{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RVO3LE7NEOQTVMT3B3KDBOVQWE","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":"28922df98f806e490632332a7e468fdc639630f8be2a1762ef41b47e07c8eaa0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T09:02:45Z","title_canon_sha256":"39be7ad59baa5d6c10a9c111f69f2edfb2fdafdbe6ef4d2df2334e6874352693"},"schema_version":"1.0","source":{"id":"2312.05278","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05278","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05278v2","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05278","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"RVO3LE7NEOQT","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_16","alias_value":"RVO3LE7NEOQTVMT3","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_8","alias_value":"RVO3LE7N","created_at":"2026-07-05T08:07:12Z"}],"graph_snapshots":[{"event_id":"sha256:871abb2b900fc0b2e1a079ef501074b04d712910ab49f0543a7595b07fa5648b","target":"graph","created_at":"2026-07-05T08:07:12Z","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/2312.05278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the details of images, leading to irreparable visual hallucinations and factual errors. In this paper, we propose Lyrics, a novel multi-modal pre-training and instruction fine-tuning paradigm that bootstraps vision-language alignment from fine-grained cross-modal collaboration. Building on the foundation of BLIP-2, Lyrics infuses local visual features extracted fr","authors_text":"Bingyi Jing, Cong Lin, Dixiang Zhang, Jiaxing Zhang, Junyu Lu, Pingjian Zhang, Songxin Zhang, Zejian Xie, Zhuoyang Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T09:02:45Z","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05278","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:fb91eee63a41ea636de684d0ccc8650815522e147ef42022ad00c3499b2eac90","target":"record","created_at":"2026-07-05T08:07:12Z","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":"28922df98f806e490632332a7e468fdc639630f8be2a1762ef41b47e07c8eaa0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T09:02:45Z","title_canon_sha256":"39be7ad59baa5d6c10a9c111f69f2edfb2fdafdbe6ef4d2df2334e6874352693"},"schema_version":"1.0","source":{"id":"2312.05278","kind":"arxiv","version":2}},"canonical_sha256":"8d5db593ed23a13ab27b0ed430bab0b11444ef027b1e09988060f3280c5e1507","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d5db593ed23a13ab27b0ed430bab0b11444ef027b1e09988060f3280c5e1507","first_computed_at":"2026-07-05T08:07:12.383577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:12.383577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2AeH7+m75NM3TneBYIqYMap2kyoiqirQelDWYcSxU6uhdNN2aN2n5tpDSzzQ5/ShMsthWms75Amg47iipSI8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:12.383989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.05278","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb91eee63a41ea636de684d0ccc8650815522e147ef42022ad00c3499b2eac90","sha256:871abb2b900fc0b2e1a079ef501074b04d712910ab49f0543a7595b07fa5648b"],"state_sha256":"63f1a6530e4b296a52e07601bab9a99d729cbaf4aeecf4ec3e36864647242ec7"}