd1e773a45bc80dd","target":"record","created_at":"2026-07-05T06:47:22Z","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":"2284f3a8bcc672b0d950e667475f9d3793b7d3b8df1d7e90527f5feb805aa252","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T13:29:09Z","title_canon_sha256":"f6c41317119eca279d44e8933b638208591e9bcd1644eb5850553efed293362b"},"schema_version":"1.0","source":{"id":"2306.09121","kind":"arxiv","version":1}},"canonical_sha256":"c5f68b70367adc32ef318d55690e355546d8f26a93a9c44edd6bffe7772b6628","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5f68b70367adc32ef318d55690e355546d8f26a93a9c44edd6bffe7772b6628","first_computed_at":"2026-07-05T06:47:22.980924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:22.980924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K9Y1xOwwjd/kTTg3zLH8vCtLGFatynByEI0V8WtCr0SaWbvu1Pz85xzbtom2byqMlqbQRddYjmTN6PZOmWVCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:22.981434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9432d08b1476f6e58b061ed494f3d7b1a7acade271b5bbdffd1e773a45bc80dd","sha256:d8716f9118ee52941cf183303fad99a5dc9d0abf38ddd6b7244255647e4e89e5"],"state_sha256":"9d53dc030590e2a009c0b96db7ea76fbbc1f57974b1524bfe4819d66427c3f7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7NnPN8oS0Ir6hkB7EaT8qA37yFFGpGXDsxEzcK9Qk9w5XKZInXc4iAy4x02n1J1kVCZC8FaKgoHJBBMeDf0tCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T15:13:58.855799Z","bundle_sha256":"18b17841bc649ae0893b98b5505fb70f2365bed2040d8ecb8c1bdeb0b02d7910"}}