{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OKPHR3GG2TSZHIJA7ORHU2OSH3","short_pith_number":"pith:OKPHR3GG","schema_version":"1.0","canonical_sha256":"729e78ecc6d4e593a120fba27a69d23ec3a1629b88e65bb244b4b055e3423796","source":{"kind":"arxiv","id":"2305.13267","version":1},"attestation_state":"computed","paper":{"title":"Enhance Reasoning Ability of Visual-Language Models via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wenjuan Han, Xintong Zhang, Yueting Yang","submitted_at":"2023-05-22T17:33:44Z","abstract_excerpt":"Pre-trained visual language models (VLM) have shown excellent performance in image caption tasks. However, it sometimes shows insufficient reasoning ability. In contrast, large language models (LLMs) emerge with powerful reasoning capabilities. Therefore, we propose a method called TReE, which transfers the reasoning ability of a large language model to a visual language model in zero-shot scenarios. TReE contains three stages: observation, thinking, and re-thinking. Observation stage indicates that VLM obtains the overall information of the relative image. Thinking stage combines the image in"},"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":"2305.13267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T17:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"248237524a3228f38b4bb10482ad3b47ccd166f6519215abe45e97176a5797a8","abstract_canon_sha256":"189881eafb69eb2c7c4c39d68dcad2ab35ea69fc52e360d31b70a8e05ea57639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:28.480954Z","signature_b64":"vfV9lBbBUhYl7+T66BJ9ZthYHJ1e0HeBNs3KX+lboGL599dFFxa5bS/tkUG64+bH+TOGG9moK9MTPkobB/YvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"729e78ecc6d4e593a120fba27a69d23ec3a1629b88e65bb244b4b055e3423796","last_reissued_at":"2026-07-05T06:12:28.480526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:28.480526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhance Reasoning Ability of Visual-Language Models via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wenjuan Han, Xintong Zhang, Yueting Yang","submitted_at":"2023-05-22T17:33:44Z","abstract_excerpt":"Pre-trained visual language models (VLM) have shown excellent performance in image caption tasks. However, it sometimes shows insufficient reasoning ability. In contrast, large language models (LLMs) emerge with powerful reasoning capabilities. Therefore, we propose a method called TReE, which transfers the reasoning ability of a large language model to a visual language model in zero-shot scenarios. TReE contains three stages: observation, thinking, and re-thinking. Observation stage indicates that VLM obtains the overall information of the relative image. Thinking stage combines the image in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13267","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/2305.13267/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":"2305.13267","created_at":"2026-07-05T06:12:28.480580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13267v1","created_at":"2026-07-05T06:12:28.480580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13267","created_at":"2026-07-05T06:12:28.480580+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKPHR3GG2TSZ","created_at":"2026-07-05T06:12:28.480580+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKPHR3GG2TSZHIJA","created_at":"2026-07-05T06:12:28.480580+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKPHR3GG","created_at":"2026-07-05T06:12:28.480580+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/OKPHR3GG2TSZHIJA7ORHU2OSH3","json":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3.json","graph_json":"https://pith.science/api/pith-number/OKPHR3GG2TSZHIJA7ORHU2OSH3/graph.json","events_json":"https://pith.science/api/pith-number/OKPHR3GG2TSZHIJA7ORHU2OSH3/events.json","paper":"https://pith.science/paper/OKPHR3GG"},"agent_actions":{"view_html":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3","download_json":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3.json","view_paper":"https://pith.science/paper/OKPHR3GG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13267&json=true","fetch_graph":"https://pith.science/api/pith-number/OKPHR3GG2TSZHIJA7ORHU2OSH3/graph.json","fetch_events":"https://pith.science/api/pith-number/OKPHR3GG2TSZHIJA7ORHU2OSH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/action/storage_attestation","attest_author":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/action/author_attestation","sign_citation":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/action/citation_signature","submit_replication":"https://pith.science/pith/OKPHR3GG2TSZHIJA7ORHU2OSH3/action/replication_record"}},"created_at":"2026-07-05T06:12:28.480580+00:00","updated_at":"2026-07-05T06:12:28.480580+00:00"}