{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3ZTBHQPRLHRXWIDAR7KSMGF353","short_pith_number":"pith:3ZTBHQPR","schema_version":"1.0","canonical_sha256":"de6613c1f159e37b20608fd52618bbeee4ee70dfc31c0dd4aa7e58c95636739f","source":{"kind":"arxiv","id":"2608.15084","version":1},"attestation_state":"computed","paper":{"title":"GATTA: Graph Active Learning with Test-Time Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Formanek, Andr\\'as G\\'ezsi, Zsombor B\\'anfi","submitted_at":"2026-08-15T07:01:59Z","abstract_excerpt":"Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision, yet its application to graph-structured data remains largely unexplored. We introduce GATTA (Graph Active Learning with Test-Time Augmentation), a framework for enhancing active learning by aggregating predictions across multiple augmented views to produce more reliable uncertainty estimates. To address the challenge of label-preserving graph augmentations, GATTA incorporates a consistency-based filtering mechanism that discards augmented views yielding unreliable pre"},"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":"2608.15084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-15T07:01:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"51014a43bf214c037a77be665cd9160804cb56d3f13933f10d5c684096023de9","abstract_canon_sha256":"b62b2a1bc5dea7cffe57eea8b2ad3c3d59f13a23fe371e3f6cb27cd125ab88a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T01:13:10.931496Z","signature_b64":"iagsKeC+Y1Uldvy+eZ9WNzhyU1D3FQN9sc+zRu8CyelXp2KgBJmbarBrEHdXnrTY6YD76j8f4qC1xHlH8H1PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6613c1f159e37b20608fd52618bbeee4ee70dfc31c0dd4aa7e58c95636739f","last_reissued_at":"2026-08-18T01:13:10.930023Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T01:13:10.930023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GATTA: Graph Active Learning with Test-Time Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Formanek, Andr\\'as G\\'ezsi, Zsombor B\\'anfi","submitted_at":"2026-08-15T07:01:59Z","abstract_excerpt":"Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision, yet its application to graph-structured data remains largely unexplored. We introduce GATTA (Graph Active Learning with Test-Time Augmentation), a framework for enhancing active learning by aggregating predictions across multiple augmented views to produce more reliable uncertainty estimates. To address the challenge of label-preserving graph augmentations, GATTA incorporates a consistency-based filtering mechanism that discards augmented views yielding unreliable pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.15084","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/2608.15084/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":"2608.15084","created_at":"2026-08-18T01:13:10.930673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.15084v1","created_at":"2026-08-18T01:13:10.930673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.15084","created_at":"2026-08-18T01:13:10.930673+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZTBHQPRLHRX","created_at":"2026-08-18T01:13:10.930673+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZTBHQPRLHRXWIDA","created_at":"2026-08-18T01:13:10.930673+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZTBHQPR","created_at":"2026-08-18T01:13:10.930673+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/3ZTBHQPRLHRXWIDAR7KSMGF353","json":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353.json","graph_json":"https://pith.science/api/pith-number/3ZTBHQPRLHRXWIDAR7KSMGF353/graph.json","events_json":"https://pith.science/api/pith-number/3ZTBHQPRLHRXWIDAR7KSMGF353/events.json","paper":"https://pith.science/paper/3ZTBHQPR"},"agent_actions":{"view_html":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353","download_json":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353.json","view_paper":"https://pith.science/paper/3ZTBHQPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.15084&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZTBHQPRLHRXWIDAR7KSMGF353/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZTBHQPRLHRXWIDAR7KSMGF353/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353/action/storage_attestation","attest_author":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353/action/author_attestation","sign_citation":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353/action/citation_signature","submit_replication":"https://pith.science/pith/3ZTBHQPRLHRXWIDAR7KSMGF353/action/replication_record"}},"created_at":"2026-08-18T01:13:10.930673+00:00","updated_at":"2026-08-18T01:13:10.930673+00:00"}