{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJCXMNH4R3GCQVDRUYGZZKMH2D","short_pith_number":"pith:JJCXMNH4","schema_version":"1.0","canonical_sha256":"4a457634fc8ecc285471a60d9ca987d0fd3d00dc2310f9580a0d8bcd9160c65d","source":{"kind":"arxiv","id":"2607.13763","version":1},"attestation_state":"computed","paper":{"title":"MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonello Monti, Arsam Aryandoust, Charilaos Papaioannou, Dimitris Giannakakos, Elissaios Sarmas, Ioannis Tsantilas, Jochen Cremer, Perdo P. Vergara, Ricardo J. Bessa, Sotiris Pelekis, Vangelis Marinakis, Vasilis Michalakopoulos","submitted_at":"2026-07-15T12:22:36Z","abstract_excerpt":"Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift. We term this topology overfitting: the tendency of task-specific gradient signals to encode relational structure particular to the training topologies rather than the underlying physics, causing models to fail on unseen grids despite strong in-distribution performance. To expose and address this failure mode, we introduce MxGPS (Multiplex GPS), a multiplex graph transformer that runs K tas"},"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":"2607.13763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T12:22:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9bb930d6ee81ad8e14233d9cc21a6a84cd220421c0eca47c8dac499a1160970f","abstract_canon_sha256":"f612086e4e6691059be79b3bc56af751e7202203b18a553edfd8289f235b1fc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:23:05.236520Z","signature_b64":"ItfQut3g+I+/x8qWDSrcrxu97hwsIhDyBu16V99leJ0ViesKfZLh0QMDnUdpeZKJiZHP93SlLYq2vIXnhT/2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a457634fc8ecc285471a60d9ca987d0fd3d00dc2310f9580a0d8bcd9160c65d","last_reissued_at":"2026-07-16T01:23:05.235644Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:23:05.235644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonello Monti, Arsam Aryandoust, Charilaos Papaioannou, Dimitris Giannakakos, Elissaios Sarmas, Ioannis Tsantilas, Jochen Cremer, Perdo P. Vergara, Ricardo J. Bessa, Sotiris Pelekis, Vangelis Marinakis, Vasilis Michalakopoulos","submitted_at":"2026-07-15T12:22:36Z","abstract_excerpt":"Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift. We term this topology overfitting: the tendency of task-specific gradient signals to encode relational structure particular to the training topologies rather than the underlying physics, causing models to fail on unseen grids despite strong in-distribution performance. To expose and address this failure mode, we introduce MxGPS (Multiplex GPS), a multiplex graph transformer that runs K tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13763","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/2607.13763/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":"2607.13763","created_at":"2026-07-16T01:23:05.236078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13763v1","created_at":"2026-07-16T01:23:05.236078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13763","created_at":"2026-07-16T01:23:05.236078+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJCXMNH4R3GC","created_at":"2026-07-16T01:23:05.236078+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJCXMNH4R3GCQVDR","created_at":"2026-07-16T01:23:05.236078+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJCXMNH4","created_at":"2026-07-16T01:23:05.236078+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/JJCXMNH4R3GCQVDRUYGZZKMH2D","json":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D.json","graph_json":"https://pith.science/api/pith-number/JJCXMNH4R3GCQVDRUYGZZKMH2D/graph.json","events_json":"https://pith.science/api/pith-number/JJCXMNH4R3GCQVDRUYGZZKMH2D/events.json","paper":"https://pith.science/paper/JJCXMNH4"},"agent_actions":{"view_html":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D","download_json":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D.json","view_paper":"https://pith.science/paper/JJCXMNH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13763&json=true","fetch_graph":"https://pith.science/api/pith-number/JJCXMNH4R3GCQVDRUYGZZKMH2D/graph.json","fetch_events":"https://pith.science/api/pith-number/JJCXMNH4R3GCQVDRUYGZZKMH2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D/action/storage_attestation","attest_author":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D/action/author_attestation","sign_citation":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D/action/citation_signature","submit_replication":"https://pith.science/pith/JJCXMNH4R3GCQVDRUYGZZKMH2D/action/replication_record"}},"created_at":"2026-07-16T01:23:05.236078+00:00","updated_at":"2026-07-16T01:23:05.236078+00:00"}