{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7UIAYFB2P2AHI336WVRODC6WV2","short_pith_number":"pith:7UIAYFB2","canonical_record":{"source":{"id":"2507.05668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"0d6728cbc07d5bef24a7d2c0a7108d18d3996dce564b287eaf26ede3128f46c0","abstract_canon_sha256":"ae325a08ab2897956c61563877a0bb997289b026fd87af0e5b8d0b4e560a9f47"},"schema_version":"1.0"},"canonical_sha256":"fd100c143a7e80746f7eb562e18bd6ae905e18e2d6a8a6d401f1976b17aca55d","source":{"kind":"arxiv","id":"2507.05668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05668","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05668v1","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05668","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_12","alias_value":"7UIAYFB2P2AH","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_16","alias_value":"7UIAYFB2P2AHI336","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_8","alias_value":"7UIAYFB2","created_at":"2026-07-05T11:33:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7UIAYFB2P2AHI336WVRODC6WV2","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"0d6728cbc07d5bef24a7d2c0a7108d18d3996dce564b287eaf26ede3128f46c0","abstract_canon_sha256":"ae325a08ab2897956c61563877a0bb997289b026fd87af0e5b8d0b4e560a9f47"},"schema_version":"1.0"},"canonical_sha256":"fd100c143a7e80746f7eb562e18bd6ae905e18e2d6a8a6d401f1976b17aca55d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:34.297468Z","signature_b64":"5dWn2SGAauwPopt+8vVUOvNvQJSywo7+i7rHm9wE3VI5AY/A1tY9Gnn8SBAq/mUSDtikkIr0WZjvYW8i6CxGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd100c143a7e80746f7eb562e18bd6ae905e18e2d6a8a6d401f1976b17aca55d","last_reissued_at":"2026-07-05T11:33:34.297041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:34.297041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05668","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":"2026-07-05T11:33:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ZxIg6RAgWb9E7v1PSyDtiklnxKNsnch39BNSG0lQEtnhw4bZtu4bWWKhP4ePqtx7waWrlGCDmCUJjz7YoEVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:50:13.438560Z"},"content_sha256":"487a54dc512e8bd9105862b1831a8a3824a93e10115c355513a0741dbd8903f2","schema_version":"1.0","event_id":"sha256:487a54dc512e8bd9105862b1831a8a3824a93e10115c355513a0741dbd8903f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7UIAYFB2P2AHI336WVRODC6WV2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Rank Adaptation for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Bo Jiang, Jiahui Wang, Qin Xu","submitted_at":"2025-07-08T04:52:21Z","abstract_excerpt":"Pre-trained large vision-language models (VLMs) like CLIP demonstrate impressive generalization ability. Existing prompt-based and adapter-based works have made significant progress in fine-tuning VLMs but still face the challenges of maintaining strong generalization abilities, particularly towards unseen new classes. This limitation partly arises from these methods treating all tokens of the image and text encoder equally, which can lead to overfitting on less informative features (e.g., background noise, template words) and degrade the general representations that are crucial for novel conc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05668","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/2507.05668/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":"2026-07-05T11:33:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DJuq4Rix8smucuTRU7YnXYXx4se0ppVh6W95wpW/8qFwoK/5kShCXfbN2L1JoZAja9Cap3OUx/OiyLSzPI6cCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:50:13.439048Z"},"content_sha256":"097dddeb708da695cb2f98184118a9cf2f6598f207c38e39ef7d38f50708f280","schema_version":"1.0","event_id":"sha256:097dddeb708da695cb2f98184118a9cf2f6598f207c38e39ef7d38f50708f280"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UIAYFB2P2AHI336WVRODC6WV2/bundle.json","state_url":"https://pith.science/pith/7UIAYFB2P2AHI336WVRODC6WV2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UIAYFB2P2AHI336WVRODC6WV2/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":"2026-08-13T12:50:13Z","links":{"resolver":"https://pith.science/pith/7UIAYFB2P2AHI336WVRODC6WV2","bundle":"https://pith.science/pith/7UIAYFB2P2AHI336WVRODC6WV2/bundle.json","state":"https://pith.science/pith/7UIAYFB2P2AHI336WVRODC6WV2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UIAYFB2P2AHI336WVRODC6WV2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7UIAYFB2P2AHI336WVRODC6WV2","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":"ae325a08ab2897956c61563877a0bb997289b026fd87af0e5b8d0b4e560a9f47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:52:21Z","title_canon_sha256":"0d6728cbc07d5bef24a7d2c0a7108d18d3996dce564b287eaf26ede3128f46c0"},"schema_version":"1.0","source":{"id":"2507.05668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05668","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05668v1","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05668","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_12","alias_value":"7UIAYFB2P2AH","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_16","alias_value":"7UIAYFB2P2AHI336","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_8","alias_value":"7UIAYFB2","created_at":"2026-07-05T11:33:34Z"}],"graph_snapshots":[{"event_id":"sha256:097dddeb708da695cb2f98184118a9cf2f6598f207c38e39ef7d38f50708f280","target":"graph","created_at":"2026-07-05T11:33:34Z","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/2507.05668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained large vision-language models (VLMs) like CLIP demonstrate impressive generalization ability. Existing prompt-based and adapter-based works have made significant progress in fine-tuning VLMs but still face the challenges of maintaining strong generalization abilities, particularly towards unseen new classes. This limitation partly arises from these methods treating all tokens of the image and text encoder equally, which can lead to overfitting on less informative features (e.g., background noise, template words) and degrade the general representations that are crucial for novel conc","authors_text":"Bin Luo, Bo Jiang, Jiahui Wang, Qin Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:52:21Z","title":"Dynamic Rank Adaptation for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05668","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":"sha256:487a54dc512e8bd9105862b1831a8a3824a93e10115c355513a0741dbd8903f2","target":"record","created_at":"2026-07-05T11:33:34Z","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":"ae325a08ab2897956c61563877a0bb997289b026fd87af0e5b8d0b4e560a9f47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:52:21Z","title_canon_sha256":"0d6728cbc07d5bef24a7d2c0a7108d18d3996dce564b287eaf26ede3128f46c0"},"schema_version":"1.0","source":{"id":"2507.05668","kind":"arxiv","version":1}},"canonical_sha256":"fd100c143a7e80746f7eb562e18bd6ae905e18e2d6a8a6d401f1976b17aca55d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd100c143a7e80746f7eb562e18bd6ae905e18e2d6a8a6d401f1976b17aca55d","first_computed_at":"2026-07-05T11:33:34.297041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:34.297041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5dWn2SGAauwPopt+8vVUOvNvQJSywo7+i7rHm9wE3VI5AY/A1tY9Gnn8SBAq/mUSDtikkIr0WZjvYW8i6CxGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:34.297468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:487a54dc512e8bd9105862b1831a8a3824a93e10115c355513a0741dbd8903f2","sha256:097dddeb708da695cb2f98184118a9cf2f6598f207c38e39ef7d38f50708f280"],"state_sha256":"6fc58a258866ffeacb06f30f56a92adcf8627a101f4a2c29aa397e6cfbd34d29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k83tWshu0tpRprp5rFc8fZ3LqiNt+2D6YwmEaKSKeCUgQcmVgDroDNfZdVziREn3gCIIEN2E+sM99gQj2+TMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T12:50:13.444124Z","bundle_sha256":"d430f293b2dcd2d5ce873840467ab029fd8a157ef81e65c8e0cfe9ad3c0abcb9"}}