{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5LCDNAOLL6HJPHZZUAIRHBO3AU","short_pith_number":"pith:5LCDNAOL","schema_version":"1.0","canonical_sha256":"eac43681cb5f8e979f39a0111385db05130cebfe0f63890a8fc6314cc89bc0ce","source":{"kind":"arxiv","id":"2409.01133","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models Can Understanding Depth from Monocular Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Tianzhao Wu, Zhongyi Xia","submitted_at":"2024-09-02T10:11:52Z","abstract_excerpt":"Monocular depth estimation is a critical function in computer vision applications. This paper shows that large language models (LLMs) can effectively interpret depth with minimal supervision, using efficient resource utilization and a consistent neural network architecture. We introduce LLM-MDE, a multimodal framework that deciphers depth through language comprehension. Specifically, LLM-MDE employs two main strategies to enhance the pretrained LLM's capability for depth estimation: cross-modal reprogramming and an adaptive prompt estimation module. These strategies align vision representation"},"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":"2409.01133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-02T10:11:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9906c7f82ac37bd86c6e558a0bd00a92ab435034cb0d1175d407b368ca85cb31","abstract_canon_sha256":"c6075d1ed026da3c6be4ca1173adedc9ae73e1d72d89e1dfff6631f4c791e418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:59.451664Z","signature_b64":"hccsCL57nIg+iUUQiRWKmvSweDc3XQkUcF8XxccnLf1ncAezKphOTdQWmwA07E0cs0gvNG+BgPGuSyX0B18oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eac43681cb5f8e979f39a0111385db05130cebfe0f63890a8fc6314cc89bc0ce","last_reissued_at":"2026-07-05T09:01:59.451194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:59.451194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Can Understanding Depth from Monocular Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Tianzhao Wu, Zhongyi Xia","submitted_at":"2024-09-02T10:11:52Z","abstract_excerpt":"Monocular depth estimation is a critical function in computer vision applications. This paper shows that large language models (LLMs) can effectively interpret depth with minimal supervision, using efficient resource utilization and a consistent neural network architecture. We introduce LLM-MDE, a multimodal framework that deciphers depth through language comprehension. Specifically, LLM-MDE employs two main strategies to enhance the pretrained LLM's capability for depth estimation: cross-modal reprogramming and an adaptive prompt estimation module. These strategies align vision representation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01133","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/2409.01133/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":"2409.01133","created_at":"2026-07-05T09:01:59.451253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01133v1","created_at":"2026-07-05T09:01:59.451253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01133","created_at":"2026-07-05T09:01:59.451253+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LCDNAOLL6HJ","created_at":"2026-07-05T09:01:59.451253+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LCDNAOLL6HJPHZZ","created_at":"2026-07-05T09:01:59.451253+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LCDNAOL","created_at":"2026-07-05T09:01:59.451253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.09082","citing_title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU","json":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU.json","graph_json":"https://pith.science/api/pith-number/5LCDNAOLL6HJPHZZUAIRHBO3AU/graph.json","events_json":"https://pith.science/api/pith-number/5LCDNAOLL6HJPHZZUAIRHBO3AU/events.json","paper":"https://pith.science/paper/5LCDNAOL"},"agent_actions":{"view_html":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU","download_json":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU.json","view_paper":"https://pith.science/paper/5LCDNAOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01133&json=true","fetch_graph":"https://pith.science/api/pith-number/5LCDNAOLL6HJPHZZUAIRHBO3AU/graph.json","fetch_events":"https://pith.science/api/pith-number/5LCDNAOLL6HJPHZZUAIRHBO3AU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/action/storage_attestation","attest_author":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/action/author_attestation","sign_citation":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/action/citation_signature","submit_replication":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/action/replication_record"}},"created_at":"2026-07-05T09:01:59.451253+00:00","updated_at":"2026-07-05T09:01:59.451253+00:00"}