{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YF4VPPM7KERC6LVDRFCEYC6CDA","short_pith_number":"pith:YF4VPPM7","canonical_record":{"source":{"id":"2312.10988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T07:26:56Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"88b41bca03b32a77150db4f88c8641a0894dfe1cb7daee7c4976141277ad8b6f","abstract_canon_sha256":"c73c6b2705dfc2207cce6e64c76218a388258c4ccabac216c4998aff6375403b"},"schema_version":"1.0"},"canonical_sha256":"c17957bd9f51222f2ea389444c0bc2182252c012be43fac25b53049177c981e4","source":{"kind":"arxiv","id":"2312.10988","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10988","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10988v1","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10988","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"YF4VPPM7KERC","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"YF4VPPM7KERC6LVD","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"YF4VPPM7","created_at":"2026-07-05T07:25:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YF4VPPM7KERC6LVDRFCEYC6CDA","target":"record","payload":{"canonical_record":{"source":{"id":"2312.10988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T07:26:56Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"88b41bca03b32a77150db4f88c8641a0894dfe1cb7daee7c4976141277ad8b6f","abstract_canon_sha256":"c73c6b2705dfc2207cce6e64c76218a388258c4ccabac216c4998aff6375403b"},"schema_version":"1.0"},"canonical_sha256":"c17957bd9f51222f2ea389444c0bc2182252c012be43fac25b53049177c981e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:15.490153Z","signature_b64":"sOoWoDqMwKHZBKPnwObFISeDcNQX/EgmfImunQuH94d8D+q3Qae9ajBfGfNkp7xSYX03ClCEGbSOKdBOZXmWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c17957bd9f51222f2ea389444c0bc2182252c012be43fac25b53049177c981e4","last_reissued_at":"2026-07-05T07:25:15.489660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:15.489660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.10988","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":"2026-07-05T07:25:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fiPlFEmi5wrXRBdiXNyNHJaPVJUiZW064nfjnLg1uz2mVFfOyBkA75/w1i0A8sJ0mlCoyq+jHNv7ViHvZVUjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:49:04.331288Z"},"content_sha256":"21ba045bef30b45ceaec993ac4a5b7fe0bbfce45bc61625d3d030b300126f54e","schema_version":"1.0","event_id":"sha256:21ba045bef30b45ceaec993ac4a5b7fe0bbfce45bc61625d3d030b300126f54e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YF4VPPM7KERC6LVDRFCEYC6CDA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Cheng Yang, Chuan Shi, Haoyang Li, Tao Tao, Tianrui Jia","submitted_at":"2023-12-18T07:26:56Z","abstract_excerpt":"Graph neural networks (GNNs) have been demonstrated to perform well in graph representation learning, but always lacking in generalization capability when tackling out-of-distribution (OOD) data. Graph invariant learning methods, backed by the invariance principle among defined multiple environments, have shown effectiveness in dealing with this issue. However, existing methods heavily rely on well-predefined or accurately generated environment partitions, which are hard to be obtained in practice, leading to sub-optimal OOD generalization performances. In this paper, we propose a novel graph "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10988","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/2312.10988/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":"2026-07-05T07:25:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgFxvd7sqXtGiMsx2s1DhqoawGgWayfbi9lVno/bdz8BHeSbS35iM3l45hg/hwjuUQQg0KyvaLX2I49KWXGjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:49:04.331788Z"},"content_sha256":"901eefe232da07239825f95a690a2f38add81ea2789543b7a903f32b599c3977","schema_version":"1.0","event_id":"sha256:901eefe232da07239825f95a690a2f38add81ea2789543b7a903f32b599c3977"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YF4VPPM7KERC6LVDRFCEYC6CDA/bundle.json","state_url":"https://pith.science/pith/YF4VPPM7KERC6LVDRFCEYC6CDA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YF4VPPM7KERC6LVDRFCEYC6CDA/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":"2026-08-06T09:49:04Z","links":{"resolver":"https://pith.science/pith/YF4VPPM7KERC6LVDRFCEYC6CDA","bundle":"https://pith.science/pith/YF4VPPM7KERC6LVDRFCEYC6CDA/bundle.json","state":"https://pith.science/pith/YF4VPPM7KERC6LVDRFCEYC6CDA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YF4VPPM7KERC6LVDRFCEYC6CDA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YF4VPPM7KERC6LVDRFCEYC6CDA","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":"c73c6b2705dfc2207cce6e64c76218a388258c4ccabac216c4998aff6375403b","cross_cats_sorted":["cs.SI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T07:26:56Z","title_canon_sha256":"88b41bca03b32a77150db4f88c8641a0894dfe1cb7daee7c4976141277ad8b6f"},"schema_version":"1.0","source":{"id":"2312.10988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10988","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10988v1","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10988","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"YF4VPPM7KERC","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"YF4VPPM7KERC6LVD","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"YF4VPPM7","created_at":"2026-07-05T07:25:15Z"}],"graph_snapshots":[{"event_id":"sha256:901eefe232da07239825f95a690a2f38add81ea2789543b7a903f32b599c3977","target":"graph","created_at":"2026-07-05T07:25:15Z","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/2312.10988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks (GNNs) have been demonstrated to perform well in graph representation learning, but always lacking in generalization capability when tackling out-of-distribution (OOD) data. Graph invariant learning methods, backed by the invariance principle among defined multiple environments, have shown effectiveness in dealing with this issue. However, existing methods heavily rely on well-predefined or accurately generated environment partitions, which are hard to be obtained in practice, leading to sub-optimal OOD generalization performances. In this paper, we propose a novel graph ","authors_text":"Cheng Yang, Chuan Shi, Haoyang Li, Tao Tao, Tianrui Jia","cross_cats":["cs.SI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T07:26:56Z","title":"Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10988","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":"sha256:21ba045bef30b45ceaec993ac4a5b7fe0bbfce45bc61625d3d030b300126f54e","target":"record","created_at":"2026-07-05T07:25:15Z","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":"c73c6b2705dfc2207cce6e64c76218a388258c4ccabac216c4998aff6375403b","cross_cats_sorted":["cs.SI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T07:26:56Z","title_canon_sha256":"88b41bca03b32a77150db4f88c8641a0894dfe1cb7daee7c4976141277ad8b6f"},"schema_version":"1.0","source":{"id":"2312.10988","kind":"arxiv","version":1}},"canonical_sha256":"c17957bd9f51222f2ea389444c0bc2182252c012be43fac25b53049177c981e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c17957bd9f51222f2ea389444c0bc2182252c012be43fac25b53049177c981e4","first_computed_at":"2026-07-05T07:25:15.489660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:15.489660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sOoWoDqMwKHZBKPnwObFISeDcNQX/EgmfImunQuH94d8D+q3Qae9ajBfGfNkp7xSYX03ClCEGbSOKdBOZXmWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:15.490153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21ba045bef30b45ceaec993ac4a5b7fe0bbfce45bc61625d3d030b300126f54e","sha256:901eefe232da07239825f95a690a2f38add81ea2789543b7a903f32b599c3977"],"state_sha256":"ea23d186fc029a7664167031f86c30eb48aaeca777076106cf68ce323c741354"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u+o2weZX/fTk0j/MFJW/b6IZkb4CxeVUV62+r4akYhf1FJPqSRz8/e72GXrMiirbr7m6t4VsoMbS9dRi8/5eCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:49:04.335907Z","bundle_sha256":"3c14557507f510ba392174b708ae4e53db1d38a8d94ba561611e86f2a8341cc1"}}