{"as_of":"2026-08-12T03:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4ce00d620e2c355aac9772ed286584629bc80b917cd126a94b0c662459630e20","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T23:34:15.094294Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.20162/citation-record","integrity":"/paper/2412.20162/integrity","json":"/paper/2412.20162/citation-record.json","paper":"/paper/2412.20162"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.717330Z","title":"Ro- bodepth: Robust out-of-distribution depth estimation under corruptions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.717330Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:10ecaa56a9717122bf517f249f5223a428fa45cfd93905dbc9d2553252c45950","observation_id":"b72cacbb-da17-4500-b114-05f4a8635f22","resolution":{"observed_at":"2026-08-10T23:34:14.717330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.461654Z","title":"Adabins: Depth estimation using adaptive bins,","venue":null,"work_id":"f7ad54aa-02c4-4ad6-8938-7a76444c8fd1","year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.734904Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:5a5a4f86c766f3536027717d1f0a24241349f07b66d1f832b290422dec557859","observation_id":"f5efef85-ea16-449c-9267-d317068f4ebb","resolution":{"observed_at":"2026-08-10T23:34:16.472377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.438597Z","title":"Transformer-based attention networks for continuous pixel-wise prediction,","venue":null,"work_id":"1ea210c2-c6a6-4392-b869-ff4523470362","year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.743861Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:a90ee07e8512d545fda408bf96c21df48c2ab0e0cf99d18a3398e74b6f2715bd","observation_id":"8fb6628a-fb02-4813-8c43-1df22e4c8a4d","resolution":{"observed_at":"2026-08-10T23:34:16.445063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08548","last_updated":"2023-12-13T22:20:45Z","snapshot_observed_at":"2026-07-06T17:01:21.970309Z","submitted_at":"2023-12-13T22:20:45Z","title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08548","snapshot_observed_at":"2026-08-10T23:34:14.756233Z","title":"Evp: Enhanced visual perception using inverse multi-attentive feature refinement and regularized image-text alignment,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.756233Z"},"links":{"cited_paper":"/paper/2312.08548","citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:3cd289f8f7c2bb453ca6bd7f16587e940076dae0ba647063d453dc3e44cfda8c","observation_id":"9722d67f-2932-4921-9802-ef447c0bae3b","resolution":{"observed_at":"2026-08-10T23:34:14.756233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.769891Z","title":"Repurposing diffusion-based image generators for monoc- ular depth estimation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.769891Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:4a049a7ced8f13ef93aef0ca91c4fd77588d6a1051d292a53e11d6cf03308e07","observation_id":"d018e618-4610-48ce-bf85-3f4ac1534f15","resolution":{"observed_at":"2026-08-10T23:34:14.769891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.388426Z","title":"Planning-oriented autonomous driving,","venue":null,"work_id":"91a4b672-ccd2-4868-8e12-88e96e70003c","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.778252Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:3fb741645bc1d6b63e89f419e83509b3206aa2f4523a36518f73fb397895e87d","observation_id":"9e873ee9-8f48-499f-9ec5-b5c730d07a11","resolution":{"observed_at":"2026-08-10T23:34:16.394194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.794420Z","title":"Robust monocular depth estimation under challenging conditions,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.794420Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:bdd906b9fef24d4096c0f815a2134362e9d355c41d0d4858bff8f30d3c0927a6","observation_id":"c8100ab4-97da-46ca-8a73-1513d3e98d44","resolution":{"observed_at":"2026-08-10T23:34:14.794420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.352564Z","title":"Diffusion models for monoc- ular depth estimation: Overcoming challenging conditions,","venue":null,"work_id":"e1f9d929-ce1d-4e77-b91f-dcb33750defc","year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.801308Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:b8a19a285c630b998908884fa0515551851fb748e387bcb26df5186f90298e7e","observation_id":"f1dca447-93da-456a-8a38-015492580445","resolution":{"observed_at":"2026-08-10T23:34:16.359819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.807073Z","title":"R4dyn: Exploring radar for self-supervised monocular depth estimation of dynamic scenes,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.807073Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:77de6d4246e8b2d57df808f445faa1bbc973246f9c9cc7f71cb3290d96690e50","observation_id":"e0997fd2-4546-4ed9-9a31-b7d8ac0a2184","resolution":{"observed_at":"2026-08-10T23:34:14.807073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.290218Z","title":"Defeat-net: