{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RACKPEIMBYPDDSDFE3AULU7JYR","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":"654e784c99ad8795ebc2c9d2a36ec3d86db6403f4a39553df1524cec4a72e992","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-27T05:45:54Z","title_canon_sha256":"c69549bdf621ee9c9cafd963a5235786daaede91385bdc3a12df4f9878fa7a0f"},"schema_version":"1.0","source":{"id":"2308.14009","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14009","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14009v1","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14009","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"RACKPEIMBYPD","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"pith_short_16","alias_value":"RACKPEIMBYPDDSDF","created_at":"2026-07-05T06:45:20Z"},{"alias_kind":"pith_short_8","alias_value":"RACKPEIM","created_at":"2026-07-05T06:45:20Z"}],"graph_snapshots":[{"event_id":"sha256:a0c750fa4492dc93184cc53a0519003dc2d5003f2f06ff453c15823f2ec34191","target":"graph","created_at":"2026-07-05T06:45:20Z","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/2308.14009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-text retrieval requires the system to bridge the heterogenous gap between vision and language for accurate retrieval while keeping the network lightweight-enough for efficient retrieval. Existing trade-off solutions mainly study from the view of incorporating cross-modal interactions with the independent-embedding framework or leveraging stronger pretrained encoders, which still demand time-consuming similarity measurement or heavyweight model structure in the retrieval stage. In this work, we propose an image-text alignment module SelfAlign on top of the independent-embedding framework,","authors_text":"Jiamin Zhuang, Jing Yu, Xiangyan Qu, Yang Ding, Yue Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-27T05:45:54Z","title":"Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14009","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":"sha256:5ea1cdce3d0b6440844d5ad6b021115facaa7a89c428c5b25f5a99eeeb32cb9e","target":"record","created_at":"2026-07-05T06:45:20Z","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":"654e784c99ad8795ebc2c9d2a36ec3d86db6403f4a39553df1524cec4a72e992","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-27T05:45:54Z","title_canon_sha256":"c69549bdf621ee9c9cafd963a5235786daaede91385bdc3a12df4f9878fa7a0f"},"schema_version":"1.0","source":{"id":"2308.14009","kind":"arxiv","version":1}},"canonical_sha256":"8804a7910c0e1e31c86526c145d3e9c46e097273915203167a85d6b1c07621e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8804a7910c0e1e31c86526c145d3e9c46e097273915203167a85d6b1c07621e8","first_computed_at":"2026-07-05T06:45:20.528861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:20.528861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XKE2H6MiwOuNzSLrsspzUDBgno6kGCN3XVwD0Lumkq0+K4RBWR9tQRVk4BNdj4QESyeZJCM5VJ9G7wwyKtunAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:20.529283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.14009","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ea1cdce3d0b6440844d5ad6b021115facaa7a89c428c5b25f5a99eeeb32cb9e","sha256:a0c750fa4492dc93184cc53a0519003dc2d5003f2f06ff453c15823f2ec34191"],"state_sha256":"d750fbc5b217f6fcdbe785ce5896920dade61fffd63027fba3bb63ba1a4c5148"}