{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5GJSSDIZFHUUPYJV3YXTALQCV3","short_pith_number":"pith:5GJSSDIZ","canonical_record":{"source":{"id":"2607.03097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T08:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"def6ed4e8d327b48debbf53c0240a69a9ac25dcc277f31e8336ecc0bf3cc0bed","abstract_canon_sha256":"8f3a07e240e4bf7efc5fe421acd24a70b75a626990ba060b768ed5d2a0640639"},"schema_version":"1.0"},"canonical_sha256":"e993290d1929e947e135de2f302e02aef0772b2ab9b9dcd769a998207a833eb6","source":{"kind":"arxiv","id":"2607.03097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03097","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03097v1","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03097","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"pith_short_12","alias_value":"5GJSSDIZFHUU","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"pith_short_16","alias_value":"5GJSSDIZFHUUPYJV","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"pith_short_8","alias_value":"5GJSSDIZ","created_at":"2026-07-07T01:16:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5GJSSDIZFHUUPYJV3YXTALQCV3","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T08:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"def6ed4e8d327b48debbf53c0240a69a9ac25dcc277f31e8336ecc0bf3cc0bed","abstract_canon_sha256":"8f3a07e240e4bf7efc5fe421acd24a70b75a626990ba060b768ed5d2a0640639"},"schema_version":"1.0"},"canonical_sha256":"e993290d1929e947e135de2f302e02aef0772b2ab9b9dcd769a998207a833eb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:42.850494Z","signature_b64":"Rxu0talY7TAQp1TVnfj09FocG29EsPI5nKWkO11OASG0SHRZLS9yKoqcn3nG1StU5+5U7Nq8Y21nxeBWCytuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e993290d1929e947e135de2f302e02aef0772b2ab9b9dcd769a998207a833eb6","last_reissued_at":"2026-07-07T01:16:42.850084Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:42.850084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03097","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":"2026-07-07T01:16:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ttv5zD4XT2rCEZXPSFY9r8bLJlq5BeJQyPVMw7hYJgBpcQFg1MPXKFp2YesF7pvGyLO8qMe6AJYb30t58D5RBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:47.552914Z"},"content_sha256":"e0b05f8f6572e2ece1d2670c64435af297abf4beb63044117c2c5cfc030e285b","schema_version":"1.0","event_id":"sha256:e0b05f8f6572e2ece1d2670c64435af297abf4beb63044117c2c5cfc030e285b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5GJSSDIZFHUUPYJV3YXTALQCV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heterogeneous Graph Condensation via Role-Aware Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fuyan Ou, Ye Yuan, Yulin Hu","submitted_at":"2026-07-03T08:34:11Z","abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) have exhibited remarkable efficacy in modeling complex systems with multiple types of nodes and relations, yet their training on large-scale heterogeneous graphs remains computationally prohibitive. Although graph condensation methods can effectively improve learning efficiency on large-scale graphs, existing condensation processes are mainly designed for homogeneous graphs and typically rely on computationally expensive gradient matching or bilevel optimization paradigms, rendering them impractical for heterogeneous settings. To address these limita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03097","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/2607.03097/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":"2026-07-07T01:16:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+SiN6oNL89LDtxh/GMN2f2XDKfuIZTMgkzNC6BkWqkKx32GH9vLS6f8DD2zD0AK2+bu0d0dEDUBcridAvUJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:47.553657Z"},"content_sha256":"f72dfa83d6f598059550797aea68ccb8fbc8547114439d96363d0e80b859109d","schema_version":"1.0","event_id":"sha256:f72dfa83d6f598059550797aea68ccb8fbc8547114439d96363d0e80b859109d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5GJSSDIZFHUUPYJV3YXTALQCV3/bundle.json","state_url":"https://pith.science/pith/5GJSSDIZFHUUPYJV3YXTALQCV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5GJSSDIZFHUUPYJV3YXTALQCV3/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":"2026-08-04T21:29:47Z","links":{"resolver":"https://pith.science/pith/5GJSSDIZFHUUPYJV3YXTALQCV3","bundle":"https://pith.science/pith/5GJSSDIZFHUUPYJV3YXTALQCV3/bundle.json","state":"https://pith.science/pith/5GJSSDIZFHUUPYJV3YXTALQCV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5GJSSDIZFHUUPYJV3YXTALQCV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5GJSSDIZFHUUPYJV3YXTALQCV3","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":"8f3a07e240e4bf7efc5fe421acd24a70b75a626990ba060b768ed5d2a0640639","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T08:34:11Z","title_canon_sha256":"def6ed4e8d327b48debbf53c0240a69a9ac25dcc277f31e8336ecc0bf3cc0bed"},"schema_version":"1.0","source":{"id":"2607.03097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03097","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03097v1","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03097","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"pith_short_12","alias_value":"5GJSSDIZFHUU","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"pith_short_16","alias_value":"5GJSSDIZFHUUPYJV","created_at":"2026-07-07T01:16:42Z"},{"alias_kind":"pith_short_8","alias_value":"5GJSSDIZ","created_at":"2026-07-07T01:16:42Z"}],"graph_snapshots":[{"event_id":"sha256:f72dfa83d6f598059550797aea68ccb8fbc8547114439d96363d0e80b859109d","target":"graph","created_at":"2026-07-07T01:16:42Z","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/2607.03097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) have exhibited remarkable efficacy in modeling complex systems with multiple types of nodes and relations, yet their training on large-scale heterogeneous graphs remains computationally prohibitive. Although graph condensation methods can effectively improve learning efficiency on large-scale graphs, existing condensation processes are mainly designed for homogeneous graphs and typically rely on computationally expensive gradient matching or bilevel optimization paradigms, rendering them impractical for heterogeneous settings. To address these limita","authors_text":"Fuyan Ou, Ye Yuan, Yulin Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T08:34:11Z","title":"Heterogeneous Graph Condensation via Role-Aware Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03097","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:e0b05f8f6572e2ece1d2670c64435af297abf4beb63044117c2c5cfc030e285b","target":"record","created_at":"2026-07-07T01:16:42Z","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":"8f3a07e240e4bf7efc5fe421acd24a70b75a626990ba060b768ed5d2a0640639","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T08:34:11Z","title_canon_sha256":"def6ed4e8d327b48debbf53c0240a69a9ac25dcc277f31e8336ecc0bf3cc0bed"},"schema_version":"1.0","source":{"id":"2607.03097","kind":"arxiv","version":1}},"canonical_sha256":"e993290d1929e947e135de2f302e02aef0772b2ab9b9dcd769a998207a833eb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e993290d1929e947e135de2f302e02aef0772b2ab9b9dcd769a998207a833eb6","first_computed_at":"2026-07-07T01:16:42.850084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:42.850084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rxu0talY7TAQp1TVnfj09FocG29EsPI5nKWkO11OASG0SHRZLS9yKoqcn3nG1StU5+5U7Nq8Y21nxeBWCytuDA==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:42.850494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0b05f8f6572e2ece1d2670c64435af297abf4beb63044117c2c5cfc030e285b","sha256:f72dfa83d6f598059550797aea68ccb8fbc8547114439d96363d0e80b859109d"],"state_sha256":"f8d60cdd40dee6595bdb9cf994ed7eff4370587b0469b337619af5b51d4d72be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asOnOTnZX2VMExhKXEuqrGYCENDu57TMqZ3+8deWgNQiIm/HuJsX0BJrKoeDFSArZ1bl6568UVQmHAUxqNG6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:29:47.560786Z","bundle_sha256":"ea7f4a212df2effe74f30e0bf1a1b196cc9dba98c10ca1be0d1a7179c0541a2c"}}