General monocular depth via simultaneous unsupervised representation learning,","venue":null,"work_id":"7fc39e6a-67be-4a5f-a23a-9542e7a5e667","year":2020},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.812566Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:5ccb6628a6b2a7f611dfe6e7139791c925dfabdda9bc2e90eff4a6453e1274e0","observation_id":"ae17f7ba-aafd-4253-bc7c-8558a7f32297","resolution":{"observed_at":"2026-08-10T23:34:16.300492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.223582Z","title":"Clip the gap: A single domain generalization approach for object detection,","venue":null,"work_id":"92a9f285-490c-45a2-b395-79dd9921e769","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.832500Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:a3f4200a8086b1929758a531d92bd4a1e6aeb17bb808dd2ea2d6a6edbf83aa0a","observation_id":"324f4471-c181-45ba-b19d-009260e02808","resolution":{"observed_at":"2026-08-10T23:34:16.230968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-10T23:34:14.842943Z","title":"Lora: Low-rank adaptation of large language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.842943Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:6a6b7c3c2d8d29496ea647d24c7467e7850199c57eae6709e6b6d0ae0d833ef8","observation_id":"a37e5c07-83a7-4f35-acc5-115dbc44e205","resolution":{"observed_at":"2026-08-10T23:34:14.842943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.198731Z","title":"Sqldepth: Generalizable self-supervised fine-structured monocular depth estimation,","venue":null,"work_id":"f102fa80-96b3-4c30-b915-e45a4553f9b4","year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.856553Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:7748e17047e18c36ce76355db1872e374ac6f05ee93891dc7cc68ca47958884c","observation_id":"8d9006d1-d8e3-422b-a51b-0956eaafe142","resolution":{"observed_at":"2026-08-10T23:34:16.204750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.174632Z","title":"Towards zero-shot scale-aware monocular depth estimation,","venue":null,"work_id":"097ae677-0f8c-40b3-91dc-77a747c0478e","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.862558Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:8693357e3ae4be85db1a9bd0a5442435022fb0821f13e271ddf87acbdcb85936","observation_id":"df3d9cd2-302d-4590-b056-18874dce7048","resolution":{"observed_at":"2026-08-10T23:34:16.183638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12288","last_updated":"2023-02-23T19:13:10Z","snapshot_observed_at":"2026-07-06T14:55:15.719380Z","submitted_at":"2023-02-23T19:13:10Z","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12288","snapshot_observed_at":"2026-08-10T23:34:14.870493Z","title":"Zoedepth: Zero-shot transfer by combining relative and metric depth,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.870493Z"},"links":{"cited_paper":"/paper/2302.12288","citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:c99ad4c4764da2d2782b959e8874a67bceebbf096a1da5f423bd74e712685114","observation_id":"f081494a-10d9-4986-972f-5ffa2fb9d3ce","resolution":{"observed_at":"2026-08-10T23:34:14.870493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.877506Z","title":"Depth anything: Unleashing the power of large-scale unlabeled data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.877506Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:ec5d67a366fca46edf4a9cd88f72bfaf125a582086dea3ef256d9857b28f423b","observation_id":"d5be21fb-8058-4ed5-b56e-297e0d3a98f4","resolution":{"observed_at":"2026-08-10T23:34:14.877506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.129707Z","title":"Forkgan: Seeing into the rainy night,","venue":null,"work_id":"609b4732-ab42-4896-98b4-642988ce0a13","year":2020},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.884826Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:d71972de5b34c9bda0c56fa1ba40fb19e7d79010f5918901db19b502da0ede47","observation_id":"a48d22c4-7235-4c20-b7f8-924a22e0f245","resolution":{"observed_at":"2026-08-10T23:34:16.140046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.086142Z","title":"Single domain generalization for lidar semantic segmentation,","venue":null,"work_id":"52371b8f-919d-42ba-84d9-b4d90b324bab","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.893621Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:e9d3f8db2b6d7be9883749ce092ae918c9180d337733272dbf73429618b7d07f","observation_id":"43d43d31-d1dd-4e75-9372-b6d8b33ac107","resolution":{"observed_at":"2026-08-10T23:34:16.104112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.040979Z","title":"Turning a clip model into a scene text