{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ODSSI67WJBRJBBV4U326BFOIJJ","short_pith_number":"pith:ODSSI67W","schema_version":"1.0","canonical_sha256":"70e5247bf648629086bca6f5e095c84a6e00efe2a838fbb660dbd4dc573ddf17","source":{"kind":"arxiv","id":"2606.30011","version":1},"attestation_state":"computed","paper":{"title":"T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Lazovik, Huy Truong, Victoria Degeler","submitted_at":"2026-06-29T09:18:11Z","abstract_excerpt":"Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, often leading to degraded performance under distribution shifts. This issue can be mitigated by conventional fine-tuning, but in many real-world cases, collecting labeled data is expensive or infeasible. A potential approach is Test-Time Training (TTT), which adapts models' weights using unlabeled test data, yet it is typically limited to shallow updates that affect only a subset of model parameters. We propose T3R, leveraging multiple Rotograd matrices to improve task affinity between the target and auxi"},"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":"2606.30011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T09:18:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad77e6d08fb25d977952e3cf62b3b14bba388934dbdffdd66de4fdbe4bd3bd2b","abstract_canon_sha256":"b2e70e1e1b43ead29009dab121948db346769be8a371303bdf11aef0fe4fef20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:45.659368Z","signature_b64":"CFc5sAD+MYz/e/JL5PAuqkQUgkC0DgN4HpEYxnBbJSfBVdH41kFKd4GtkUBQHKraKXYNnL2rExjpHEEI/PLOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70e5247bf648629086bca6f5e095c84a6e00efe2a838fbb660dbd4dc573ddf17","last_reissued_at":"2026-06-30T02:17:45.658770Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:45.658770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Lazovik, Huy Truong, Victoria Degeler","submitted_at":"2026-06-29T09:18:11Z","abstract_excerpt":"Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, often leading to degraded performance under distribution shifts. This issue can be mitigated by conventional fine-tuning, but in many real-world cases, collecting labeled data is expensive or infeasible. A potential approach is Test-Time Training (TTT), which adapts models' weights using unlabeled test data, yet it is typically limited to shallow updates that affect only a subset of model parameters. We propose T3R, leveraging multiple Rotograd matrices to improve task affinity between the target and auxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30011","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/2606.30011/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":"2606.30011","created_at":"2026-06-30T02:17:45.658844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30011v1","created_at":"2026-06-30T02:17:45.658844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30011","created_at":"2026-06-30T02:17:45.658844+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODSSI67WJBRJ","created_at":"2026-06-30T02:17:45.658844+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODSSI67WJBRJBBV4","created_at":"2026-06-30T02:17:45.658844+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODSSI67W","created_at":"2026-06-30T02:17:45.658844+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/ODSSI67WJBRJBBV4U326BFOIJJ","json":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ.json","graph_json":"https://pith.science/api/pith-number/ODSSI67WJBRJBBV4U326BFOIJJ/graph.json","events_json":"https://pith.science/api/pith-number/ODSSI67WJBRJBBV4U326BFOIJJ/events.json","paper":"https://pith.science/paper/ODSSI67W"},"agent_actions":{"view_html":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ","download_json":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ.json","view_paper":"https://pith.science/paper/ODSSI67W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30011&json=true","fetch_graph":"https://pith.science/api/pith-number/ODSSI67WJBRJBBV4U326BFOIJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ODSSI67WJBRJBBV4U326BFOIJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ/action/storage_attestation","attest_author":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ/action/author_attestation","sign_citation":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ/action/citation_signature","submit_replication":"https://pith.science/pith/ODSSI67WJBRJBBV4U326BFOIJJ/action/replication_record"}},"created_at":"2026-06-30T02:17:45.658844+00:00","updated_at":"2026-06-30T02:17:45.658844+00:00"}