{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7EBE5S4EA7DVTORV5UTZJOVLE6","short_pith_number":"pith:7EBE5S4E","schema_version":"1.0","canonical_sha256":"f9024ecb8407c759ba35ed2794baab278f0688d63085f995ec433495988c917a","source":{"kind":"arxiv","id":"2502.16137","version":1},"attestation_state":"computed","paper":{"title":"Chain-of-Description: What I can understand, I can put into words","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Yuanchang Luo, Zongyao Li","submitted_at":"2025-02-22T08:27:31Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.16137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-22T08:27:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aec7f2201454e5d49c8b138e84102344187b0a656ea8e44b417042522492aadd","abstract_canon_sha256":"052d685a3290b7ad941e70519ae9fef956ff2715535581d31bdc61c6a4f06d4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:21.843630Z","signature_b64":"8XtHHVGg9kYbeMzAX8J2l8xyYX4flT0nWsR1H+YGNH3y7hlW9CBf/8sjUcRJeX33UTJW57l7x3oozx+s4KbxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9024ecb8407c759ba35ed2794baab278f0688d63085f995ec433495988c917a","last_reissued_at":"2026-07-05T10:18:21.843150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:21.843150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Description: What I can understand, I can put into words","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Yuanchang Luo, Zongyao Li","submitted_at":"2025-02-22T08:27:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16137","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.16137/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.16137","created_at":"2026-07-05T10:18:21.843208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16137v1","created_at":"2026-07-05T10:18:21.843208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16137","created_at":"2026-07-05T10:18:21.843208+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EBE5S4EA7DV","created_at":"2026-07-05T10:18:21.843208+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EBE5S4EA7DVTORV","created_at":"2026-07-05T10:18:21.843208+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EBE5S4E","created_at":"2026-07-05T10:18:21.843208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6","json":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6.json","graph_json":"https://pith.science/api/pith-number/7EBE5S4EA7DVTORV5UTZJOVLE6/graph.json","events_json":"https://pith.science/api/pith-number/7EBE5S4EA7DVTORV5UTZJOVLE6/events.json","paper":"https://pith.science/paper/7EBE5S4E"},"agent_actions":{"view_html":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6","download_json":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6.json","view_paper":"https://pith.science/paper/7EBE5S4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16137&json=true","fetch_graph":"https://pith.science/api/pith-number/7EBE5S4EA7DVTORV5UTZJOVLE6/graph.json","fetch_events":"https://pith.science/api/pith-number/7EBE5S4EA7DVTORV5UTZJOVLE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6/action/storage_attestation","attest_author":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6/action/author_attestation","sign_citation":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6/action/citation_signature","submit_replication":"https://pith.science/pith/7EBE5S4EA7DVTORV5UTZJOVLE6/action/replication_record"}},"created_at":"2026-07-05T10:18:21.843208+00:00","updated_at":"2026-07-05T10:18:21.843208+00:00"}