spotter,","venue":null,"work_id":"600a39a0-f87e-4851-9825-8c31f41b08af","year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.900909Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:bab952c648d6e6cf1c0998da9cb9cec9651a8a5f049a37a913598520e0da4cf3","observation_id":"5cdcebf6-be5e-460b-9f31-2b1175cae0ba","resolution":{"observed_at":"2026-08-10T23:34:16.056474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.006179Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"f70be98e-e689-4826-9e01-c0d2b618767a","year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.907891Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:e8b4925ef7c55a6c7dc384462ac146a710bb534b993e352f52b9d1c92a594fff","observation_id":"db8946ac-7ab9-4003-97d1-f23cdb0f27f0","resolution":{"observed_at":"2026-08-10T23:34:16.017466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.968052Z","title":"T2vlad: global-local sequence alignment for text-video retrieval,","venue":null,"work_id":"925baf12-dcf2-45c9-9310-7abf8030b4c1","year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.913179Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:c3e92cc0a28e9aa79ba05af96ac61e322b33979d85ebe84c78d6cc9e1f469fc8","observation_id":"0b788cfc-8d5b-460c-b13c-701b08f9250c","resolution":{"observed_at":"2026-08-10T23:34:15.979410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.922258Z","title":"What you see is what you read? improv- ing text-image alignment evaluation,","venue":null,"work_id":"3d0c021e-c54b-49f2-8fa9-96c3456e4cef","year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.920712Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:564819d229ea04c4b10b6585f51b05f81ead8e0056b33c4d19ac2f6f0f1b3e63","observation_id":"15b3f287-bbf3-49f4-9891-a64d46e10db3","resolution":{"observed_at":"2026-08-10T23:34:15.937099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.891242Z","title":"Clip-vip: Adapting pre-trained image-text model to video-language alignment,","venue":null,"work_id":"4af289b6-ba0f-4790-9ae7-7134bf32e5b5","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.928532Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:71a00f5da01847a4f167d17402d32229a06c07ede6755987ab756544deea7a28","observation_id":"e3524d3e-ebe8-438a-a284-0b9c36bec255","resolution":{"observed_at":"2026-08-10T23:34:15.897068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.934753Z","title":"Unleashing text-to-image diffusion models for visual perception,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.934753Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:85cae9f566ed50db5736dee16abe65c6c43120427c6d123ceec3e837b6106927","observation_id":"64020a63-df0d-4fc6-9c08-b7b37adb167b","resolution":{"observed_at":"2026-08-10T23:34:14.934753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-10T23:34:14.941321Z","title":"Hierarchical text-conditional image generation with clip latents,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.941321Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:964a7eb97fd8024573653cb324374ee30fa699d47bb213bed1b391a887df9116","observation_id":"7ecda788-eab2-4c6a-bf70-7417b7af1682","resolution":{"observed_at":"2026-08-10T23:34:14.941321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.831570Z","title":"Self-supervised monocular depth estimation for all day images using domain separation","venue":null,"work_id":"4d91d55c-b934-4c7f-a503-b35c2655352a","year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.951932Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:707f806066da9214de7a6d038644ecc42d51a9de0ac3ea122ed95c840097639d","observation_id":"278f7b62-2565-4c44-8307-12c572ff79f7","resolution":{"observed_at":"2026-08-10T23:34:15.847274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.799814Z","title":"Learning depth estimation for transparent and mirror surfaces,","venue":null,"work_id":"68bee77f-50db-483a-9624-062a0f3ffaff","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.968171Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:69a447adb7c3848d3bca8c55bb1d2f437f9b6fff791202968d30874579d99e59","observation_id":"c394d7b7-0329-4aff-8301-f71a9d684e5b","resolution":{"observed_at":"2026-08-10T23:34:15.811921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.743506Z","title":"Regularizing nighttime weirdness: Efficient self-supervised monocular depth estimation in the dark,","venue":null,"work_id":"f4a5f45b-5c22-4e57-9bb2-759348d1d641","year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.976131Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:138abf051d49be25f6737bb6675ac85bab16790a247737c7aab70077a833d2cc","observation_id":"af8e51d2-4b39-40f6-8b62-0c988e4b2b32","resolution":{"observed_at":"2026-08-10T23:34:15.761405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:16.257666Z","title":"Self-supervised monocular depth estimation: Let’s talk about the