{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XSBUDOTGCINEGJXR7OMH64YWWQ","short_pith_number":"pith:XSBUDOTG","canonical_record":{"source":{"id":"2508.00945","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T17:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"78c9a902dd45e666d460e8a8b9d8a17b80163ffd3aa39bd77326b3c091d10eb1","abstract_canon_sha256":"bce479d49f762c5c4e11e7e06f72fb0c4d22103a5a8bca9e918673a32cbd603e"},"schema_version":"1.0"},"canonical_sha256":"bc8341ba66121a4326f1fb987f7316b4343932df5d10c97dc0e7bbcd571a757e","source":{"kind":"arxiv","id":"2508.00945","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00945","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00945v1","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00945","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"XSBUDOTGCINE","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"pith_short_16","alias_value":"XSBUDOTGCINEGJXR","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"pith_short_8","alias_value":"XSBUDOTG","created_at":"2026-07-05T11:47:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XSBUDOTGCINEGJXR7OMH64YWWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.00945","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T17:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"78c9a902dd45e666d460e8a8b9d8a17b80163ffd3aa39bd77326b3c091d10eb1","abstract_canon_sha256":"bce479d49f762c5c4e11e7e06f72fb0c4d22103a5a8bca9e918673a32cbd603e"},"schema_version":"1.0"},"canonical_sha256":"bc8341ba66121a4326f1fb987f7316b4343932df5d10c97dc0e7bbcd571a757e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:30.272477Z","signature_b64":"SdtJdx9tVUK+R+WgPobrFT/RPuAzt9eiymLs9Hyir5jFnJM1lzsfdrWYE3AQqRpftMdlIhUvu7IuwD6RwpmbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc8341ba66121a4326f1fb987f7316b4343932df5d10c97dc0e7bbcd571a757e","last_reissued_at":"2026-07-05T11:47:30.272052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:30.272052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.00945","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":"2026-07-05T11:47:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uVW93GrmCZk388js1fvYFP4/9fwE9Y8eiIoXu0IRO0k/beFVS0/uEXOhOYxaTaLmZfQ6mmkCaFx7Ju0yz5BjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:23:20.239066Z"},"content_sha256":"67cefb5d82e924ad6aa71697fb99d3962fc3dbfc20cf9b93012b20c6574aceeb","schema_version":"1.0","event_id":"sha256:67cefb5d82e924ad6aa71697fb99d3962fc3dbfc20cf9b93012b20c6574aceeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XSBUDOTGCINEGJXR7OMH64YWWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Jiang, Chenzhong Li, Hongfeng Ai, Jiahua Dong, Maowei Jiang, Mengting Xiao, Quangao Liu, Ruiqi Li, Ruiyuan Kang, Yifan Wang","submitted_at":"2025-07-31T17:14:55Z","abstract_excerpt":"Vision Language Models (VLMs) face challenges in effectively coordinating diverse attention mechanisms for cross-modal embedding learning, leading to mismatched attention and suboptimal performance. We propose Consistent Cross-layer Regional Alignment (CCRA), which introduces Layer-Patch-wise Cross Attention (LPWCA) to capture fine-grained regional-semantic correlations by jointly weighting patch and layer-wise embedding, and Progressive Attention Integration (PAI) that systematically coordinates LPWCA, layer-wise, and patch-wise attention mechanisms in sequence. This progressive design ensure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00945","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/2508.00945/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":"2026-07-05T11:47:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEj+NtZVoy+UejLJUWmRFZG5HGaGqLNeHf8cxta4iEdjUbHKaqr6cYAgAUsYfitaycjFsJ/YZhABDnAY5O9zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:23:20.239582Z"},"content_sha256":"69bd343c9aabb8b4542162ddb86deb798108df1dba92c6bbb99ff1eb607b957d","schema_version":"1.0","event_id":"sha256:69bd343c9aabb8b4542162ddb86deb798108df1dba92c6bbb99ff1eb607b957d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSBUDOTGCINEGJXR7OMH64YWWQ/bundle.json","state_url":