{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:55IT5XPUQUON3FMX47TDRIQ7DK","short_pith_number":"pith:55IT5XPU","canonical_record":{"source":{"id":"2406.15306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T08:32:24Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"0544fc45f0579ae3b2e6665a2ace3e90f4092e4f2f28b3852414535e4c5d0ca8","abstract_canon_sha256":"55154932e9824b222580e8054e050f0b002e2187eafbc69bb2739356760aaf6a"},"schema_version":"1.0"},"canonical_sha256":"ef513eddf4851cdd9597e7e638a21f1a941a57db7059b7853c08bf7182e46d9b","source":{"kind":"arxiv","id":"2406.15306","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15306","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15306v1","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15306","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"pith_short_12","alias_value":"55IT5XPUQUON","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"pith_short_16","alias_value":"55IT5XPUQUON3FMX","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"pith_short_8","alias_value":"55IT5XPU","created_at":"2026-07-05T08:35:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:55IT5XPUQUON3FMX47TDRIQ7DK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T08:32:24Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"0544fc45f0579ae3b2e6665a2ace3e90f4092e4f2f28b3852414535e4c5d0ca8","abstract_canon_sha256":"55154932e9824b222580e8054e050f0b002e2187eafbc69bb2739356760aaf6a"},"schema_version":"1.0"},"canonical_sha256":"ef513eddf4851cdd9597e7e638a21f1a941a57db7059b7853c08bf7182e46d9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:16.841433Z","signature_b64":"jiZYqaWVGpOktpuFNpvhKhvy5F46lM8/8t38e6dV9eKdeBhTwDch401C2K9nYK0K4YTpNC59+SDoCqyC3c6cAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef513eddf4851cdd9597e7e638a21f1a941a57db7059b7853c08bf7182e46d9b","last_reissued_at":"2026-07-05T08:35:16.840927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:16.840927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15306","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":"2026-07-05T08:35:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIRmbkxBNhOssBohccTs8ETRexQpNDlHc/JJVFiq1t1ulUuFrkIDfSobRdANw56NiiG2r0gH1xwvlMpUaAsgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:04:17.488181Z"},"content_sha256":"6497cfe10a978023541fa7e24fcbb01d2b54c72f2b50ca0616b9a30e2cbaf41a","schema_version":"1.0","event_id":"sha256:6497cfe10a978023541fa7e24fcbb01d2b54c72f2b50ca0616b9a30e2cbaf41a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:55IT5XPUQUON3FMX47TDRIQ7DK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advanced Multimodal Deep Learning Architecture for Image-Text Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Haijing Zhang, Jinyin Wang, Rongwei Ji, Yihao Zhong, Yingbin Liang, Yiru Cang","submitted_at":"2024-06-13T08:32:24Z","abstract_excerpt":"Image-text matching is a key multimodal task that aims to model the semantic association between images and text as a matching relationship. With the advent of the multimedia information age, image, and text data show explosive growth, and how to accurately realize the efficient and accurate semantic correspondence between them has become the core issue of common concern in academia and industry. In this study, we delve into the limitations of current multimodal deep learning models in processing image-text pairing tasks. Therefore, we innovatively design an advanced multimodal deep learning a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15306","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/2406.15306/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":"2026-07-05T08:35:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQ+kJvfA7vBeXQGfcl0I/yDYLOBmapUmvQ8NzuewTu1jd+EZa7pNd+ivsqKWMjeuu6MPxxwkjgb9/sFXm3lUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:04:17.489052Z"},"content_sha256":"f538de76a9a3e9dcefc59984d94ca7048b78a80c07c2d3a0f0ed7081ed38147d","schema_version":"1.0","event_id":"sha256:f538de76a9a3e9dcefc59984d94ca7048b78a80c07c2d3a0f0ed7081ed38147d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55IT5XPUQUON3FMX47TDRIQ7DK/bundle.json","state_url":"https://pith.science/pith/55IT5XPUQUON3FMX47TDRIQ7DK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55IT5XPUQUON3FMX47TDRIQ7DK/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":"2026-08-10T08:04:17Z","links":{"resolver":"https://pith.science/pith/55IT5XPUQUON3FMX47TDRIQ7DK","bundle":"https://pith.science/pith/55IT5XPUQUON3FMX47TDRIQ7DK/bundle.json","state":"https://pith.science/pith/55IT5XPUQUON3FMX47TDRIQ7DK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55IT5XPUQUON3FMX47TDRIQ7DK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:55IT5XPUQUON3FMX47TDRIQ7DK","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":"55154932e9824b222580e8054e050f0b002e2187eafbc69bb2739356760aaf6a","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T08:32:24Z","title_canon_sha256":"0544fc45f0579ae3b2e6665a2ace3e90f4092e4f2f28b3852414535e4c5d0ca8"},"schema_version":"1.0","source":{"id":"2406.15306","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15306","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15306v1","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15306","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"pith_short_12","alias_value":"55IT5XPUQUON","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"pith_short_16","alias_value":"55IT5XPUQUON3FMX","created_at":"2026-07-05T08:35:16Z"},{"alias_kind":"pith_short_8","alias_value":"55IT5XPU","created_at":"2026-07-05T08:35:16Z"}],"graph_snapshots":[{"event_id":"sha256:f538de76a9a3e9dcefc59984d94ca7048b78a80c07c2d3a0f0ed7081ed38147d","target":"graph","created_at":"2026-07-05T08:35:16Z","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/2406.15306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-text matching is a key multimodal task that aims to model the semantic association between images and text as a matching relationship. With the advent of the multimedia information age, image, and text data show explosive growth, and how to accurately realize the efficient and accurate semantic correspondence between them has become the core issue of common concern in academia and industry. In this study, we delve into the limitations of current multimodal deep learning models in processing image-text pairing tasks. Therefore, we innovatively design an advanced multimodal deep learning a","authors_text":"Haijing Zhang, Jinyin Wang, Rongwei Ji, Yihao Zhong, Yingbin Liang, Yiru Cang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T08:32:24Z","title":"Advanced Multimodal Deep Learning Architecture for Image-Text Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15306","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":"sha256:6497cfe10a978023541fa7e24fcbb01d2b54c72f2b50ca0616b9a30e2cbaf41a","target":"record","created_at":"2026-07-05T08:35:16Z","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":"55154932e9824b222580e8054e050f0b002e2187eafbc69bb2739356760aaf6a","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T08:32:24Z","title_canon_sha256":"0544fc45f0579ae3b2e6665a2ace3e90f4092e4f2f28b3852414535e4c5d0ca8"},"schema_version":"1.0","source":{"id":"2406.15306","kind":"arxiv","version":1}},"canonical_sha256":"ef513eddf4851cdd9597e7e638a21f1a941a57db7059b7853c08bf7182e46d9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef513eddf4851cdd9597e7e638a21f1a941a57db7059b7853c08bf7182e46d9b","first_computed_at":"2026-07-05T08:35:16.840927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:16.840927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jiZYqaWVGpOktpuFNpvhKhvy5F46lM8/8t38e6dV9eKdeBhTwDch401C2K9nYK0K4YTpNC59+SDoCqyC3c6cAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:16.841433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15306","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6497cfe10a978023541fa7e24fcbb01d2b54c72f2b50ca0616b9a30e2cbaf41a","sha256:f538de76a9a3e9dcefc59984d94ca7048b78a80c07c2d3a0f0ed7081ed38147d"],"state_sha256":"1589d299ca44eb362a5852299c7f11dd680e8f196a5d2f56f62786a51130c123"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9F7Wj/nqeFh8WWhsVwQQYLJKTA5n6+/vIT4No0j/olxWc5nBAg9iRjHdzsIvyzVQY5/N3mIU2kXuunFLid4+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:04:17.512880Z","bundle_sha256":"e1ff9e9c7a03e58251b6c769ff9c65c4690cb131647afbc36a7b759523163cfd"}}