{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OYO4JHOVXFIY34656SRNHZWC5D","short_pith_number":"pith:OYO4JHOV","canonical_record":{"source":{"id":"2401.09725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-18T05:00:18Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"285418593a41ef403ebdbbb50e98e7fac2ae15c714226cb65c046768b40b1d1e","abstract_canon_sha256":"76d03b0ac771777e171cf8eb387f183e11600003707d3508bde4d88e3ef6eec7"},"schema_version":"1.0"},"canonical_sha256":"761dc49dd5b9518df3ddf4a2d3e6c2e8f10d25419a8b7be49e0c877631997c3a","source":{"kind":"arxiv","id":"2401.09725","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09725","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09725v1","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09725","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_12","alias_value":"OYO4JHOVXFIY","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_16","alias_value":"OYO4JHOVXFIY3465","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_8","alias_value":"OYO4JHOV","created_at":"2026-07-05T07:35:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OYO4JHOVXFIY34656SRNHZWC5D","target":"record","payload":{"canonical_record":{"source":{"id":"2401.09725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-18T05:00:18Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"285418593a41ef403ebdbbb50e98e7fac2ae15c714226cb65c046768b40b1d1e","abstract_canon_sha256":"76d03b0ac771777e171cf8eb387f183e11600003707d3508bde4d88e3ef6eec7"},"schema_version":"1.0"},"canonical_sha256":"761dc49dd5b9518df3ddf4a2d3e6c2e8f10d25419a8b7be49e0c877631997c3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:01.292685Z","signature_b64":"aSomqL4eUkhmkYtOojHEASi6Jc/9zrSCkTbPVUZQfh+CFWvI0KcZwDMyxxZWoib6+pZhf2c9ftnZpeXijBUcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"761dc49dd5b9518df3ddf4a2d3e6c2e8f10d25419a8b7be49e0c877631997c3a","last_reissued_at":"2026-07-05T07:35:01.292092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:01.292092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.09725","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":"2026-07-05T07:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXfvbJ9UDvDo8EH2x0VF2Y27ckC1fxV4clBJfEWMe1w4HjoRuht0XvadcAWfyhWGjL/975X7a4xHT849RBRMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:17:43.282193Z"},"content_sha256":"e894d1a6139edeb84d8d5db6bb39452e25da4bbe7b5e7dfbd335394973f5e337","schema_version":"1.0","event_id":"sha256:e894d1a6139edeb84d8d5db6bb39452e25da4bbe7b5e7dfbd335394973f5e337"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OYO4JHOVXFIY34656SRNHZWC5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"I.V. Ramakrishnan, Yunting Yin, Zuhui Wang","submitted_at":"2024-01-18T05:00:18Z","abstract_excerpt":"Image-text matching aims to find matched cross-modal pairs accurately. While current methods often rely on projecting cross-modal features into a common embedding space, they frequently suffer from imbalanced feature representations across different modalities, leading to unreliable retrieval results. To address these limitations, we introduce a novel Feature Enhancement Module that adaptively aggregates single-modal features for more balanced and robust image-text retrieval. Additionally, we propose a new loss function that overcomes the shortcomings of original triplet ranking loss, thereby "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09725","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/2401.09725/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":"2026-07-05T07:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1dmSG1N4knQAsOKERXQqMnlVZpVP7vayVQkzNjITta14fDZ7RpJb2IUmzp+Ee5HOwxUoLd4ExpfcqIfCYzHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:17:43.282742Z"},"content_sha256":"322808581c6168175e537942efe005ded4e840c9b82e4aa0654f6e8bc5ebd3f3","schema_version":"1.0","event_id":"sha256:322808581c6168175e537942efe005ded4e840c9b82e4aa0654f6e8bc5ebd3f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/bundle.json","state_url":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYO4JHOVXFIY34656SRNHZWC5D/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":"2026-08-03T18:17:43Z","links":{"resolver":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D","bundle":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/bundle.json","state":"https://pith.science/pith/OYO4JHOVXFIY34656SRNHZWC5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYO4JHOVXFIY34656SRNHZWC5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OYO4JHOVXFIY34656SRNHZWC5D","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":"76d03b0ac771777e171cf8eb387f183e11600003707d3508bde4d88e3ef6eec7","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-18T05:00:18Z","title_canon_sha256":"285418593a41ef403ebdbbb50e98e7fac2ae15c714226cb65c046768b40b1d1e"},"schema_version":"1.0","source":{"id":"2401.09725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09725","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09725v1","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09725","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_12","alias_value":"OYO4JHOVXFIY","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_16","alias_value":"OYO4JHOVXFIY3465","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_8","alias_value":"OYO4JHOV","created_at":"2026-07-05T07:35:01Z"}],"graph_snapshots":[{"event_id":"sha256:322808581c6168175e537942efe005ded4e840c9b82e4aa0654f6e8bc5ebd3f3","target":"graph","created_at":"2026-07-05T07:35:01Z","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/2401.09725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-text matching aims to find matched cross-modal pairs accurately. While current methods often rely on projecting cross-modal features into a common embedding space, they frequently suffer from imbalanced feature representations across different modalities, leading to unreliable retrieval results. To address these limitations, we introduce a novel Feature Enhancement Module that adaptively aggregates single-modal features for more balanced and robust image-text retrieval. Additionally, we propose a new loss function that overcomes the shortcomings of original triplet ranking loss, thereby ","authors_text":"I.V. Ramakrishnan, Yunting Yin, Zuhui Wang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-18T05:00:18Z","title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09725","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:e894d1a6139edeb84d8d5db6bb39452e25da4bbe7b5e7dfbd335394973f5e337","target":"record","created_at":"2026-07-05T07:35:01Z","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":"76d03b0ac771777e171cf8eb387f183e11600003707d3508bde4d88e3ef6eec7","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-18T05:00:18Z","title_canon_sha256":"285418593a41ef403ebdbbb50e98e7fac2ae15c714226cb65c046768b40b1d1e"},"schema_version":"1.0","source":{"id":"2401.09725","kind":"arxiv","version":1}},"canonical_sha256":"761dc49dd5b9518df3ddf4a2d3e6c2e8f10d25419a8b7be49e0c877631997c3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"761dc49dd5b9518df3ddf4a2d3e6c2e8f10d25419a8b7be49e0c877631997c3a","first_computed_at":"2026-07-05T07:35:01.292092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:01.292092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aSomqL4eUkhmkYtOojHEASi6Jc/9zrSCkTbPVUZQfh+CFWvI0KcZwDMyxxZWoib6+pZhf2c9ftnZpeXijBUcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:01.292685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e894d1a6139edeb84d8d5db6bb39452e25da4bbe7b5e7dfbd335394973f5e337","sha256:322808581c6168175e537942efe005ded4e840c9b82e4aa0654f6e8bc5ebd3f3"],"state_sha256":"d83b650f804c4e00c28e0c325736bdf9b76923bd2b3ae47d4c13945e59ba6e0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kR/UeyWZTQXgK0g5iCpOAday1DfAQ1WhUolhncq0EFhy2F2R1b3b0HyQhH+vnja/9JNVeHwrhxzxs8mRhQfCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:17:43.286392Z","bundle_sha256":"55ec34863d1c1d13703b27f022267540e4d020b32a5761aa578fe3afbac9716b"}}