{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WKZL534ZAXBK5WRSP6QVERZNC3","short_pith_number":"pith:WKZL534Z","canonical_record":{"source":{"id":"2507.11710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T20:30:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68c40bdafdc53a5542d50f5fcb1b0bf0e591cb441f284cb7c64b67ada099786b","abstract_canon_sha256":"ba12dd3244dad0dfed952393aff32d9766232f1b07daa89dd78ec9b8619be24e"},"schema_version":"1.0"},"canonical_sha256":"b2b2beef9905c2aeda327fa152472d16ee8f141afb9a8fdce84eab39197588ef","source":{"kind":"arxiv","id":"2507.11710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11710","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11710v1","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11710","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"pith_short_12","alias_value":"WKZL534ZAXBK","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"pith_short_16","alias_value":"WKZL534ZAXBK5WRS","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"pith_short_8","alias_value":"WKZL534Z","created_at":"2026-07-05T11:37:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WKZL534ZAXBK5WRSP6QVERZNC3","target":"record","payload":{"canonical_record":{"source":{"id":"2507.11710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T20:30:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68c40bdafdc53a5542d50f5fcb1b0bf0e591cb441f284cb7c64b67ada099786b","abstract_canon_sha256":"ba12dd3244dad0dfed952393aff32d9766232f1b07daa89dd78ec9b8619be24e"},"schema_version":"1.0"},"canonical_sha256":"b2b2beef9905c2aeda327fa152472d16ee8f141afb9a8fdce84eab39197588ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:49.037966Z","signature_b64":"b+OL9xzxDXRbo5Mv2hzjzcGyQviRprO852JkTBDSp82CnNyPhVW+KBiCtE4X0OfD/cfEzHnK7XNvXKMR9zWdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b2beef9905c2aeda327fa152472d16ee8f141afb9a8fdce84eab39197588ef","last_reissued_at":"2026-07-05T11:37:49.037518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:49.037518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.11710","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":"2026-07-05T11:37:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SzfzREjDcrMMe305pklOXjiawfsSzcTW326TL84DoIDTWcV70bS8NsJg7RjIx1O5f5TjBb32pAHFA9RLTy0PDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:56:43.815542Z"},"content_sha256":"bf4ce0105078d904da6da909f7daad2eea34d094ba37f8a868d8143363056f0b","schema_version":"1.0","event_id":"sha256:bf4ce0105078d904da6da909f7daad2eea34d094ba37f8a868d8143363056f0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WKZL534ZAXBK5WRSP6QVERZNC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subgraph Generation for Generalizing on Out-of-Distribution Links","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Harry Shomer, Jay Revolinsky, Jiliang Tang","submitted_at":"2025-07-15T20:30:16Z","abstract_excerpt":"Graphs Neural Networks (GNNs) demonstrate high-performance on the link prediction (LP) task. However, these models often rely on all dataset samples being drawn from the same distribution. In addition, graph generative models (GGMs) show a pronounced ability to generate novel output graphs. Despite this, GGM applications remain largely limited to domain-specific tasks. To bridge this gap, we propose FLEX as a GGM framework which leverages two mechanism: (1) structurally-conditioned graph generation, and (2) adversarial co-training between an auto-encoder and GNN. As such, FLEX ensures structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11710","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/2507.11710/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":"2026-07-05T11:37:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KrV8Gy9pTP08aLh0IVBEAOEEyoccbFF+m2saMvBC9q//61UiWcqoyG55PSgYtIClfAqSdwcN8OtgaZBG3FrfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:56:43.816057Z"},"content_sha256":"398a23698f4799213b74d256ffc8076808926f3d373e6d6f1bdf629fbd3875af","schema_version":"1.0","event_id":"sha256:398a23698f4799213b74d256ffc8076808926f3d373e6d6f1bdf629fbd3875af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKZL534ZAXBK5WRSP6QVERZNC3/bundle.json","state_url":"https://pith.science/pith/WKZL534ZAXBK5WRSP6QVERZNC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKZL534ZAXBK5WRSP6QVERZNC3/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":"2026-08-07T10:56:43Z","links":{"resolver":"https://pith.science/pith/WKZL534ZAXBK5WRSP6QVERZNC3","bundle":"https://pith.science/pith/WKZL534ZAXBK5WRSP6QVERZNC3/bundle.json","state":"https://pith.science/pith/WKZL534ZAXBK5WRSP6QVERZNC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKZL534ZAXBK5WRSP6QVERZNC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WKZL534ZAXBK5WRSP6QVERZNC3","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":"ba12dd3244dad0dfed952393aff32d9766232f1b07daa89dd78ec9b8619be24e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T20:30:16Z","title_canon_sha256":"68c40bdafdc53a5542d50f5fcb1b0bf0e591cb441f284cb7c64b67ada099786b"},"schema_version":"1.0","source":{"id":"2507.11710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11710","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11710v1","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11710","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"pith_short_12","alias_value":"WKZL534ZAXBK","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"pith_short_16","alias_value":"WKZL534ZAXBK5WRS","created_at":"2026-07-05T11:37:49Z"},{"alias_kind":"pith_short_8","alias_value":"WKZL534Z","created_at":"2026-07-05T11:37:49Z"}],"graph_snapshots":[{"event_id":"sha256:398a23698f4799213b74d256ffc8076808926f3d373e6d6f1bdf629fbd3875af","target":"graph","created_at":"2026-07-05T11:37:49Z","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/2507.11710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphs Neural Networks (GNNs) demonstrate high-performance on the link prediction (LP) task. However, these models often rely on all dataset samples being drawn from the same distribution. In addition, graph generative models (GGMs) show a pronounced ability to generate novel output graphs. Despite this, GGM applications remain largely limited to domain-specific tasks. To bridge this gap, we propose FLEX as a GGM framework which leverages two mechanism: (1) structurally-conditioned graph generation, and (2) adversarial co-training between an auto-encoder and GNN. As such, FLEX ensures structur","authors_text":"Harry Shomer, Jay Revolinsky, Jiliang Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T20:30:16Z","title":"Subgraph Generation for Generalizing on Out-of-Distribution Links"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11710","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:bf4ce0105078d904da6da909f7daad2eea34d094ba37f8a868d8143363056f0b","target":"record","created_at":"2026-07-05T11:37:49Z","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":"ba12dd3244dad0dfed952393aff32d9766232f1b07daa89dd78ec9b8619be24e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T20:30:16Z","title_canon_sha256":"68c40bdafdc53a5542d50f5fcb1b0bf0e591cb441f284cb7c64b67ada099786b"},"schema_version":"1.0","source":{"id":"2507.11710","kind":"arxiv","version":1}},"canonical_sha256":"b2b2beef9905c2aeda327fa152472d16ee8f141afb9a8fdce84eab39197588ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2b2beef9905c2aeda327fa152472d16ee8f141afb9a8fdce84eab39197588ef","first_computed_at":"2026-07-05T11:37:49.037518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:49.037518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b+OL9xzxDXRbo5Mv2hzjzcGyQviRprO852JkTBDSp82CnNyPhVW+KBiCtE4X0OfD/cfEzHnK7XNvXKMR9zWdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:49.037966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf4ce0105078d904da6da909f7daad2eea34d094ba37f8a868d8143363056f0b","sha256:398a23698f4799213b74d256ffc8076808926f3d373e6d6f1bdf629fbd3875af"],"state_sha256":"66f94f7a41947fef5b5ac3937fb81a7260caed531c46835c1658f22bd1a3e3ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PpzwiwO8SufETV4Amaa3IXy9C9E5LoMILzCNhMbmFEjDSYcsuRW/r/xvrj2TnedXzRSNXwDOrJ5yd9vsKFjTAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:56:43.820892Z","bundle_sha256":"44ce96a35f133c82b499df7af6f8dde2b8a18a57d2fd4e74527db96ec56f686e"}}