{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NA2ITDV47QNSIJ4ILY36YLQ6AC","short_pith_number":"pith:NA2ITDV4","canonical_record":{"source":{"id":"2304.10254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T12:23:29Z","cross_cats_sorted":[],"title_canon_sha256":"d2c27bd73843bc72836132e49432243aeb1007472e0e5a1965ca1c37e76975bf","abstract_canon_sha256":"e3cad7fc6f53b176fba66c6ff6972baa739076214a82b203026e2e0e6ae59192"},"schema_version":"1.0"},"canonical_sha256":"6834898ebcfc1b2427885e37ec2e1e009c026126dbb0bcbf224833e9a93c8227","source":{"kind":"arxiv","id":"2304.10254","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.10254","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2304.10254v2","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10254","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"NA2ITDV47QNS","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"NA2ITDV47QNSIJ4I","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"NA2ITDV4","created_at":"2026-07-05T06:05:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NA2ITDV47QNSIJ4ILY36YLQ6AC","target":"record","payload":{"canonical_record":{"source":{"id":"2304.10254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T12:23:29Z","cross_cats_sorted":[],"title_canon_sha256":"d2c27bd73843bc72836132e49432243aeb1007472e0e5a1965ca1c37e76975bf","abstract_canon_sha256":"e3cad7fc6f53b176fba66c6ff6972baa739076214a82b203026e2e0e6ae59192"},"schema_version":"1.0"},"canonical_sha256":"6834898ebcfc1b2427885e37ec2e1e009c026126dbb0bcbf224833e9a93c8227","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:16.532156Z","signature_b64":"KKpjmTYTwRPwMnkuWDmpzoubsy+r1Bg8JdbvXTjkOcm4cB2o7KFeyQ4cE71ZPuGmyTgJdlJYtcHnQiu0vwghCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6834898ebcfc1b2427885e37ec2e1e009c026126dbb0bcbf224833e9a93c8227","last_reissued_at":"2026-07-05T06:05:16.531800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:16.531800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.10254","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gj3OW155GjxHU8Ty+qv7vBOzGjcSA96f/zYWn5BaSoHvgsT4K+2SxhGFGzlgmFr9AHQpbpKoiKrpHmY7Gt4ZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:14:25.670855Z"},"content_sha256":"ed413c46da8f5d78eb486a12a24169c51c44e70d9044d90f7281e8c73be3330b","schema_version":"1.0","event_id":"sha256:ed413c46da8f5d78eb486a12a24169c51c44e70d9044d90f7281e8c73be3330b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NA2ITDV47QNSIJ4ILY36YLQ6AC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image-text Retrieval via Preserving Main Semantics of Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Philippe Fournier-Viger, Xinzheng Niu, Xudong Dai, Xu Zhang","submitted_at":"2023-04-20T12:23:29Z","abstract_excerpt":"Image-text retrieval is one of the major tasks of cross-modal retrieval. Several approaches for this task map images and texts into a common space to create correspondences between the two modalities. However, due to the content (semantics) richness of an image, redundant secondary information in an image may cause false matches. To address this issue, this paper presents a semantic optimization approach, implemented as a Visual Semantic Loss (VSL), to assist the model in focusing on an image's main content. This approach is inspired by how people typically annotate the content of an image by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10254","kind":"arxiv","version":2},"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/2304.10254/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":"2026-07-05T06:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0bTLozbhPTLKJIr/JuWu/x51vBSOVqbtxh62fpU/21aiFM1U6Vo8rk+Ua0HghjklslCwPO2G0V2QBog1F1RqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:14:25.671251Z"},"content_sha256":"1c59b051b81fa04d6d3f7022d184aead0e3fa0d1462130ddc992035a3fae245e","schema_version":"1.0","event_id":"sha256:1c59b051b81fa04d6d3f7022d184aead0e3fa0d1462130ddc992035a3fae245e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NA2ITDV47QNSIJ4ILY36YLQ6AC/bundle.json","state_url":"https://pith.science/pith/NA2ITDV47QNSIJ4ILY36YLQ6AC