{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WLWQTO6AMNZ6UTWHZWPGXHVJM6","short_pith_number":"pith:WLWQTO6A","canonical_record":{"source":{"id":"2108.02417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T07:24:54Z","cross_cats_sorted":[],"title_canon_sha256":"ba48314a510323817497dced9c4b69bde1310f2679ce295784ae549c97ff7f00","abstract_canon_sha256":"9fb7d9a9220cfe7954692d09850f9cd6cb4c84396907d4a76c0efa5cfde8c113"},"schema_version":"1.0"},"canonical_sha256":"b2ed09bbc06373ea4ec7cd9e6b9ea967b4144f772d933cc81f28513e128e39f7","source":{"kind":"arxiv","id":"2108.02417","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WLWQTO6AMNZ6UTWHZWPGXHVJM6","target":"record","payload":{"canonical_record":{"source":{"id":"2108.02417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-05T07:24:54Z","cross_cats_sorted":[],"title_canon_sha256":"ba48314a510323817497dced9c4b69bde1310f2679ce295784ae549c97ff7f00","abstract_canon_sha256":"9fb7d9a9220cfe7954692d09850f9cd6cb4c84396907d4a76c0efa5cfde8c113"},"schema_version":"1.0"},"canonical_sha256":"b2ed09bbc06373ea4ec7cd9e6b9ea967b4144f772d933cc81f28513e128e39f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:32.855484Z","signature_b64":"icsVEa3qN2GMhx2Y1GxUo4HKdURvZhh9bLNmFqtEmMVw6Kdt5iEbx4cmUib6ZF90NXgL6TDKISLz6RjtknkTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2ed09bbc06373ea4ec7cd9e6b9ea967b4144f772d933cc81f28513e128e39f7","last_reissued_at":"2026-07-05T03:03:32.855086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:32.855086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.02417","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":"2026-07-05T03:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sA4StH80QWnlI+o73xoQg6By79geNrDQR0KnOtANFMVuh9z+PD3tpK1AyBfUm52bVRJ7vxJgZ8yGUR9Ao1L+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:53:06.345251Z"},"content_sha256":"6f98023ec377572abc72a75d30a0781d33121962a3052bd6aa37a0efa2cbf315","schema_version":"1.0","event_id":"sha256:6f98023ec377572abc72a75d30a0781d33121962a3052bd6aa37a0efa2cbf315"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WLWQTO6AMNZ6UTWHZWPGXHVJM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuhai Chen, Joemon M. Jose, Xiao Liu, Xuri Ge, Zhilong Ji, Zhongqin Wu","submitted_at":"2021-08-05T07:24:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02417","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/2108.02417/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":"2026-07-05T03:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VK89jbWeomQAxYPTxUDwYIEl/PokWUVpjfZ30nhCKFf70qjH+8DEKLIL0H4iiPqcSivuHJveKShhKyQvTtB3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:53:06.345638Z"},"content_sha256":"84dab86356c5cb9f2be594f2af0ecb0120d8588f611c447f72c7f135f6fe7f05","schema_version":"1.0","event_id":"sha256:84dab86356c5cb9f2be594f2af0ecb0120d8588f611c447f72c7f135f6fe7f05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLWQTO6AMNZ6UTWHZWPGXHVJM6/bundle.json","state_url":"https://pith.science/pith/WLWQTO6AMNZ6UTWHZWPGXHVJM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLWQTO6AMNZ6UTWHZWPGXHVJM6/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":"2026-07-07T15:53:06Z","links":{"resolver":"https://pith.science/pith/WLWQTO6AMNZ6UTWHZWPGXHVJM6","bundle":"https://pith.science/pith/WLWQTO6AMNZ6UTWHZWPGXHVJM6/bundle.json","state":"https://pith.science/pith/WLWQTO6AMNZ6UTWHZWPGXHVJM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLWQTO6AMNZ6UTWHZWPGXHVJM6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJ4btmLvx3bi2FAaFna0plesuCZvfahpGSvo4TH6+hZZEB7mP4UuqPpjbyMPIloN8nZEl48W2SJCfIvY2jLKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:53:06.347604Z","bundle_sha256":"886fd97aa8255cad4cff1beb12df2023cce385546d4206c54253cbe99285f0a9"}}