"https://pith.science/pith/XSBUDOTGCINEGJXR7OMH64YWWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSBUDOTGCINEGJXR7OMH64YWWQ/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":"2026-07-07T03:23:20Z","links":{"resolver":"https://pith.science/pith/XSBUDOTGCINEGJXR7OMH64YWWQ","bundle":"https://pith.science/pith/XSBUDOTGCINEGJXR7OMH64YWWQ/bundle.json","state":"https://pith.science/pith/XSBUDOTGCINEGJXR7OMH64YWWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSBUDOTGCINEGJXR7OMH64YWWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XSBUDOTGCINEGJXR7OMH64YWWQ","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":"bce479d49f762c5c4e11e7e06f72fb0c4d22103a5a8bca9e918673a32cbd603e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T17:14:55Z","title_canon_sha256":"78c9a902dd45e666d460e8a8b9d8a17b80163ffd3aa39bd77326b3c091d10eb1"},"schema_version":"1.0","source":{"id":"2508.00945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00945","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00945v1","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00945","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"XSBUDOTGCINE","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"pith_short_16","alias_value":"XSBUDOTGCINEGJXR","created_at":"2026-07-05T11:47:30Z"},{"alias_kind":"pith_short_8","alias_value":"XSBUDOTG","created_at":"2026-07-05T11:47:30Z"}],"graph_snapshots":[{"event_id":"sha256:69bd343c9aabb8b4542162ddb86deb798108df1dba92c6bbb99ff1eb607b957d","target":"graph","created_at":"2026-07-05T11:47:30Z","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/2508.00945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) face challenges in effectively coordinating diverse attention mechanisms for cross-modal embedding learning, leading to mismatched attention and suboptimal performance. We propose Consistent Cross-layer Regional Alignment (CCRA), which introduces Layer-Patch-wise Cross Attention (LPWCA) to capture fine-grained regional-semantic correlations by jointly weighting patch and layer-wise embedding, and Progressive Attention Integration (PAI) that systematically coordinates LPWCA, layer-wise, and patch-wise attention mechanisms in sequence. This progressive design ensure","authors_text":"Cheng Jiang, Chenzhong Li, Hongfeng Ai, Jiahua Dong, Maowei Jiang, Mengting Xiao, Quangao Liu, Ruiqi Li, Ruiyuan Kang, Yifan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T17:14:55Z","title":"Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00945","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":"sha256:67cefb5d82e924ad6aa71697fb99d3962fc3dbfc20cf9b93012b20c6574aceeb","target":"record","created_at":"2026-07-05T11:47:30Z","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":"bce479d49f762c5c4e11e7e06f72fb0c4d22103a5a8bca9e918673a32cbd603e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T17:14:55Z","title_canon_sha256":"78c9a902dd45e666d460e8a8b9d8a17b80163ffd3aa39bd77326b3c091d10eb1"},"schema_version":"1.0","source":{"id":"2508.00945","kind":"arxiv","version":1}},"canonical_sha256":"bc8341ba66121a4326f1fb987f7316b4343932df5d10c97dc0e7bbcd571a757e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc8341ba66121a4326f1fb987f7316b4343932df5d10c97dc0e7bbcd571a757e","first_computed_at":"2026-07-05T11:47:30.272052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:30.272052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SdtJdx9tVUK+R+WgPobrFT/RPuAzt9eiymLs9Hyir5jFnJM1lzsfdrWYE3AQqRpftMdlIhUvu7IuwD6RwpmbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:30.272477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67cefb5d82e924ad6aa71697fb99d3962fc3dbfc20cf9b93012b20c6574aceeb","sha256:69bd343c9aabb8b4542162ddb86deb798108df1dba92c6bbb99ff1eb607b957d"],"state_sha256":"e5eb60333a2ab3aa2d71c9f95b20f8e7f7a5c5a9bd2e024df09a26ee889ba6ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pAsfmbStxdC1uJf3WSVknMJJWEp/rLm3QtNM0MIuPWzLVgE6oWfwdkKsXcAEyO1bAsfKZGSNG+s3xInSF03SDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:23:20.242443Z","bundle_sha256":"c2f06c8260ee70b9ca18092d8bdcf58f427d48cba1c02507f3337e68ab8e315f"}}