{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:26ZMP2T6I574VIMCQHWMW3AT24","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":"7bc7e4669a47ffb1dc3beefc81e15710c8cbeda6864d6533fc4727ce844b2163","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-09T15:01:12Z","title_canon_sha256":"f19ec871d73feadddce49e771b2b56dfda66d1f9f53ee2a366adcf582a85983d"},"schema_version":"1.0","source":{"id":"2303.05313","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.05313","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"2303.05313v2","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05313","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"26ZMP2T6I574","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"26ZMP2T6I574VIMC","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"26ZMP2T6","created_at":"2026-07-05T06:07:37Z"}],"graph_snapshots":[{"event_id":"sha256:00b4fe80587acce984d44a123f63d14c65ea56ec0c369c3a7ae69d90546b2b68","target":"graph","created_at":"2026-07-05T06:07:37Z","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/2303.05313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained supervision based on object annotations has been widely used for vision and language pre-training (VLP). However, in real-world application scenarios, aligned multi-modal data is usually in the image-caption format, which only provides coarse-grained supervision. It is not only cost-expensive but also compute-expensive to collect object annotations and build object annotation pre-extractor for different scenarios. In this paper, we propose a fine-grained VLP scheme without object annotations from the linguistic perspective. First, we propose a homonym sentence rewriting (HSR) algo","authors_text":"Lisai Zhang, Qingcai Chen, Yunpeng Han, Zhao Cao, Zhijian Chen, Zhonghua Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-09T15:01:12Z","title":"Refined Vision-Language Modeling for Fine-grained Multi-modal Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05313","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":"sha256:7840d4defaffc81de9c005dbca62fc70558a420392199d2728ee54ee5a251c04","target":"record","created_at":"2026-07-05T06:07:37Z","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":"7bc7e4669a47ffb1dc3beefc81e15710c8cbeda6864d6533fc4727ce844b2163","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-09T15:01:12Z","title_canon_sha256":"f19ec871d73feadddce49e771b2b56dfda66d1f9f53ee2a366adcf582a85983d"},"schema_version":"1.0","source":{"id":"2303.05313","kind":"arxiv","version":2}},"canonical_sha256":"d7b2c7ea7e477fcaa18281eccb6c13d719fcfa833cc389ff879383a6f5683261","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7b2c7ea7e477fcaa18281eccb6c13d719fcfa833cc389ff879383a6f5683261","first_computed_at":"2026-07-05T06:07:37.663027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:37.663027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"82VymKdRazgdvCxffA/5ytS1Ze64Yo7L6Gh3X/8dUj8M1gurMr+ob/PbZGFDXYwhWCXjS7GbSkXGEvvCHWkuBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:37.663567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.05313","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7840d4defaffc81de9c005dbca62fc70558a420392199d2728ee54ee5a251c04","sha256:00b4fe80587acce984d44a123f63d14c65ea56ec0c369c3a7ae69d90546b2b68"],"state_sha256":"dd9cef859b4dd09d1b232066056e36583b7e9926506a8ec3ce37564521d2c6fe"}