{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KZPVITFKGLIULSSP4T46XSM6WS","short_pith_number":"pith:KZPVITFK","schema_version":"1.0","canonical_sha256":"565f544caa32d145ca4fe4f9ebc99eb48ecd132ea4c99eab95eded35b501572a","source":{"kind":"arxiv","id":"2605.03403","version":2},"attestation_state":"computed","paper":{"title":"GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GRPO-TTA applies GRPO to test-time visual tuning of vision-language models via group-wise policy optimization on unlabeled class candidates, outperforming prior TTA methods especially under natural distribution shifts.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongyuan Zhang, Yuan Yuan, Yujun Li","submitted_at":"2026-05-05T06:23:20Z","abstract_excerpt":"Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It raises a question of whether the GRPO also significantly promotes the test-time adaptation (TTA) of vision language models. In this paper, we propose Group Relative Policy Optimization for Test-Time Adaptation (GRPO-TTA), which adapts GRPO to the TTA setting by reformulating class-specific prompt prediction as a group-wise policy optimization problem. Specifically, we construct output groups by sampling top-K class candidates from CLIP similarity"},"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":"2605.03403","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-05T06:23:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d74a1d201abbf5de94cf02c297d491c4464bc71ece9b99f4de06303adb1e1d4a","abstract_canon_sha256":"d6dc7942558f67369e1d00e8f14e57f14270fc3fff6b7780143eb5e23359686b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:53.600052Z","signature_b64":"xnkvhYJzGBTJQbnVM1gNt+0nWM5RBBfpYMQyZrHQ0NV98SQ6TnehwmY+eZnVEfzE0lErqvfCa1wPTM6msJMJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"565f544caa32d145ca4fe4f9ebc99eb48ecd132ea4c99eab95eded35b501572a","last_reissued_at":"2026-06-02T02:04:53.599649Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:53.599649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GRPO-TTA applies GRPO to test-time visual tuning of vision-language models via group-wise policy optimization on unlabeled class candidates, outperforming prior TTA methods especially under natural distribution shifts.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongyuan Zhang, Yuan Yuan, Yujun Li","submitted_at":"2026-05-05T06:23:20Z","abstract_excerpt":"Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It raises a question of whether the GRPO also significantly promotes the test-time adaptation (TTA) of vision language models. In this paper, we propose Group Relative Policy Optimization for Test-Time Adaptation (GRPO-TTA), which adapts GRPO to the TTA setting by reformulating class-specific prompt prediction as a group-wise policy optimization problem. Specifically, we construct output groups by sampling top-K class candidates from CLIP similarity"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"GRPO-TTA consistently outperforms existing test-time adaptation methods, with notably larger performance gains under natural distribution shifts.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That constructing output groups by sampling top-K class candidates from CLIP similarity distributions enables effective probability-driven optimization without ground-truth labels, and that the designed alignment and dispersion rewards guide effective visual encoder tuning at test time.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GRPO-TTA applies GRPO to test-time visual tuning of vision-language models via group-wise policy optimization on unlabeled class candidates, outperforming prior TTA methods especially under natural distribution shifts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"52e19a8a2cc17da8513b9278e83bc3f3746a5da9120ae4d53f3ca5ff3998271b"},"source":{"id":"2605.03403","kind":"arxiv","version":2},"verdict":{"id":"3545f4e1-c389-4705-a454-9e0b86db7e03","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T17:59:29.852352Z","strongest_claim":"GRPO-TTA consistently outperforms existing test-time adaptation methods, with notably larger performance gains under natural distribution shifts.","one_line_summary":"GRPO-TTA applies GRPO to test-time visual tuning of vision-language models via group-wise policy optimization on unlabeled class candidates, outperforming prior TTA methods especially under natural distribution shifts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That constructing output groups by sampling top-K class candidates from CLIP similarity distributions enables effective probability-driven optimization without ground-truth labels, and that the designed alignment and dispersion rewards guide effective visual encoder tuning at test time.","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03403/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T13:42:07.424276Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T01:01:22.216932Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:26:23.986363Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3df2f4034b60b226084ee939d6eab9b0511ca69b3d54c9a89cb1470e9b8ddb1d"},"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":"2605.03403","created_at":"2026-06-02T02:04:53.599707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.03403v2","created_at":"2026-06-02T02:04:53.599707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03403","created_at":"2026-06-02T02:04:53.599707+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZPVITFKGLIU","created_at":"2026-06-02T02:04:53.599707+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZPVITFKGLIULSSP","created_at":"2026-06-02T02:04:53.599707+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZPVITFK","created_at":"2026-06-02T02:04:53.599707+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/KZPVITFKGLIULSSP4T46XSM6WS","json":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS.json","graph_json":"https://pith.science/api/pith-number/KZPVITFKGLIULSSP4T46XSM6WS/graph.json","events_json":"https://pith.science/api/pith-number/KZPVITFKGLIULSSP4T46XSM6WS/events.json","paper":"https://pith.science/paper/KZPVITFK"},"agent_actions":{"view_html":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS","download_json":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS.json","view_paper":"https://pith.science/paper/KZPVITFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.03403&json=true","fetch_graph":"https://pith.science/api/pith-number/KZPVITFKGLIULSSP4T46XSM6WS/graph.json","fetch_events":"https://pith.science/api/pith-number/KZPVITFKGLIULSSP4T46XSM6WS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS/action/storage_attestation","attest_author":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS/action/author_attestation","sign_citation":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS/action/citation_signature","submit_replication":"https://pith.science/pith/KZPVITFKGLIULSSP4T46XSM6WS/action/replication_record"}},"created_at":"2026-06-02T02:04:53.599707+00:00","updated_at":"2026-06-02T02:04:53.599707+00:00"}