{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:37HXZ36EMX235Y26Z7JFTNDQVZ","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":"58792f682b8df5561de3dad89edb0f71c041cb55681c68f22a0b710b0d78e1ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T02:19:35Z","title_canon_sha256":"501d10556c83d3585b3e11ac7720d64dc3a83cc04dd29897c7bf31a7247e1198"},"schema_version":"1.0","source":{"id":"2312.02433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02433","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02433v1","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02433","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"37HXZ36EMX23","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"37HXZ36EMX235Y26","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"37HXZ36E","created_at":"2026-07-05T07:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:5e6b7fd23a96619db3769e81a33e6a1ec09617585ed31bcda722284dc85d05d2","target":"graph","created_at":"2026-07-05T07:20:17Z","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/2312.02433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the fast-paced development of multimodal large language models (MLLMs), we can now converse with AI systems in natural languages to understand images. However, the reasoning power and world knowledge embedded in the large language models have been much less investigated and exploited for image perception tasks. In this paper, we propose Lenna, a language-enhanced reasoning detection assistant, which utilizes the robust multimodal feature representation of MLLMs, while preserving location information for detection. This is achieved by incorporating an additional <DET> token in the MLLM voc","authors_text":"Ailing Zhang, Bo Zhang, Fei Wei, Xiangxiang Chu, Xinyu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T02:19:35Z","title":"Lenna: Language Enhanced Reasoning Detection Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02433","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":"sha256:0fa7341d6263f5ccab28b8ef796647b405a7b2a07f4550fea8d802aec217b57d","target":"record","created_at":"2026-07-05T07:20:17Z","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":"58792f682b8df5561de3dad89edb0f71c041cb55681c68f22a0b710b0d78e1ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T02:19:35Z","title_canon_sha256":"501d10556c83d3585b3e11ac7720d64dc3a83cc04dd29897c7bf31a7247e1198"},"schema_version":"1.0","source":{"id":"2312.02433","kind":"arxiv","version":1}},"canonical_sha256":"dfcf7cefc465f5bee35ecfd259b470ae4eaf7756212dfc668abdc8d40cec146e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfcf7cefc465f5bee35ecfd259b470ae4eaf7756212dfc668abdc8d40cec146e","first_computed_at":"2026-07-05T07:20:17.973493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:17.973493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ECZcto2Un606q8OFHHG5xHk3211nqnDb/pf/QWNsF2s1BuvNebvGeuRXDSvsU0bkVfxHx3tkxWciz/O9gnF4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:17.974026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fa7341d6263f5ccab28b8ef796647b405a7b2a07f4550fea8d802aec217b57d","sha256:5e6b7fd23a96619db3769e81a33e6a1ec09617585ed31bcda722284dc85d05d2"],"state_sha256":"44dee32817d40c3a125030c08db71293215442d836c3f36eb669177d542c83ed"}