{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WMIYVDQGXN657S2T6754MPCHHZ","short_pith_number":"pith:WMIYVDQG","schema_version":"1.0","canonical_sha256":"b3118a8e06bb7ddfcb53f7fbc63c473e6499b725db5e48550d49e8604b426ff5","source":{"kind":"arxiv","id":"2607.27767","version":1},"attestation_state":"computed","paper":{"title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.soc-ph"],"primary_cat":"cs.LG","authors_text":"M. \\'Angeles Serrano, Mari\\'an Bogu\\~n\\'a, Melanie Weber, Pedro Almagro-Blanco, Robert Jankowski","submitted_at":"2026-07-30T07:03:23Z","abstract_excerpt":"Graph neural networks (GNNs) can operate on large graphs but become infrastructure-sensitive at the scale of millions of nodes and typically require scalable training techniques for even larger graphs. This raises a central question: when can a model trained on a smaller, scaled-down replica of a graph be deployed on the full-resolution graph without retraining? We introduce a zero-shot transfer protocol in which a GNN is trained on a graph coarse-grained by geometric renormalization (GR), and the resulting weights are transferred directly to the original network. Across synthetic and real-wor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.27767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T07:03:23Z","cross_cats_sorted":["cs.AI","physics.soc-ph"],"title_canon_sha256":"5d9032d44e398bf7105a48a28e073c0f4121d3c4d0ba45a298539160764650b5","abstract_canon_sha256":"84ad94dcd84d3b5ddde6bcc3c54b7693ef8d59ddf596f2121c47472dc5d381bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3118a8e06bb7ddfcb53f7fbc63c473e6499b725db5e48550d49e8604b426ff5","last_reissued_at":"2026-07-31T01:30:31.799724Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:30:31.799724Z"},"graph_snapshot":{"paper":{"title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.soc-ph"],"primary_cat":"cs.LG","authors_text":"M. \\'Angeles Serrano, Mari\\'an Bogu\\~n\\'a, Melanie Weber, Pedro Almagro-Blanco, Robert Jankowski","submitted_at":"2026-07-30T07:03:23Z","abstract_excerpt":"Graph neural networks (GNNs) can operate on large graphs but become infrastructure-sensitive at the scale of millions of nodes and typically require scalable training techniques for even larger graphs. This raises a central question: when can a model trained on a smaller, scaled-down replica of a graph be deployed on the full-resolution graph without retraining? We introduce a zero-shot transfer protocol in which a GNN is trained on a graph coarse-grained by geometric renormalization (GR), and the resulting weights are transferred directly to the original network. Across synthetic and real-wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27767","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/2607.27767/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.27767","created_at":"2026-07-31T01:30:31.802741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27767v1","created_at":"2026-07-31T01:30:31.802741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27767","created_at":"2026-07-31T01:30:31.802741+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMIYVDQGXN65","created_at":"2026-07-31T01:30:31.802741+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMIYVDQGXN657S2T","created_at":"2026-07-31T01:30:31.802741+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMIYVDQG","created_at":"2026-07-31T01:30:31.802741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ","json":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ.json","graph_json":"https://pith.science/api/pith-number/WMIYVDQGXN657S2T6754MPCHHZ/graph.json","events_json":"https://pith.science/api/pith-number/WMIYVDQGXN657S2T6754MPCHHZ/events.json","paper":"https://pith.science/paper/WMIYVDQG"},"agent_actions":{"view_html":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ","download_json":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ.json","view_paper":"https://pith.science/paper/WMIYVDQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27767&json=true","fetch_graph":"https://pith.science/api/pith-number/WMIYVDQGXN657S2T6754MPCHHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WMIYVDQGXN657S2T6754MPCHHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ/action/storage_attestation","attest_author":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ/action/author_attestation","sign_citation":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ/action/citation_signature","submit_replication":"https://pith.science/pith/WMIYVDQGXN657S2T6754MPCHHZ/action/replication_record"}},"created_at":"2026-07-31T01:30:31.802741+00:00","updated_at":"2026-07-31T01:30:31.802741+00:00"}