{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3MFTTDMWUGU7YZTLXDGF4F2OCW","short_pith_number":"pith:3MFTTDMW","canonical_record":{"source":{"id":"2303.11090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T13:22:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"353a7da90ff91a8e6fa535847c6f8e1fc5b5617a10f2962c1621da7e04a827bd","abstract_canon_sha256":"1fd275b24eec96d77d50719e7ccca67be206cc3a54a01d258d29c45b75199daf"},"schema_version":"1.0"},"canonical_sha256":"db0b398d96a1a9fc666bb8cc5e174e15a4e82314bd9539aa38069329db71f25c","source":{"kind":"arxiv","id":"2303.11090","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11090","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11090v1","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11090","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"3MFTTDMWUGU7","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"3MFTTDMWUGU7YZTL","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"3MFTTDMW","created_at":"2026-07-05T05:52:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3MFTTDMWUGU7YZTLXDGF4F2OCW","target":"record","payload":{"canonical_record":{"source":{"id":"2303.11090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T13:22:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"353a7da90ff91a8e6fa535847c6f8e1fc5b5617a10f2962c1621da7e04a827bd","abstract_canon_sha256":"1fd275b24eec96d77d50719e7ccca67be206cc3a54a01d258d29c45b75199daf"},"schema_version":"1.0"},"canonical_sha256":"db0b398d96a1a9fc666bb8cc5e174e15a4e82314bd9539aa38069329db71f25c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:40.193514Z","signature_b64":"bCHSHUG35zGm0BMZaFX++ilVjznExWTxev7+kQUdwAJDwuJ5WTxx9wLysiLvxCewToxgR0s8Rn1LawUOMQBAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db0b398d96a1a9fc666bb8cc5e174e15a4e82314bd9539aa38069329db71f25c","last_reissued_at":"2026-07-05T05:52:40.193086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:40.193086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.11090","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":"2026-07-05T05:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xatQlLptEYTZ3PBFGPOGVFDG5Qx+63GK2A3XzbkzTl9OVAegp+hxi3CFWbqow3zjU5CYbSO3tiVivcHS6CgpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:57:55.892647Z"},"content_sha256":"b980a5f3ceb78096afea68a5fede1cb71a491060102861172f82a4dbb3807fb0","schema_version":"1.0","event_id":"sha256:b980a5f3ceb78096afea68a5fede1cb71a491060102861172f82a4dbb3807fb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3MFTTDMWUGU7YZTLXDGF4F2OCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scene Graph Based Fusion Network For Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guoliang Wang, Yanlei Shang, Yong Chen","submitted_at":"2023-03-20T13:22:56Z","abstract_excerpt":"A critical challenge to image-text retrieval is how to learn accurate correspondences between images and texts. Most existing methods mainly focus on coarse-grained correspondences based on co-occurrences of semantic objects, while failing to distinguish the fine-grained local correspondences. In this paper, we propose a novel Scene Graph based Fusion Network (dubbed SGFN), which enhances the images'/texts' features through intra- and cross-modal fusion for image-text retrieval. To be specific, we design an intra-modal hierarchical attention fusion to incorporate semantic contexts, such as obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11090","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/2303.11090/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":"2026-07-05T05:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBWGU12a/Yl3pTIwwBHy54aJ3ToKEDpUwtkNPjiqq3cZGaBHoLBtTGTP0zC5DOFC/bkmr+UJzuyN2l19W5rgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:57:55.893475Z"},"content_sha256":"6c4f2b203800dde873104d82dc8b4edfa17bc8c309d0fac52daa169def05b2b1","schema_version":"1.0","event_id":"sha256:6c4f2b203800dde873104d82dc8b4edfa17bc8c309d0fac52daa169def05b2b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MFTTDMWUGU7YZTLXDGF4F2OCW/bundle.json","state_url":"https://pith.science/pith/3MFTTDMWUGU7YZTLXDGF4F2OCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MFTTDMWUGU7YZTLXDGF4F2OCW/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":"2026-08-04T19:57:55Z","links":{"resolver":"https://pith.science/pith/3MFTTDMWUGU7YZTLXDGF4F2OCW","bundle":"https://pith.science/pith/3MFTTDMWUGU7YZTLXDGF4F2OCW/bundle.json","state":"https://pith.science/pith/3MFTTDMWUGU7YZTLXDGF4F2OCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MFTTDMWUGU7YZTLXDGF4F2OCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3MFTTDMWUGU7YZTLXDGF4F2OCW","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":"1fd275b24eec96d77d50719e7ccca67be206cc3a54a01d258d29c45b75199daf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T13:22:56Z","title_canon_sha256":"353a7da90ff91a8e6fa535847c6f8e1fc5b5617a10f2962c1621da7e04a827bd"},"schema_version":"1.0","source":{"id":"2303.11090","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11090","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11090v1","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11090","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"3MFTTDMWUGU7","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"3MFTTDMWUGU7YZTL","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"3MFTTDMW","created_at":"2026-07-05T05:52:40Z"}],"graph_snapshots":[{"event_id":"sha256:6c4f2b203800dde873104d82dc8b4edfa17bc8c309d0fac52daa169def05b2b1","target":"graph","created_at":"2026-07-05T05:52:40Z","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/2303.11090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A critical challenge to image-text retrieval is how to learn accurate correspondences between images and texts. Most existing methods mainly focus on coarse-grained correspondences based on co-occurrences of semantic objects, while failing to distinguish the fine-grained local correspondences. In this paper, we propose a novel Scene Graph based Fusion Network (dubbed SGFN), which enhances the images'/texts' features through intra- and cross-modal fusion for image-text retrieval. To be specific, we design an intra-modal hierarchical attention fusion to incorporate semantic contexts, such as obj","authors_text":"Guoliang Wang, Yanlei Shang, Yong Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T13:22:56Z","title":"Scene Graph Based Fusion Network For Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11090","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:b980a5f3ceb78096afea68a5fede1cb71a491060102861172f82a4dbb3807fb0","target":"record","created_at":"2026-07-05T05:52:40Z","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":"1fd275b24eec96d77d50719e7ccca67be206cc3a54a01d258d29c45b75199daf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T13:22:56Z","title_canon_sha256":"353a7da90ff91a8e6fa535847c6f8e1fc5b5617a10f2962c1621da7e04a827bd"},"schema_version":"1.0","source":{"id":"2303.11090","kind":"arxiv","version":1}},"canonical_sha256":"db0b398d96a1a9fc666bb8cc5e174e15a4e82314bd9539aa38069329db71f25c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db0b398d96a1a9fc666bb8cc5e174e15a4e82314bd9539aa38069329db71f25c","first_computed_at":"2026-07-05T05:52:40.193086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:40.193086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bCHSHUG35zGm0BMZaFX++ilVjznExWTxev7+kQUdwAJDwuJ5WTxx9wLysiLvxCewToxgR0s8Rn1LawUOMQBAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:40.193514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.11090","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b980a5f3ceb78096afea68a5fede1cb71a491060102861172f82a4dbb3807fb0","sha256:6c4f2b203800dde873104d82dc8b4edfa17bc8c309d0fac52daa169def05b2b1"],"state_sha256":"7f46cac57119993026bbb2e2523a350108d02e2060f6716ba76832cd8b98bbde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bbkO6EsF0b96epPHjl5ZlgmbXtBDOcM6mnfEyclU1Hb50xHsWIcGRv1AsnVTx2fT1Pnx1ka2sWLLcmuUh2D+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:57:55.901512Z","bundle_sha256":"973500f13f132d03e1a7ca9f7db0c65783a8da2b00ec6438ee060924098441d8"}}