{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LIMRAP3ZWV4MQCCZ75LBXGUVXK","short_pith_number":"pith:LIMRAP3Z","canonical_record":{"source":{"id":"2203.10453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-20T04:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"50c9cea80f2edd84dd185654fb1dbaa1f85642e1383c0c19ced46f6eb8d7d86b","abstract_canon_sha256":"893d63810bc83c14a75182fb48419a9c26db56719719dfa713a7f7eabe2322ca"},"schema_version":"1.0"},"canonical_sha256":"5a19103f79b578c80859ff561b9a95babba6860b83cd174b04448ae3c9780ee8","source":{"kind":"arxiv","id":"2203.10453","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10453","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10453v1","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10453","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"LIMRAP3ZWV4M","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"LIMRAP3ZWV4MQCCZ","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"LIMRAP3Z","created_at":"2026-07-05T04:22:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LIMRAP3ZWV4MQCCZ75LBXGUVXK","target":"record","payload":{"canonical_record":{"source":{"id":"2203.10453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-20T04:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"50c9cea80f2edd84dd185654fb1dbaa1f85642e1383c0c19ced46f6eb8d7d86b","abstract_canon_sha256":"893d63810bc83c14a75182fb48419a9c26db56719719dfa713a7f7eabe2322ca"},"schema_version":"1.0"},"canonical_sha256":"5a19103f79b578c80859ff561b9a95babba6860b83cd174b04448ae3c9780ee8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:05.725130Z","signature_b64":"AzFf6FfPFJ74syRTobQ0coOfvf2mj5uMaPfh70IZzmtWDBLWvNbZMyTELAiW+6de8PcMtoTOP9ccD6g3Vv0OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a19103f79b578c80859ff561b9a95babba6860b83cd174b04448ae3c9780ee8","last_reissued_at":"2026-07-05T04:22:05.724698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:05.724698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.10453","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":"2026-07-05T04:22:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5v4kMXwnrcIzipcMOIpAnQYn6ULUf4tcuWFFXI2gCePm9rFfQHjpeEn69gD/72SNoUX8FVHg6tB/eQm82zdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:28:53.971998Z"},"content_sha256":"91752970916262d46fe11ed58349717f8928fdadb596676898e52d145e3d368c","schema_version":"1.0","event_id":"sha256:91752970916262d46fe11ed58349717f8928fdadb596676898e52d145e3d368c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LIMRAP3ZWV4MQCCZ75LBXGUVXK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiying Zhang, Long-Kai Huang, Xi Xiao, Yatao Bian, Yu Rong","submitted_at":"2022-03-20T04:41:17Z","abstract_excerpt":"Recently, the pretrain-finetuning paradigm has attracted tons of attention in graph learning community due to its power of alleviating the lack of labels problem in many real-world applications. Current studies use existing techniques, such as weight constraint, representation constraint, which are derived from images or text data, to transfer the invariant knowledge from the pre-train stage to fine-tuning stage. However, these methods failed to preserve invariances from graph structure and Graph Neural Network (GNN) style models. In this paper, we present a novel optimal transport-based fine-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10453","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/2203.10453/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":"2026-07-05T04:22:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gjqg0BcMQsPSe1v1jC7+ik8A9JmV5pCz0OX+QoNQ3fmo5zUtIZFenyxcFB3FteOpqobHg/3pwc5CPZts65QlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:28:53.972384Z"},"content_sha256":"e3b47ad0e13fc15b2ba7c3be64bfe5c53878bcd1928077b1fca62b2f5924bc1c","schema_version":"1.0","event_id":"sha256:e3b47ad0e13fc15b2ba7c3be64bfe5c53878bcd1928077b1fca62b2f5924bc1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIMRAP3ZWV4MQCCZ75LBXGUVXK/bundle.json","state_url":"https://pith.science/pith/LIMRAP3ZWV4MQCCZ75LBXGUVXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIMRAP3ZWV4MQCCZ75LBXGUVXK/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":"2026-07-07T13:28:53Z","links":{"resolver":"https://pith.science/pith/LIMRAP3ZWV4MQCCZ75LBXGUVXK","bundle":"https://pith.science/pith/LIMRAP3ZWV4MQCCZ75LBXGUVXK/bundle.json","state":"https://pith.science/pith/LIMRAP3ZWV4MQCCZ75LBXGUVXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIMRAP3ZWV4MQCCZ75LBXGUVXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LIMRAP3ZWV4MQCCZ75LBXGUVXK","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":"893d63810bc83c14a75182fb48419a9c26db56719719dfa713a7f7eabe2322ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-20T04:41:17Z","title_canon_sha256":"50c9cea80f2edd84dd185654fb1dbaa1f85642e1383c0c19ced46f6eb8d7d86b"},"schema_version":"1.0","source":{"id":"2203.10453","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10453","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10453v1","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10453","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"LIMRAP3ZWV4M","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"LIMRAP3ZWV4MQCCZ","created_at":"2026-07-05T04:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"LIMRAP3Z","created_at":"2026-07-05T04:22:05Z"}],"graph_snapshots":[{"event_id":"sha256:e3b47ad0e13fc15b2ba7c3be64bfe5c53878bcd1928077b1fca62b2f5924bc1c","target":"graph","created_at":"2026-07-05T04:22:05Z","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/2203.10453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the pretrain-finetuning paradigm has attracted tons of attention in graph learning community due to its power of alleviating the lack of labels problem in many real-world applications. Current studies use existing techniques, such as weight constraint, representation constraint, which are derived from images or text data, to transfer the invariant knowledge from the pre-train stage to fine-tuning stage. However, these methods failed to preserve invariances from graph structure and Graph Neural Network (GNN) style models. In this paper, we present a novel optimal transport-based fine-","authors_text":"Jiying Zhang, Long-Kai Huang, Xi Xiao, Yatao Bian, Yu Rong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-20T04:41:17Z","title":"Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10453","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":"sha256:91752970916262d46fe11ed58349717f8928fdadb596676898e52d145e3d368c","target":"record","created_at":"2026-07-05T04:22:05Z","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":"893d63810bc83c14a75182fb48419a9c26db56719719dfa713a7f7eabe2322ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-20T04:41:17Z","title_canon_sha256":"50c9cea80f2edd84dd185654fb1dbaa1f85642e1383c0c19ced46f6eb8d7d86b"},"schema_version":"1.0","source":{"id":"2203.10453","kind":"arxiv","version":1}},"canonical_sha256":"5a19103f79b578c80859ff561b9a95babba6860b83cd174b04448ae3c9780ee8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a19103f79b578c80859ff561b9a95babba6860b83cd174b04448ae3c9780ee8","first_computed_at":"2026-07-05T04:22:05.724698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:05.724698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AzFf6FfPFJ74syRTobQ0coOfvf2mj5uMaPfh70IZzmtWDBLWvNbZMyTELAiW+6de8PcMtoTOP9ccD6g3Vv0OBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:05.725130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10453","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91752970916262d46fe11ed58349717f8928fdadb596676898e52d145e3d368c","sha256:e3b47ad0e13fc15b2ba7c3be64bfe5c53878bcd1928077b1fca62b2f5924bc1c"],"state_sha256":"b56e831bb34295b1f9da4911d27c32410c931df9b8f03ea87d3c2a76d62e2d70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c11mnhT8+jOAZKbpmNsro7pMoBUuRDvYmrk3BvozHGP7KmTYrZYi3MkubOMl27L0Zlm5iYhDfKa2gf60scoyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:28:53.974286Z","bundle_sha256":"959edc008d5233ced7bb47dde5e9124b0755d775bf13b8bc988c65d267328d39"}}