{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PW2YMRSA2VIOEJCQFSETTVBNO3","short_pith_number":"pith:PW2YMRSA","canonical_record":{"source":{"id":"2507.08590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-11T13:38:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cef4f3f25b4497df9a4a1069a25ac9b3eb7f0c08e3b28d28880c8a24139850ef","abstract_canon_sha256":"c8259a93ac3f672940fd361ea2a133a62c3bca5cdd3643b0c45f14ef735e42bb"},"schema_version":"1.0"},"canonical_sha256":"7db5864640d550e224502c8939d42d76ce0c7313396b321fcd85820b5dfc42a7","source":{"kind":"arxiv","id":"2507.08590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08590","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08590v1","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08590","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"PW2YMRSA2VIO","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"PW2YMRSA2VIOEJCQ","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"PW2YMRSA","created_at":"2026-07-05T11:35:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PW2YMRSA2VIOEJCQFSETTVBNO3","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-11T13:38:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cef4f3f25b4497df9a4a1069a25ac9b3eb7f0c08e3b28d28880c8a24139850ef","abstract_canon_sha256":"c8259a93ac3f672940fd361ea2a133a62c3bca5cdd3643b0c45f14ef735e42bb"},"schema_version":"1.0"},"canonical_sha256":"7db5864640d550e224502c8939d42d76ce0c7313396b321fcd85820b5dfc42a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:42.453830Z","signature_b64":"LxbDw9ErRfxk6urkyMVajj3eWvdEUNKedykzZVw4+3PTLXSug/e0F+ZHhldGwrkAgCaYcZN5Lv6Gg3hkoOzxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db5864640d550e224502c8939d42d76ce0c7313396b321fcd85820b5dfc42a7","last_reissued_at":"2026-07-05T11:35:42.453383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:42.453383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08590","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":"2026-07-05T11:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2wuvVyuK9KzW0hAA/1bUW6CPreATvQyJf/zUge4QaX7A4czJHvB7joNpabkpaWufxIspYYMRxtm9ntSB8ye8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:39:42.242924Z"},"content_sha256":"f6f4907ea4c5d0a6a63b9d913d3434dd3d32d9d6b333a07d97ca8404adac515c","schema_version":"1.0","event_id":"sha256:f6f4907ea4c5d0a6a63b9d913d3434dd3d32d9d6b333a07d97ca8404adac515c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PW2YMRSA2VIOEJCQFSETTVBNO3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Semantic Description Generation with MLLMs for Image-Text Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Junyu Chen, Mingyong Li, Yihua Gao","submitted_at":"2025-07-11T13:38:01Z","abstract_excerpt":"Image-text matching (ITM) aims to address the fundamental challenge of aligning visual and textual modalities, which inherently differ in their representations, continuous, high-dimensional image features vs. discrete, structured text. We propose a novel framework that bridges the modality gap by leveraging multimodal large language models (MLLMs) as visual semantic parsers. By generating rich Visual Semantic Descriptions (VSD), MLLMs provide semantic anchor that facilitate cross-modal alignment. Our approach combines: (1) Instance-level alignment by fusing visual features with VSD to enhance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08590","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/2507.08590/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":"2026-07-05T11:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X65mdljWbgG1pk9pR3ybbJVH4ipL5WyqHfeV9HnQDJHUkqIr0LTZLO083y8KHbLw60l/YLEhICWeEJcajyNLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:39:42.243417Z"},"content_sha256":"b4feeee2b5949f0bd807cafb34bcfaed63c00da7bd3c5f2c453c3a697734b087","schema_version":"1.0","event_id":"sha256:b4feeee2b5949f0bd807cafb34bcfaed63c00da7bd3c5f2c453c3a697734b087"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PW2YMRSA2VIOEJCQFSETTVBNO3/bundle.json","state_url":"https://pith.science/pith/PW2YMRSA2