{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5LCDNAOLL6HJPHZZUAIRHBO3AU","short_pith_number":"pith:5LCDNAOL","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"},"canonical_sha256":"eac43681cb5f8e979f39a0111385db05130cebfe0f63890a8fc6314cc89bc0ce","source":{"kind":"arxiv","id":"2409.01133","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01133","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01133v1","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01133","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"5LCDNAOLL6HJ","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"5LCDNAOLL6HJPHZZ","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"5LCDNAOL","created_at":"2026-07-05T09:01:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5LCDNAOLL6HJPHZZUAIRHBO3AU","target":"record","payload":{"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"},"canonical_sha256":"eac43681cb5f8e979f39a0111385db05130cebfe0f63890a8fc6314cc89bc0ce","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"},"source_kind":"arxiv","source_id":"2409.01133","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ycJxc2DVjoJjxqiF8GdfyLqLYYtIs0hzuQtuUod3p2Vot2Tba2aRmouUjTw7L25rSLeIQTtE7b8Dj3/Qu1ACCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:07:01.782973Z"},"content_sha256":"c1b7673a401dab03fdaa934f62468435f1fbe748c80ab64ec3ed8a3c7f962410","schema_version":"1.0","event_id":"sha256:c1b7673a401dab03fdaa934f62468435f1fbe748c80ab64ec3ed8a3c7f962410"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5LCDNAOLL6HJPHZZUAIRHBO3AU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7QmrW//FrMM0/LsSvnTjJhorFi1lPVIOoaqxJmA4tYjJVmXyNf29th8YoOQ3GoqW2lXriww+eKB54zQXn3nCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:07:01.783496Z"},"content_sha256":"46b9c823ad82ec87b585814e910a9d5454269cdd9f7382b22f9ade88cea7896f","schema_version":"1.0","event_id":"sha256:46b9c823ad82ec87b585814e910a9d5454269cdd9f7382b22f9ade88cea7896f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/bundle.json","state_url":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T14:07:01Z","links":{"resolver":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU","bundle":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/bundle.json","state":"https://pith.science/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LCDNAOLL6HJPHZZUAIRHBO3AU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5LCDNAOLL6HJPHZZUAIRHBO3AU","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":"c6075d1ed026da3c6be4ca1173adedc9ae73e1d72d89e1dfff6631f4c791e418","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-02T10:11:52Z","title_canon_sha256":"9906c7f82ac37bd86c6e558a0bd00a92ab435034cb0d1175d407b368ca85cb31"},"schema_version":"1.0","source":{"id":"2409.01133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01133","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01133v1","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01133","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"5LCDNAOLL6HJ","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"5LCDNAOLL6HJPHZZ","created_at":"2026-07-05T09:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"5LCDNAOL","created_at":"2026-07-05T09:01:59Z"}],"graph_snapshots":[{"event_id":"sha256:46b9c823ad82ec87b585814e910a9d5454269cdd9f7382b22f9ade88cea7896f","target":"graph","created_at":"2026-07-05T09:01:59Z","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/2409.01133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Tianzhao Wu, Zhongyi Xia","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-02T10:11:52Z","title":"Large Language Models Can Understanding Depth from Monocular Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01133","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:c1b7673a401dab03fdaa934f62468435f1fbe748c80ab64ec3ed8a3c7f962410","target":"record","created_at":"2026-07-05T09:01:59Z","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":"c6075d1ed026da3c6be4ca1173adedc9ae73e1d72d89e1dfff6631f4c791e418","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-02T10:11:52Z","title_canon_sha256":"9906c7f82ac37bd86c6e558a0bd00a92ab435034cb0d1175d407b368ca85cb31"},"schema_version":"1.0","source":{"id":"2409.01133","kind":"arxiv","version":1}},"canonical_sha256":"eac43681cb5f8e979f39a0111385db05130cebfe0f63890a8fc6314cc89bc0ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eac43681cb5f8e979f39a0111385db05130cebfe0f63890a8fc6314cc89bc0ce","first_computed_at":"2026-07-05T09:01:59.451194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:59.451194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hccsCL57nIg+iUUQiRWKmvSweDc3XQkUcF8XxccnLf1ncAezKphOTdQWmwA07E0cs0gvNG+BgPGuSyX0B18oDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:59.451664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1b7673a401dab03fdaa934f62468435f1fbe748c80ab64ec3ed8a3c7f962410","sha256:46b9c823ad82ec87b585814e910a9d5454269cdd9f7382b22f9ade88cea7896f"],"state_sha256":"48704263733d692383c8cb41eec1a675f89994b83c74320fb8fac58681d8a481"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGqhGpC/3nR/KjaAmLZIxZg1Y+YeJWi0zWsX584jM80JbtreLlRX+Eu5wyoo1P5grp1/frL7hNFzvth2hLhpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:07:01.787709Z","bundle_sha256":"09f0cf6b366002f9675f8b6f221ddc956898fbdf59e5a3f7d5a7daf19de294c1"}}