{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C442GH7XPOQZHUWPI6U3VJXSNL","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":"42999fca9996d442ccc7d11462dae18441f9d8a8e3bbf437adb487b42847a51b","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T13:09:57Z","title_canon_sha256":"a2ad6948ce7b61d3e998ebee45e81de2201150a4fc2e6aa69fbf8148f773a433"},"schema_version":"1.0","source":{"id":"2308.01126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01126","created_at":"2026-07-05T06:37:05Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01126v1","created_at":"2026-07-05T06:37:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01126","created_at":"2026-07-05T06:37:05Z"},{"alias_kind":"pith_short_12","alias_value":"C442GH7XPOQZ","created_at":"2026-07-05T06:37:05Z"},{"alias_kind":"pith_short_16","alias_value":"C442GH7XPOQZHUWP","created_at":"2026-07-05T06:37:05Z"},{"alias_kind":"pith_short_8","alias_value":"C442GH7X","created_at":"2026-07-05T06:37:05Z"}],"graph_snapshots":[{"event_id":"sha256:44d1ca7383db169be3aa44e43a8110caa99533215d68689fe29e4e1fc98d62b1","target":"graph","created_at":"2026-07-05T06:37:05Z","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/2308.01126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current captioning approaches tend to generate correct but \"generic\" descriptions that lack real-world knowledge, e.g., named entities and contextual information. Considering that Vision-Language Pre-Training (VLP) models master massive such knowledge from large-scale web-harvested data, it is promising to utilize the generalizability of VLP models to incorporate knowledge into image descriptions. However, using VLP models faces challenges: zero-shot inference suffers from knowledge hallucination that leads to low-quality descriptions, but the generic bias in downstream task fine-tuning hinder","authors_text":"Jianbing Zhang, Kanzhi Cheng, Wenhao Zhu, Wenpo Song, Zheng Ma, Zixuan Zhu","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T13:09:57Z","title":"Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01126","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:a6d1e7800756400a2b75a04a5271c2e2e92d817934b54efe3e32960186ffd20f","target":"record","created_at":"2026-07-05T06:37:05Z","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":"42999fca9996d442ccc7d11462dae18441f9d8a8e3bbf437adb487b42847a51b","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T13:09:57Z","title_canon_sha256":"a2ad6948ce7b61d3e998ebee45e81de2201150a4fc2e6aa69fbf8148f773a433"},"schema_version":"1.0","source":{"id":"2308.01126","kind":"arxiv","version":1}},"canonical_sha256":"1739a31ff77ba193d2cf47a9baa6f26ad3d661c9cb6583e96b5e065e942e5aff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1739a31ff77ba193d2cf47a9baa6f26ad3d661c9cb6583e96b5e065e942e5aff","first_computed_at":"2026-07-05T06:37:05.744054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:05.744054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dA82hdVzAeNNbS4BG5yNdZDfgJfYxl+uFuh58oDtciErJeDKIipo+tsK1NB8PJ2yoeVJXzATB1ZjqCOAdUzeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:05.744484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6d1e7800756400a2b75a04a5271c2e2e92d817934b54efe3e32960186ffd20f","sha256:44d1ca7383db169be3aa44e43a8110caa99533215d68689fe29e4e1fc98d62b1"],"state_sha256":"10709c42c5990999618c46c268cd63b8fbd10b4c59922f943c960d26c8743ded"}