{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IAGIXZORAE6ZQB24JPHAZBYZFS","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":"2398ba1104a5b83d93b853264ac72f9eaaf641d2a421535487d07e7a82cb47e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T10:53:07Z","title_canon_sha256":"7d6de7269917d27f7fb0bbcef690e1a497d815652cd962cffdc060e90bab047b"},"schema_version":"1.0","source":{"id":"2106.13552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13552","created_at":"2026-07-05T02:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13552v1","created_at":"2026-07-05T02:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13552","created_at":"2026-07-05T02:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"IAGIXZORAE6Z","created_at":"2026-07-05T02:52:23Z"},{"alias_kind":"pith_short_16","alias_value":"IAGIXZORAE6ZQB24","created_at":"2026-07-05T02:52:23Z"},{"alias_kind":"pith_short_8","alias_value":"IAGIXZOR","created_at":"2026-07-05T02:52:23Z"}],"graph_snapshots":[{"event_id":"sha256:6e579edae5be8e66206d84c464eedc145cda36fd0c8894a629f6f0e1cc02bc4b","target":"graph","created_at":"2026-07-05T02:52:23Z","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/2106.13552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal retrieval aims to enable flexible retrieval experience by combining multimedia data such as image, video, text, and audio. One core of unsupervised approaches is to dig the correlations among different object representations to complete satisfied retrieval performance without requiring expensive labels. In this paper, we propose a Graph Pattern Loss based Diversified Attention Network(GPLDAN) for unsupervised cross-modal retrieval to deeply analyze correlations among representations. First, we propose a diversified attention feature projector by considering the interaction between ","authors_text":"Rong Zhang, Xueying Chen, Yibing Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T10:53:07Z","title":"Graph Pattern Loss based Diversified Attention Network for Cross-Modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13552","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":"sha256:326c2c659e53240879cc4b1069d9f035587be0ddbeb215fae1c219bae729f583","target":"record","created_at":"2026-07-05T02:52:23Z","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":"2398ba1104a5b83d93b853264ac72f9eaaf641d2a421535487d07e7a82cb47e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T10:53:07Z","title_canon_sha256":"7d6de7269917d27f7fb0bbcef690e1a497d815652cd962cffdc060e90bab047b"},"schema_version":"1.0","source":{"id":"2106.13552","kind":"arxiv","version":1}},"canonical_sha256":"400c8be5d1013d98075c4bce0c87192c92fb8539c02ee40d6667a0685fc30700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"400c8be5d1013d98075c4bce0c87192c92fb8539c02ee40d6667a0685fc30700","first_computed_at":"2026-07-05T02:52:23.323272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:23.323272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eZfBS0CPH2RgQ4oKti9KfXm5ldJJK93ldtGoIVnhlul/tBbAb7d/oi7Rlsovd8LVfKZ7iB7FDwVDKaqVJWu0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:23.323671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:326c2c659e53240879cc4b1069d9f035587be0ddbeb215fae1c219bae729f583","sha256:6e579edae5be8e66206d84c464eedc145cda36fd0c8894a629f6f0e1cc02bc4b"],"state_sha256":"b1f48c888fd61d26d7e1c88d29538a6e9eb367c5adec43b507e4275633a28c12"}