{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V4CMUYV3NOK2DLPEZDNTR6QAMP","short_pith_number":"pith:V4CMUYV3","schema_version":"1.0","canonical_sha256":"af04ca62bb6b95a1ade4c8db38fa0063f0c9278cc9e02fc296021b23cfc6c2bd","source":{"kind":"arxiv","id":"2605.20248","version":1},"attestation_state":"computed","paper":{"title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brown Zaz, Ferran Hernandez Caralt, Mar Gonz\\`alez I Catal\\`a, Moshe Eliasof, Pietro Li\\`o","submitted_at":"2026-05-18T06:47:41Z","abstract_excerpt":"In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on architectural innovation. In this paper, we revisit an orthogonal axis: the training objective. We start from a simple observation: transductive models produce predictions for every node during training, including nodes without labels. These unlabeled-node predictions may contain useful training signal, but standard supervised objectives discard them because no ground-truth labels are available. Inspired by the decomp"},"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":"2605.20248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T06:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"3099616615533bf649bc13e5b5b6341d798a470beefe65ce4c1363f21e0eb9ae","abstract_canon_sha256":"edda2c528738fedf7a2d610972f16470b6335c1cc5cce977a3e1a4b2724a4403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T00:04:22.660294Z","signature_b64":"buzy0XI+nYLj3XY+lXJgRbo2qZju4Ar9nItF/g6YGLRUo35WCSl+F/JxA7UQVrdSuGAIgiTIT5kNsCwsUuX3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af04ca62bb6b95a1ade4c8db38fa0063f0c9278cc9e02fc296021b23cfc6c2bd","last_reissued_at":"2026-05-21T00:04:22.659877Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T00:04:22.659877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brown Zaz, Ferran Hernandez Caralt, Mar Gonz\\`alez I Catal\\`a, Moshe Eliasof, Pietro Li\\`o","submitted_at":"2026-05-18T06:47:41Z","abstract_excerpt":"In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on architectural innovation. In this paper, we revisit an orthogonal axis: the training objective. We start from a simple observation: transductive models produce predictions for every node during training, including nodes without labels. These unlabeled-node predictions may contain useful training signal, but standard supervised objectives discard them because no ground-truth labels are available. Inspired by the decomp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20248","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/2605.20248/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":"2605.20248","created_at":"2026-05-21T00:04:22.659934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20248v1","created_at":"2026-05-21T00:04:22.659934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20248","created_at":"2026-05-21T00:04:22.659934+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4CMUYV3NOK2","created_at":"2026-05-21T00:04:22.659934+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4CMUYV3NOK2DLPE","created_at":"2026-05-21T00:04:22.659934+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4CMUYV3","created_at":"2026-05-21T00:04:22.659934+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/V4CMUYV3NOK2DLPEZDNTR6QAMP","json":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP.json","graph_json":"https://pith.science/api/pith-number/V4CMUYV3NOK2DLPEZDNTR6QAMP/graph.json","events_json":"https://pith.science/api/pith-number/V4CMUYV3NOK2DLPEZDNTR6QAMP/events.json","paper":"https://pith.science/paper/V4CMUYV3"},"agent_actions":{"view_html":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP","download_json":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP.json","view_paper":"https://pith.science/paper/V4CMUYV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20248&json=true","fetch_graph":"https://pith.science/api/pith-number/V4CMUYV3NOK2DLPEZDNTR6QAMP/graph.json","fetch_events":"https://pith.science/api/pith-number/V4CMUYV3NOK2DLPEZDNTR6QAMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP/action/storage_attestation","attest_author":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP/action/author_attestation","sign_citation":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP/action/citation_signature","submit_replication":"https://pith.science/pith/V4CMUYV3NOK2DLPEZDNTR6QAMP/action/replication_record"}},"created_at":"2026-05-21T00:04:22.659934+00:00","updated_at":"2026-05-21T00:04:22.659934+00:00"}