{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KZPVITFKGLIULSSP4T46XSM6WS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d6dc7942558f67369e1d00e8f14e57f14270fc3fff6b7780143eb5e23359686b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-05T06:23:20Z","title_canon_sha256":"d74a1d201abbf5de94cf02c297d491c4464bc71ece9b99f4de06303adb1e1d4a"},"schema_version":"1.0","source":{"id":"2605.03403","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03403","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03403v2","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03403","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"KZPVITFKGLIU","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"KZPVITFKGLIULSSP","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"KZPVITFK","created_at":"2026-06-02T02:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:e17ecaf0866e384b17ae6fd4d2e2f523d85b44f38f94f0e45dab1503d42502b1","target":"graph","created_at":"2026-06-02T02:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"GRPO-TTA consistently outperforms existing test-time adaptation methods, with notably larger performance gains under natural distribution shifts."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."}],"snapshot_sha256":"52e19a8a2cc17da8513b9278e83bc3f3746a5da9120ae4d53f3ca5ff3998271b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.03403/integrity.json","findings":[],"snapshot_sha256":"3df2f4034b60b226084ee939d6eab9b0511ca69b3d54c9a89cb1470e9b8ddb1d","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hongyuan Zhang, Yuan Yuan, Yujun Li","cross_cats":["cs.LG"],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-05T06:23:20Z","title":"GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.03403","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T17:59:29.852352Z","id":"3545f4e1-c389-4705-a454-9e0b86db7e03","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"","strongest_claim":"GRPO-TTA consistently outperforms existing test-time adaptation methods, with notably larger performance gains under natural distribution shifts.","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."}},"verdict_id":"3545f4e1-c389-4705-a454-9e0b86db7e03"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9f83818527b1cd0ec587dc7d5af9cd404133bc015641005d978ddcc96fcab42d","target":"record","created_at":"2026-06-02T02:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d6dc7942558f67369e1d00e8f14e57f14270fc3fff6b7780143eb5e23359686b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-05T06:23:20Z","title_canon_sha256":"d74a1d201abbf5de94cf02c297d491c4464bc71ece9b99f4de06303adb1e1d4a"},"schema_version":"1.0","source":{"id":"2605.03403","kind":"arxiv","version":2}},"canonical_sha256":"565f544caa32d145ca4fe4f9ebc99eb48ecd132ea4c99eab95eded35b501572a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"565f544caa32d145ca4fe4f9ebc99eb48ecd132ea4c99eab95eded35b501572a","first_computed_at":"2026-06-02T02:04:53.599649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:53.599649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xnkvhYJzGBTJQbnVM1gNt+0nWM5RBBfpYMQyZrHQ0NV98SQ6TnehwmY+eZnVEfzE0lErqvfCa1wPTM6msJMJBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:53.600052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.03403","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f83818527b1cd0ec587dc7d5af9cd404133bc015641005d978ddcc96fcab42d","sha256:e17ecaf0866e384b17ae6fd4d2e2f523d85b44f38f94f0e45dab1503d42502b1"],"state_sha256":"c1443142b4629ae4c80b0d6d2a288eb1f68849255f2422f681d8e9094b8f7ac1"}