{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WLWQTO6AMNZ6UTWHZWPGXHVJM6","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":"9fb7d9a9220cfe7954692d09850f9cd6cb4c84396907d4a76c0efa5cfde8c113","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T07:24:54Z","title_canon_sha256":"ba48314a510323817497dced9c4b69bde1310f2679ce295784ae549c97ff7f00"},"schema_version":"1.0","source":{"id":"2108.02417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02417","created_at":"2026-07-05T03:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02417v1","created_at":"2026-07-05T03:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02417","created_at":"2026-07-05T03:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"WLWQTO6AMNZ6","created_at":"2026-07-05T03:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"WLWQTO6AMNZ6UTWH","created_at":"2026-07-05T03:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"WLWQTO6A","created_at":"2026-07-05T03:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:84dab86356c5cb9f2be594f2af0ecb0120d8588f611c447f72c7f135f6fe7f05","target":"graph","created_at":"2026-07-05T03:03:32Z","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/2108.02417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic correspondences. However, the retrieval performance remains unsatisfactory due to a lack of consistent representation in both semantics and structural spaces. In this work, we propose to address the above issue from two aspects: (i) constructing intrinsic structure (along with relations) among the fragments of respective modalities, e.g., \"dog $\\to$ play $\\to$ ba","authors_text":"Fuhai Chen, Joemon M. Jose, Xiao Liu, Xuri Ge, Zhilong Ji, Zhongqin Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T07:24:54Z","title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02417","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":"sha256:6f98023ec377572abc72a75d30a0781d33121962a3052bd6aa37a0efa2cbf315","target":"record","created_at":"2026-07-05T03:03:32Z","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":"9fb7d9a9220cfe7954692d09850f9cd6cb4c84396907d4a76c0efa5cfde8c113","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T07:24:54Z","title_canon_sha256":"ba48314a510323817497dced9c4b69bde1310f2679ce295784ae549c97ff7f00"},"schema_version":"1.0","source":{"id":"2108.02417","kind":"arxiv","version":1}},"canonical_sha256":"b2ed09bbc06373ea4ec7cd9e6b9ea967b4144f772d933cc81f28513e128e39f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2ed09bbc06373ea4ec7cd9e6b9ea967b4144f772d933cc81f28513e128e39f7","first_computed_at":"2026-07-05T03:03:32.855086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:32.855086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icsVEa3qN2GMhx2Y1GxUo4HKdURvZhh9bLNmFqtEmMVw6Kdt5iEbx4cmUib6ZF90NXgL6TDKISLz6RjtknkTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:32.855484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f98023ec377572abc72a75d30a0781d33121962a3052bd6aa37a0efa2cbf315","sha256:84dab86356c5cb9f2be594f2af0ecb0120d8588f611c447f72c7f135f6fe7f05"],"state_sha256":"12ab1f528028ac59e36d2f939158c2b4eea758f754d61e1d1b7df3a3f905fa59"}