{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WSBQ7RUZQMY4EGZIHR2Y5MQJ5L","short_pith_number":"pith:WSBQ7RUZ","schema_version":"1.0","canonical_sha256":"b4830fc6998331c21b283c758eb209eae626e47737413d99097c43760c310421","source":{"kind":"arxiv","id":"2505.16903","version":2},"attestation_state":"computed","paper":{"title":"Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peyman Baghershahi, Sourav Medya","submitted_at":"2025-05-22T17:03:20Z","abstract_excerpt":"Prompt tuning has become a key mechanism for adapting pre-trained Graph Neural Networks (GNNs) to new downstream tasks. However, existing approaches are predominantly supervised, relying on labeled data to optimize the prompting parameters and typically fine-tuning a task-specific prediction head -- practices that undermine the promise of parameter-efficient adaptation. We propose Unsupervised Graph Prompting Problem (UGPP), a challenging new setting where the pre-trained GNN is kept entirely frozen, labels on the target domain are unavailable, the source data is inaccessible, and the target d"},"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":"2505.16903","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:03:20Z","cross_cats_sorted":[],"title_canon_sha256":"957733e3c5fa0d2658fc9cb3c8f4d8fd37f4006b12aca43610824a77668836e8","abstract_canon_sha256":"0ce29236d9ba5cdd09572f08c4d20245a7a09ceffaf8ed69a475fddc171b8e0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:51.731422Z","signature_b64":"k03ULHKvYVqj2lsUOJTtZpaYfPYwOoWMgZM90M93QjA6xvvE0+yzoWJ011n2Agro6IeBZwJlMEB/vinQH+pcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4830fc6998331c21b283c758eb209eae626e47737413d99097c43760c310421","last_reissued_at":"2026-06-30T02:16:51.730184Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:51.730184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peyman Baghershahi, Sourav Medya","submitted_at":"2025-05-22T17:03:20Z","abstract_excerpt":"Prompt tuning has become a key mechanism for adapting pre-trained Graph Neural Networks (GNNs) to new downstream tasks. However, existing approaches are predominantly supervised, relying on labeled data to optimize the prompting parameters and typically fine-tuning a task-specific prediction head -- practices that undermine the promise of parameter-efficient adaptation. We propose Unsupervised Graph Prompting Problem (UGPP), a challenging new setting where the pre-trained GNN is kept entirely frozen, labels on the target domain are unavailable, the source data is inaccessible, and the target d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16903","kind":"arxiv","version":2},"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/2505.16903/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":"2505.16903","created_at":"2026-06-30T02:16:51.730307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16903v2","created_at":"2026-06-30T02:16:51.730307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16903","created_at":"2026-06-30T02:16:51.730307+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSBQ7RUZQMY4","created_at":"2026-06-30T02:16:51.730307+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSBQ7RUZQMY4EGZI","created_at":"2026-06-30T02:16:51.730307+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSBQ7RUZ","created_at":"2026-06-30T02:16:51.730307+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/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L","json":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L.json","graph_json":"https://pith.science/api/pith-number/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/graph.json","events_json":"https://pith.science/api/pith-number/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/events.json","paper":"https://pith.science/paper/WSBQ7RUZ"},"agent_actions":{"view_html":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L","download_json":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L.json","view_paper":"https://pith.science/paper/WSBQ7RUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16903&json=true","fetch_graph":"https://pith.science/api/pith-number/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/graph.json","fetch_events":"https://pith.science/api/pith-number/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/action/storage_attestation","attest_author":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/action/author_attestation","sign_citation":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/action/citation_signature","submit_replication":"https://pith.science/pith/WSBQ7RUZQMY4EGZIHR2Y5MQJ5L/action/replication_record"}},"created_at":"2026-06-30T02:16:51.730307+00:00","updated_at":"2026-06-30T02:16:51.730307+00:00"}