{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N3FM7D3NI5S4XDLFOWLG3YIU43","short_pith_number":"pith:N3FM7D3N","canonical_record":{"source":{"id":"2502.02069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T07:40:26Z","cross_cats_sorted":[],"title_canon_sha256":"9697daecbe65779d120daebdfe71fb6c6946c32fb84df88dabd67cb33d619308","abstract_canon_sha256":"118338decdffa06f8793d4b8d6f31cde5d9bf4bca2e7953679be11b4c60287ba"},"schema_version":"1.0"},"canonical_sha256":"6ecacf8f6d4765cb8d6575966de114e6f292ec3fa63660acae1ed39d405af8ad","source":{"kind":"arxiv","id":"2502.02069","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02069","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02069v1","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02069","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"N3FM7D3NI5S4","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"N3FM7D3NI5S4XDLF","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"N3FM7D3N","created_at":"2026-07-05T10:09:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N3FM7D3NI5S4XDLFOWLG3YIU43","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T07:40:26Z","cross_cats_sorted":[],"title_canon_sha256":"9697daecbe65779d120daebdfe71fb6c6946c32fb84df88dabd67cb33d619308","abstract_canon_sha256":"118338decdffa06f8793d4b8d6f31cde5d9bf4bca2e7953679be11b4c60287ba"},"schema_version":"1.0"},"canonical_sha256":"6ecacf8f6d4765cb8d6575966de114e6f292ec3fa63660acae1ed39d405af8ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:23.290351Z","signature_b64":"HbbgIHHq00vNNOzQMiQ6JDHaOkm4T8iIhHRL5sxyJLFHbcgk6p7tXo/Njk6A0RG/KY+DurxE4CXsPSkjvbHTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ecacf8f6d4765cb8d6575966de114e6f292ec3fa63660acae1ed39d405af8ad","last_reissued_at":"2026-07-05T10:09:23.289871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:23.289871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02069","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lj5DR7h7hgbcbnrUc5cSIpEN1aQy24HQpnHogjkpOEdxkART3P/af+ofJotabmuc+P+XXI8D4naSMG/b0zrpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:11:02.484566Z"},"content_sha256":"c57a1b79c860d36d5206e5cf3f2992f3adbeaaae37954bcbdc4f79af0e915779","schema_version":"1.0","event_id":"sha256:c57a1b79c860d36d5206e5cf3f2992f3adbeaaae37954bcbdc4f79af0e915779"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N3FM7D3NI5S4XDLFOWLG3YIU43","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiarui Xu, Xiaolong Wang, Xueyan Zou, Yuto Kojima","submitted_at":"2025-02-04T07:40:26Z","abstract_excerpt":"The rapid advancements in vision-language models (VLMs), such as CLIP, have intensified the need to address distribution shifts between training and testing datasets. Although prior Test-Time Training (TTT) techniques for VLMs have demonstrated robust performance, they predominantly rely on tuning text prompts, a process that demands substantial computational resources and is heavily dependent on entropy-based loss. In this paper, we propose LoRA-TTT, a novel TTT method that leverages Low-Rank Adaptation (LoRA), applied exclusively to the image encoder of VLMs. By introducing LoRA and updating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02069","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/2502.02069/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M1Q8CbVTSRaYnI2P8rSQJolatPs1AH2UawjiKxlV5AoCQqyZIvU6yfDMS5bfAplD9vHTQG35UCHCVgoS3mmvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:11:02.485501Z"},"content_sha256":"f8f07426b4e56827a653ed08a476292dcf421425be6816d1b2871eb69990d1f0","schema_version":"1.0","event_id":"sha256:f8f07426b4e56827a653ed08a476292dcf421425be6816d1b2871eb69990d1f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3FM7D3NI5S4XDLFOWLG3YIU43/bundle.json","state_url":"https://pith.science/pith/N3FM7D3NI5S4XDLFOWLG3YIU43/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3FM7D3NI5S4XDLFOWLG3YIU43/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T03:11:02Z","links":{"resolver":"https://pith.science/pith/N3FM7D3NI5S4XDLFOWLG3YIU43","bundle":"https://pith.science/pith/N3FM7D3NI5S4XDLFOWLG3YIU43/bundle.json","state":"https://pith.science/pith/N3FM7D3NI5S4XDLFOWLG3YIU43/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3FM7D3NI5S4XDLFOWLG3YIU43/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N3FM7D3NI5S4XDLFOWLG3YIU43","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":"118338decdffa06f8793d4b8d6f31cde5d9bf4bca2e7953679be11b4c60287ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T07:40:26Z","title_canon_sha256":"9697daecbe65779d120daebdfe71fb6c6946c32fb84df88dabd67cb33d619308"},"schema_version":"1.0","source":{"id":"2502.02069","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02069","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02069v1","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02069","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"N3FM7D3NI5S4","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"N3FM7D3NI5S4XDLF","created_at":"2026-07-05T10:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"N3FM7D3N","created_at":"2026-07-05T10:09:23Z"}],"graph_snapshots":[{"event_id":"sha256:f8f07426b4e56827a653ed08a476292dcf421425be6816d1b2871eb69990d1f0","target":"graph","created_at":"2026-07-05T10:09:23Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.02069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancements in vision-language models (VLMs), such as CLIP, have intensified the need to address distribution shifts between training and testing datasets. Although prior Test-Time Training (TTT) techniques for VLMs have demonstrated robust performance, they predominantly rely on tuning text prompts, a process that demands substantial computational resources and is heavily dependent on entropy-based loss. In this paper, we propose LoRA-TTT, a novel TTT method that leverages Low-Rank Adaptation (LoRA), applied exclusively to the image encoder of VLMs. By introducing LoRA and updating","authors_text":"Jiarui Xu, Xiaolong Wang, Xueyan Zou, Yuto Kojima","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T07:40:26Z","title":"LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02069","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c57a1b79c860d36d5206e5cf3f2992f3adbeaaae37954bcbdc4f79af0e915779","target":"record","created_at":"2026-07-05T10:09:23Z","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":"118338decdffa06f8793d4b8d6f31cde5d9bf4bca2e7953679be11b4c60287ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T07:40:26Z","title_canon_sha256":"9697daecbe65779d120daebdfe71fb6c6946c32fb84df88dabd67cb33d619308"},"schema_version":"1.0","source":{"id":"2502.02069","kind":"arxiv","version":1}},"canonical_sha256":"6ecacf8f6d4765cb8d6575966de114e6f292ec3fa63660acae1ed39d405af8ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ecacf8f6d4765cb8d6575966de114e6f292ec3fa63660acae1ed39d405af8ad","first_computed_at":"2026-07-05T10:09:23.289871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:23.289871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HbbgIHHq00vNNOzQMiQ6JDHaOkm4T8iIhHRL5sxyJLFHbcgk6p7tXo/Njk6A0RG/KY+DurxE4CXsPSkjvbHTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:23.290351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02069","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c57a1b79c860d36d5206e5cf3f2992f3adbeaaae37954bcbdc4f79af0e915779","sha256:f8f07426b4e56827a653ed08a476292dcf421425be6816d1b2871eb69990d1f0"],"state_sha256":"97bb0c04a9fb9b9825202a57d572f2097edb05621ee1813c5580906f9ae257a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHAOuFfQGqK/7UG1CPsOf/xLzorBjO2rbosd+Q0pwXib77+qYPi9vf0CBnfuemWe6DuC0lklQQ2pCXm1+zGcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:11:02.492887Z","bundle_sha256":"572f336b0479c9279a9272463f2a4fbaa67c4c652e96e139235929c1b3a41441"}}