VIOEJCQFSETTVBNO3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PW2YMRSA2VIOEJCQFSETTVBNO3/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":"2026-08-08T11:39:42Z","links":{"resolver":"https://pith.science/pith/PW2YMRSA2VIOEJCQFSETTVBNO3","bundle":"https://pith.science/pith/PW2YMRSA2VIOEJCQFSETTVBNO3/bundle.json","state":"https://pith.science/pith/PW2YMRSA2VIOEJCQFSETTVBNO3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PW2YMRSA2VIOEJCQFSETTVBNO3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PW2YMRSA2VIOEJCQFSETTVBNO3","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":"c8259a93ac3f672940fd361ea2a133a62c3bca5cdd3643b0c45f14ef735e42bb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-11T13:38:01Z","title_canon_sha256":"cef4f3f25b4497df9a4a1069a25ac9b3eb7f0c08e3b28d28880c8a24139850ef"},"schema_version":"1.0","source":{"id":"2507.08590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08590","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08590v1","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08590","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"PW2YMRSA2VIO","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"PW2YMRSA2VIOEJCQ","created_at":"2026-07-05T11:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"PW2YMRSA","created_at":"2026-07-05T11:35:42Z"}],"graph_snapshots":[{"event_id":"sha256:b4feeee2b5949f0bd807cafb34bcfaed63c00da7bd3c5f2c453c3a697734b087","target":"graph","created_at":"2026-07-05T11:35:42Z","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/2507.08590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-text matching (ITM) aims to address the fundamental challenge of aligning visual and textual modalities, which inherently differ in their representations, continuous, high-dimensional image features vs. discrete, structured text. We propose a novel framework that bridges the modality gap by leveraging multimodal large language models (MLLMs) as visual semantic parsers. By generating rich Visual Semantic Descriptions (VSD), MLLMs provide semantic anchor that facilitate cross-modal alignment. Our approach combines: (1) Instance-level alignment by fusing visual features with VSD to enhance ","authors_text":"Junyu Chen, Mingyong Li, Yihua Gao","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-11T13:38:01Z","title":"Visual Semantic Description Generation with MLLMs for Image-Text Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08590","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:f6f4907ea4c5d0a6a63b9d913d3434dd3d32d9d6b333a07d97ca8404adac515c","target":"record","created_at":"2026-07-05T11:35:42Z","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":"c8259a93ac3f672940fd361ea2a133a62c3bca5cdd3643b0c45f14ef735e42bb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-11T13:38:01Z","title_canon_sha256":"cef4f3f25b4497df9a4a1069a25ac9b3eb7f0c08e3b28d28880c8a24139850ef"},"schema_version":"1.0","source":{"id":"2507.08590","kind":"arxiv","version":1}},"canonical_sha256":"7db5864640d550e224502c8939d42d76ce0c7313396b321fcd85820b5dfc42a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7db5864640d550e224502c8939d42d76ce0c7313396b321fcd85820b5dfc42a7","first_computed_at":"2026-07-05T11:35:42.453383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:42.453383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LxbDw9ErRfxk6urkyMVajj3eWvdEUNKedykzZVw4+3PTLXSug/e0F+ZHhldGwrkAgCaYcZN5Lv6Gg3hkoOzxAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:42.453830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6f4907ea4c5d0a6a63b9d913d3434dd3d32d9d6b333a07d97ca8404adac515c","sha256:b4feeee2b5949f0bd807cafb34bcfaed63c00da7bd3c5f2c453c3a697734b087"],"state_sha256":"72a3d2e0b2f0a4ec617a132fbc8012d31ed74877973e7c4466b04352ea8162e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WKlVHYiX2g7ouldVMQUoqF1XVZz7C8kL0VzuHS8PzcnCoaRlLUOnF9yHyBi2l9yTv6kkqHCNJLNM+nAGiSoHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:39:42.248170Z","bundle_sha256":"631202d8f0a58740e42db0ed108a03ef36c9da9af2f303a11694ea3e99c32283"}}