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NA2ITDV47QNSIJ4ILY36YLQ6AC/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":"2026-08-05T03:14:25Z","links":{"resolver":"https://pith.science/pith/NA2ITDV47QNSIJ4ILY36YLQ6AC","bundle":"https://pith.science/pith/NA2ITDV47QNSIJ4ILY36YLQ6AC/bundle.json","state":"https://pith.science/pith/NA2ITDV47QNSIJ4ILY36YLQ6AC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NA2ITDV47QNSIJ4ILY36YLQ6AC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NA2ITDV47QNSIJ4ILY36YLQ6AC","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":"e3cad7fc6f53b176fba66c6ff6972baa739076214a82b203026e2e0e6ae59192","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T12:23:29Z","title_canon_sha256":"d2c27bd73843bc72836132e49432243aeb1007472e0e5a1965ca1c37e76975bf"},"schema_version":"1.0","source":{"id":"2304.10254","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.10254","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2304.10254v2","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10254","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"NA2ITDV47QNS","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"NA2ITDV47QNSIJ4I","created_at":"2026-07-05T06:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"NA2ITDV4","created_at":"2026-07-05T06:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:1c59b051b81fa04d6d3f7022d184aead0e3fa0d1462130ddc992035a3fae245e","target":"graph","created_at":"2026-07-05T06:05:16Z","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/2304.10254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-text retrieval is one of the major tasks of cross-modal retrieval. Several approaches for this task map images and texts into a common space to create correspondences between the two modalities. However, due to the content (semantics) richness of an image, redundant secondary information in an image may cause false matches. To address this issue, this paper presents a semantic optimization approach, implemented as a Visual Semantic Loss (VSL), to assist the model in focusing on an image's main content. This approach is inspired by how people typically annotate the content of an image by ","authors_text":"Philippe Fournier-Viger, Xinzheng Niu, Xudong Dai, Xu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T12:23:29Z","title":"Image-text Retrieval via Preserving Main Semantics of Vision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10254","kind":"arxiv","version":2},"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:ed413c46da8f5d78eb486a12a24169c51c44e70d9044d90f7281e8c73be3330b","target":"record","created_at":"2026-07-05T06:05:16Z","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":"e3cad7fc6f53b176fba66c6ff6972baa739076214a82b203026e2e0e6ae59192","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T12:23:29Z","title_canon_sha256":"d2c27bd73843bc72836132e49432243aeb1007472e0e5a1965ca1c37e76975bf"},"schema_version":"1.0","source":{"id":"2304.10254","kind":"arxiv","version":2}},"canonical_sha256":"6834898ebcfc1b2427885e37ec2e1e009c026126dbb0bcbf224833e9a93c8227","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6834898ebcfc1b2427885e37ec2e1e009c026126dbb0bcbf224833e9a93c8227","first_computed_at":"2026-07-05T06:05:16.531800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:16.531800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KKpjmTYTwRPwMnkuWDmpzoubsy+r1Bg8JdbvXTjkOcm4cB2o7KFeyQ4cE71ZPuGmyTgJdlJYtcHnQiu0vwghCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:16.532156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.10254","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed413c46da8f5d78eb486a12a24169c51c44e70d9044d90f7281e8c73be3330b","sha256:1c59b051b81fa04d6d3f7022d184aead0e3fa0d1462130ddc992035a3fae245e"],"state_sha256":"1a2f5c3542a9a3549a7d3bdfd3fedc9b2f218260088f6c93c4ba40e2decc6804"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LyDqqHWAVZ/x2YFx65XocWy56nHom6ftI2PuXdHuvWzeq00Hmr3UCvtA3AL3LmV9xvvkBfY85u74NceUegHmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:14:25.674087Z","bundle_sha256":"e82bde0b7acc9a9f3628876cd01e52e9d1c03a5b84d23985af5fe7f167a83cc5"}}