{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2EA3LLGUJDXD4FQFKGVR72B25O","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":"5f24329df9c2973e2eef7ccc0e2c905ca1942950ad8b7abb329a691be7f5f78d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T06:54:33Z","title_canon_sha256":"7fce3010e3ce1f070c2aa0b01fbb9a71eeeb181de7b3b9a021f25892b7ed272b"},"schema_version":"1.0","source":{"id":"2403.12488","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12488","created_at":"2026-07-05T08:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12488v3","created_at":"2026-07-05T08:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12488","created_at":"2026-07-05T08:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"2EA3LLGUJDXD","created_at":"2026-07-05T08:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"2EA3LLGUJDXD4FQF","created_at":"2026-07-05T08:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"2EA3LLGU","created_at":"2026-07-05T08:47:16Z"}],"graph_snapshots":[{"event_id":"sha256:e9f7a5983e2ae4827574f681fbe86de9bb9b7bbea6e1b5f4e30452527d64611b","target":"graph","created_at":"2026-07-05T08:47:16Z","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/2403.12488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini. Our approach consists of a detection prompting toolkit inspired by high-precision detection priors and a new Chain-of-Thought to implement these prompts. Specifically, the prompts in the toolkit are designed to guide the MLLM to focus on regional information (e.g., zooming in), read coordinates according to measure standards (e.g., overlaying rulers and compasses), and infer from the contextual information (e.g., overlayi","authors_text":"Jian Wu, Philip Torr, Shixiang Tang, Tong He, Wanli Ouyang, Wenhao Wu, Yixuan Wu, Yizhou Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T06:54:33Z","title":"DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12488","kind":"arxiv","version":3},"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":"sha256:8565885f105baac2abc1c2f9dd66572d369d2c5a11e69d3a3069b87a579b1122","target":"record","created_at":"2026-07-05T08:47:16Z","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":"5f24329df9c2973e2eef7ccc0e2c905ca1942950ad8b7abb329a691be7f5f78d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T06:54:33Z","title_canon_sha256":"7fce3010e3ce1f070c2aa0b01fbb9a71eeeb181de7b3b9a021f25892b7ed272b"},"schema_version":"1.0","source":{"id":"2403.12488","kind":"arxiv","version":3}},"canonical_sha256":"d101b5acd448ee3e160551ab1fe83aeb8f060530460ba4dabe73a7ad13aec646","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d101b5acd448ee3e160551ab1fe83aeb8f060530460ba4dabe73a7ad13aec646","first_computed_at":"2026-07-05T08:47:16.838938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:16.838938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnLIAMYl2NxmKwXCTdTgCwepiOY3gO1NDS8JkYVZPXhjKH16p6CwUp3h4tRzcdFplt9PmboccEllTbvU/QEQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:16.839463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12488","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8565885f105baac2abc1c2f9dd66572d369d2c5a11e69d3a3069b87a579b1122","sha256:e9f7a5983e2ae4827574f681fbe86de9bb9b7bbea6e1b5f4e30452527d64611b"],"state_sha256":"199e97db56740b82b3883fbd7b8b17a37239b6606ea2765ac838fe3f61d55d1f"}