{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RPXPLSEUUV72XYJRT5VWD3GEDE","short_pith_number":"pith:RPXPLSEU","canonical_record":{"source":{"id":"2505.13233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T15:15:37Z","cross_cats_sorted":[],"title_canon_sha256":"3f0c37fcaee52aedc2632142db097b5cd4b6596be6aa285b5dddc73027cb4c93","abstract_canon_sha256":"e4a269adbda2db8557fa3d7ada1aaccbb12cc1aad9ef8e457b607bbabf5ae0dd"},"schema_version":"1.0"},"canonical_sha256":"8beef5c894a57fabe1319f6b61ecc41921eae87d9bb78ed84409bc2e177e8dda","source":{"kind":"arxiv","id":"2505.13233","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13233","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13233v1","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13233","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"RPXPLSEUUV72","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"RPXPLSEUUV72XYJR","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"RPXPLSEU","created_at":"2026-07-05T11:05:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RPXPLSEUUV72XYJRT5VWD3GEDE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T15:15:37Z","cross_cats_sorted":[],"title_canon_sha256":"3f0c37fcaee52aedc2632142db097b5cd4b6596be6aa285b5dddc73027cb4c93","abstract_canon_sha256":"e4a269adbda2db8557fa3d7ada1aaccbb12cc1aad9ef8e457b607bbabf5ae0dd"},"schema_version":"1.0"},"canonical_sha256":"8beef5c894a57fabe1319f6b61ecc41921eae87d9bb78ed84409bc2e177e8dda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:27.136225Z","signature_b64":"jAGNnoFY8eheS9ilC3ik4GOmqvTqaoLHSZL6PAqM1rtwU9jMflwzzGaeRuvx8djZDRG/FTOkhjy4Fk7Dn63aDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8beef5c894a57fabe1319f6b61ecc41921eae87d9bb78ed84409bc2e177e8dda","last_reissued_at":"2026-07-05T11:05:27.135719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:27.135719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13233","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":"2026-07-05T11:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPkZYMCFxnojRpxMWYbhd5u0TU+H5JwSQVfgmZBUsc+x1odd0lKMDl6JYQ+5FTALvEG1A2ZKyekxNA7GehdmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:22:28.066701Z"},"content_sha256":"f6af19b0a22e7865dc32ce969e7b2529293ffca67313d18b7a5ed55f097450d8","schema_version":"1.0","event_id":"sha256:f6af19b0a22e7865dc32ce969e7b2529293ffca67313d18b7a5ed55f097450d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RPXPLSEUUV72XYJRT5VWD3GEDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binhui Xie, Jian Liang, Jingxuan Kang, Lincan Cai, Shuang Li, Wenxuan Ma, Zhida Qin","submitted_at":"2025-05-19T15:15:37Z","abstract_excerpt":"Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks. Prior research highlights the crucial role of visual augmentation techniques, like random cropping, in alignment with fine-grained class descriptions generated by large language models (LLMs), significantly enhancing zero-shot performance by incorporating multi-view information. However, the inherent randomness of these augmentations can inevitably introduce background artifacts and cause models to overly focus on local details, compromising global semantic understanding. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13233","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/2505.13233/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":"2026-07-05T11:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LU+bsmMLijT7Qi7leOMWGlxKlRm4hJxDI66qD/ONDGs0y/o5G46hvXa5uXqCR1ZuQim4j/TX4CNaB8IETG3lAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:22:28.067067Z"},"content_sha256":"f9057e54e3cb84f268d2b6a5c1a9334e2c7d3d183adb4c3591dc27862345234c","schema_version":"1.0","event_id":"sha256:f9057e54e3cb84f268d2b6a5c1a9334e2c7d3d183adb4c3591dc27862345234c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RPXPLSEUUV72XYJRT5VWD3GEDE/bundle.json","state_url":"https://pith.science/pith/RPXPLSEUUV72XYJRT5VWD3GEDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RPXPLSEUUV72XYJRT5VWD3GEDE/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":"2026-07-06T17:22:28Z","links":{"resolver":"https://pith.science/pith/RPXPLSEUUV72XYJRT5VWD3GEDE","bundle":"https://pith.science/pith/RPXPLSEUUV72XYJRT5VWD3GEDE/bundle.json","state":"https://pith.science/pith/RPXPLSEUUV72XYJRT5VWD3GEDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RPXPLSEUUV72XYJRT5VWD3GEDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RPXPLSEUUV72XYJRT5VWD3GEDE","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":"e4a269adbda2db8557fa3d7ada1aaccbb12cc1aad9ef8e457b607bbabf5ae0dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T15:15:37Z","title_canon_sha256":"3f0c37fcaee52aedc2632142db097b5cd4b6596be6aa285b5dddc73027cb4c93"},"schema_version":"1.0","source":{"id":"2505.13233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13233","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13233v1","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13233","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"RPXPLSEUUV72","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"RPXPLSEUUV72XYJR","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"RPXPLSEU","created_at":"2026-07-05T11:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:f9057e54e3cb84f268d2b6a5c1a9334e2c7d3d183adb4c3591dc27862345234c","target":"graph","created_at":"2026-07-05T11:05:27Z","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/2505.13233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks. Prior research highlights the crucial role of visual augmentation techniques, like random cropping, in alignment with fine-grained class descriptions generated by large language models (LLMs), significantly enhancing zero-shot performance by incorporating multi-view information. However, the inherent randomness of these augmentations can inevitably introduce background artifacts and cause models to overly focus on local details, compromising global semantic understanding. To","authors_text":"Binhui Xie, Jian Liang, Jingxuan Kang, Lincan Cai, Shuang Li, Wenxuan Ma, Zhida Qin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T15:15:37Z","title":"From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13233","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:f6af19b0a22e7865dc32ce969e7b2529293ffca67313d18b7a5ed55f097450d8","target":"record","created_at":"2026-07-05T11:05:27Z","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":"e4a269adbda2db8557fa3d7ada1aaccbb12cc1aad9ef8e457b607bbabf5ae0dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T15:15:37Z","title_canon_sha256":"3f0c37fcaee52aedc2632142db097b5cd4b6596be6aa285b5dddc73027cb4c93"},"schema_version":"1.0","source":{"id":"2505.13233","kind":"arxiv","version":1}},"canonical_sha256":"8beef5c894a57fabe1319f6b61ecc41921eae87d9bb78ed84409bc2e177e8dda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8beef5c894a57fabe1319f6b61ecc41921eae87d9bb78ed84409bc2e177e8dda","first_computed_at":"2026-07-05T11:05:27.135719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:27.135719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jAGNnoFY8eheS9ilC3ik4GOmqvTqaoLHSZL6PAqM1rtwU9jMflwzzGaeRuvx8djZDRG/FTOkhjy4Fk7Dn63aDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:27.136225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6af19b0a22e7865dc32ce969e7b2529293ffca67313d18b7a5ed55f097450d8","sha256:f9057e54e3cb84f268d2b6a5c1a9334e2c7d3d183adb4c3591dc27862345234c"],"state_sha256":"776ea270ef2d3010dcac4ad66f72d08356f86dfc5dc9ad563f40b5e6804bd9d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4oB+mE3GUQ8smmwPc9hg9scRxET/QyhqSX+K7qu5ILVhK6P36ajp5Hu+z/ryOysm7zjkBDUrgycs1AjhosVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:22:28.068949Z","bundle_sha256":"e85e545c8ceba216aa86ab35d51a2dac0e0587facb875b9c1c49a47ed7f4d150"}}