{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7EBE5S4EA7DVTORV5UTZJOVLE6","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":"052d685a3290b7ad941e70519ae9fef956ff2715535581d31bdc61c6a4f06d4b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-22T08:27:31Z","title_canon_sha256":"aec7f2201454e5d49c8b138e84102344187b0a656ea8e44b417042522492aadd"},"schema_version":"1.0","source":{"id":"2502.16137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16137","created_at":"2026-07-05T10:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16137v1","created_at":"2026-07-05T10:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16137","created_at":"2026-07-05T10:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"7EBE5S4EA7DV","created_at":"2026-07-05T10:18:21Z"},{"alias_kind":"pith_short_16","alias_value":"7EBE5S4EA7DVTORV","created_at":"2026-07-05T10:18:21Z"},{"alias_kind":"pith_short_8","alias_value":"7EBE5S4E","created_at":"2026-07-05T10:18:21Z"}],"graph_snapshots":[{"event_id":"sha256:22763fcacaf2409eeadef2edd9c37c045a97871f6a3686a70a5ef76a73a81066","target":"graph","created_at":"2026-07-05T10:18:21Z","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/2502.16137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel strategy defined as Chain-of-Description (CoD) Prompting, tailored for Multi-Modal Large Language Models. This approach involves having the model first provide a detailed description of the multi-modal input before generating an answer to the question. When applied to models such as Qwen2-Audio, Qwen2-VL, and Qwen2.5-VL, CoD Prompting significantly enhances performance compared to standard prompting methods. This is demonstrated by nearly a 4\\% improvement in the speech category of the audio benchmark AIR-Bench-Chat and a 5.3\\% improvement in the hard-level po","authors_text":"Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Yuanchang Luo, Zongyao Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-22T08:27:31Z","title":"Chain-of-Description: What I can understand, I can put into words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16137","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:af8597ea9f64dfa2eb287541ab67760132ab5bd9ab1bf530b9af0c7345031985","target":"record","created_at":"2026-07-05T10:18:21Z","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":"052d685a3290b7ad941e70519ae9fef956ff2715535581d31bdc61c6a4f06d4b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-22T08:27:31Z","title_canon_sha256":"aec7f2201454e5d49c8b138e84102344187b0a656ea8e44b417042522492aadd"},"schema_version":"1.0","source":{"id":"2502.16137","kind":"arxiv","version":1}},"canonical_sha256":"f9024ecb8407c759ba35ed2794baab278f0688d63085f995ec433495988c917a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9024ecb8407c759ba35ed2794baab278f0688d63085f995ec433495988c917a","first_computed_at":"2026-07-05T10:18:21.843150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:21.843150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8XtHHVGg9kYbeMzAX8J2l8xyYX4flT0nWsR1H+YGNH3y7hlW9CBf/8sjUcRJeX33UTJW57l7x3oozx+s4KbxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:21.843630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.16137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af8597ea9f64dfa2eb287541ab67760132ab5bd9ab1bf530b9af0c7345031985","sha256:22763fcacaf2409eeadef2edd9c37c045a97871f6a3686a70a5ef76a73a81066"],"state_sha256":"9f306ff7831bb83f45327e447710974ccc5b0677ced7441b8e5b18e96d612b20"}