{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BR73RUM7XRJK56HX73QGAUIYRS","short_pith_number":"pith:BR73RUM7","canonical_record":{"source":{"id":"2406.02915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T04:08:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7ec9b3c905d6bc282077c1c92384314af1542a17519e6f6ce65c7aca8faf4d3","abstract_canon_sha256":"0276aebaf344618cc96b5455a3ab24c82eb29c9804322835bc6b96ac2a82ace8"},"schema_version":"1.0"},"canonical_sha256":"0c7fb8d19fbc52aef8f7fee06051188c89c11603a70b0518388828a54c20bcd9","source":{"kind":"arxiv","id":"2406.02915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02915","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02915v1","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02915","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"BR73RUM7XRJK","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"BR73RUM7XRJK56HX","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"BR73RUM7","created_at":"2026-07-05T08:27:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BR73RUM7XRJK56HX73QGAUIYRS","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T04:08:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7ec9b3c905d6bc282077c1c92384314af1542a17519e6f6ce65c7aca8faf4d3","abstract_canon_sha256":"0276aebaf344618cc96b5455a3ab24c82eb29c9804322835bc6b96ac2a82ace8"},"schema_version":"1.0"},"canonical_sha256":"0c7fb8d19fbc52aef8f7fee06051188c89c11603a70b0518388828a54c20bcd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:32.624786Z","signature_b64":"5nQZDMjGRRqF63KEdfEGesGsAY+yQz9EJfOBorQh3S+49vsAgNkzzQnmTUPO/ITeia+iLQuFO50CWgP5WJN2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c7fb8d19fbc52aef8f7fee06051188c89c11603a70b0518388828a54c20bcd9","last_reissued_at":"2026-07-05T08:27:32.624246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:32.624246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02915","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":"2026-07-05T08:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xf1xko064piFENa9QV3Oh4ictD3r6S21nXrfqcBkGS4RFEj55uhqZv+VGCdYnSo+vjZb7dcF4cKJTedTd/jzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:42:08.075314Z"},"content_sha256":"3ada5eaad5cde74ccc36059c58c874ffce3782259b58c972d86fce0bad46cc33","schema_version":"1.0","event_id":"sha256:3ada5eaad5cde74ccc36059c58c874ffce3782259b58c972d86fce0bad46cc33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BR73RUM7XRJK56HX73QGAUIYRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Feng Liu, Haopeng Li, James Bailey, Jinhao Li, Lei Feng, Sarah Erfani","submitted_at":"2024-06-05T04:08:41Z","abstract_excerpt":"It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot performance. However, in this paper, we empirically find that the finer descriptions tend to align more effectively with local areas of the query image rather than the whole image, and then we theoretically validate this finding. Thus, we present a method called weighted visual-text cross alignment (WCA). This method begins with a localized visual prompting tech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02915","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/2406.02915/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":"2026-07-05T08:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jGJ3wCRKzfB2V29hmia8KceSRyv4JaoYlQbzVwS0nVaEhZAq+gpBXj3PqCh8Ih9rvThOlG4Q/dt6+ZxedKIqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:42:08.076353Z"},"content_sha256":"dd7fffe3e1346a0a10ce32a9dbe11459214154d53d7b20d28a314fcccad2edb2","schema_version":"1.0","event_id":"sha256:dd7fffe3e1346a0a10ce32a9dbe11459214154d53d7b20d28a314fcccad2edb2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BR73RUM7XRJK56HX73QGAUIYRS/bundle.json","state_url":"https://pith.science/pith/BR73RUM7XRJK56HX73QGAUIYRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BR73RUM7XRJK56HX73QGAUIYRS/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":"2026-08-04T09:42:08Z","links":{"resolver":"https://pith.science/pith/BR73RUM7XRJK56HX73QGAUIYRS","bundle":"https://pith.science/pith/BR73RUM7XRJK56HX73QGAUIYRS/bundle.json","state":"https://pith.science/pith/BR73RUM7XRJK56HX73QGAUIYRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BR73RUM7XRJK56HX73QGAUIYRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BR73RUM7XRJK56HX73QGAUIYRS","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":"0276aebaf344618cc96b5455a3ab24c82eb29c9804322835bc6b96ac2a82ace8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T04:08:41Z","title_canon_sha256":"a7ec9b3c905d6bc282077c1c92384314af1542a17519e6f6ce65c7aca8faf4d3"},"schema_version":"1.0","source":{"id":"2406.02915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02915","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02915v1","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02915","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"BR73RUM7XRJK","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"BR73RUM7XRJK56HX","created_at":"2026-07-05T08:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"BR73RUM7","created_at":"2026-07-05T08:27:32Z"}],"graph_snapshots":[{"event_id":"sha256:dd7fffe3e1346a0a10ce32a9dbe11459214154d53d7b20d28a314fcccad2edb2","target":"graph","created_at":"2026-07-05T08:27:32Z","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/2406.02915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot performance. However, in this paper, we empirically find that the finer descriptions tend to align more effectively with local areas of the query image rather than the whole image, and then we theoretically validate this finding. Thus, we present a method called weighted visual-text cross alignment (WCA). This method begins with a localized visual prompting tech","authors_text":"Feng Liu, Haopeng Li, James Bailey, Jinhao Li, Lei Feng, Sarah Erfani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T04:08:41Z","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02915","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":"sha256:3ada5eaad5cde74ccc36059c58c874ffce3782259b58c972d86fce0bad46cc33","target":"record","created_at":"2026-07-05T08:27:32Z","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":"0276aebaf344618cc96b5455a3ab24c82eb29c9804322835bc6b96ac2a82ace8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T04:08:41Z","title_canon_sha256":"a7ec9b3c905d6bc282077c1c92384314af1542a17519e6f6ce65c7aca8faf4d3"},"schema_version":"1.0","source":{"id":"2406.02915","kind":"arxiv","version":1}},"canonical_sha256":"0c7fb8d19fbc52aef8f7fee06051188c89c11603a70b0518388828a54c20bcd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c7fb8d19fbc52aef8f7fee06051188c89c11603a70b0518388828a54c20bcd9","first_computed_at":"2026-07-05T08:27:32.624246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:32.624246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5nQZDMjGRRqF63KEdfEGesGsAY+yQz9EJfOBorQh3S+49vsAgNkzzQnmTUPO/ITeia+iLQuFO50CWgP5WJN2BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:32.624786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ada5eaad5cde74ccc36059c58c874ffce3782259b58c972d86fce0bad46cc33","sha256:dd7fffe3e1346a0a10ce32a9dbe11459214154d53d7b20d28a314fcccad2edb2"],"state_sha256":"318faa1082021967aea09f614509346e26c504920fdd1cae05a376a18972d8e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XH997bGQ+uuBjNsmnQ/5L8rKPwLC1xX7M0eCKOiWFThCmmyU3Doae/PjhRdaXCfVJeTW/P/M9MrqTHZznYvQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:42:08.081666Z","bundle_sha256":"397bca7984b9700c4577a6167a4aa84ecb9722bc22f2f3fa35da366e41607001"}}