weather,","venue":null,"work_id":"55ac9585-dfc9-46a6-984a-a529abcfd27c","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.983559Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:e94da6c93b8d47eff4ce367a28677624efe56554d3352af1dee084fcbf5ba1fb","observation_id":"98fcb1fe-6385-47f3-93d6-ee91e53c2b2c","resolution":{"observed_at":"2026-08-10T23:34:16.269163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.990303Z","title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross- dataset transfer,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.990303Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:c787395bc5cca4d255642275a2df5a76e05c7177706f14243b5826b22e3509cb","observation_id":"a0f566d6-77f2-46e7-828c-29f92c109052","resolution":{"observed_at":"2026-08-10T23:34:14.990303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:14.996140Z","title":"Unidepth: Universal monocular metric depth estimation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:14.996140Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:bea2a6ca9de13b13cc149e498b194b41f3dd161595f0b1f5b6942a4c65304327","observation_id":"a24ef0bf-5888-4fdf-90ba-5d3d295d63f7","resolution":{"observed_at":"2026-08-10T23:34:14.996140Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.651508Z","title":"Metric3d: Towards zero-shot metric 3d prediction from a sin- gle image,","venue":null,"work_id":"eec42254-20ce-4582-bc73-d1e258bf9471","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.002852Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:8024d98a69ae0e2dfa0cb8c92d9564b398322c1e05e3b89502a57dba71c7e6de","observation_id":"8ba62ef2-b6a1-4ab2-98ca-08c3c83caace","resolution":{"observed_at":"2026-08-10T23:34:15.659932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.013177Z","title":"Can language understand depth?","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.013177Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:c04fb23d7328a08b2fa4aed87cd9fd395aa325c9c0ac482f996596125b9f057e","observation_id":"a0e53f0b-7626-4e6f-a832-f123c455a73f","resolution":{"observed_at":"2026-08-10T23:34:15.013177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.595644Z","title":"Clip-decoder: Zeroshot multilabel classification using multimodal clip aligned representations,","venue":null,"work_id":"fae876af-a137-4446-9c8e-2f28ab310675","year":2021},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.019691Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:8fc872303460984fce422c0cea44083aed71738caa1b413e0719fff64ced8a7f","observation_id":"98220c84-56a9-4c79-880a-bade461715be","resolution":{"observed_at":"2026-08-10T23:34:15.605434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.555399Z","title":"Cora: Adapting clip for open- vocabulary detection with region prompting and anchor pre-matching,","venue":null,"work_id":"22c48fc7-a938-42ed-bfb9-3c6cacee1310","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.028023Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:dd8fb255e4d850ed929b47fe0346d0d86a95ab5f69bac2b48a24ba42ed85a9e3","observation_id":"458eb8e1-13fb-4e89-9fdf-5ce697d59230","resolution":{"observed_at":"2026-08-10T23:34:15.566850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.526174Z","title":"Text-to-concept (and back) via cross-model alignment,","venue":null,"work_id":"ec58d208-f740-4dad-8107-0d7d1311989e","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.033287Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:c1861dad921ff7b24b1fb42438c6a0e0d031b31523da6518bd7a5c53ac3444c5","observation_id":"c5e75a94-0844-469b-9374-ebc6e2860aee","resolution":{"observed_at":"2026-08-10T23:34:15.531998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.041413Z","title":"Extract free dense labels from clip,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.041413Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:8705511bd51b4d18abb55178686d67910db33c60e7b19acb71e05ea4733b31ab","observation_id":"d3f848b2-b1ed-4103-a678-f522b7704357","resolution":{"observed_at":"2026-08-10T23:34:15.041413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13077","last_updated":"2023-05-22T14:48:53Z","snapshot_observed_at":"2026-08-11T06:30:14.015336Z","submitted_at":"2023-05-22T14:48:53Z","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13077","snapshot_observed_at":"2026-08-10T23:34:15.052306Z","title":"Con- trolvideo: Training-free controllable text-to-video generation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.052306Z"},"links":{"cited_paper":"/paper/2305.13077","citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:7240f3280a741e9d70b3d4daed5e8b155826f70df1bdf6798355a013ea0297c6","observation_id":"e8b8ed8d-6fc9-4838-ad76-f97b48fa14bc","resolution":{"observed_at":"2026-08-10T23:34:15.052306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.058684Z","title":"Digging into self-supervised monocular depth estimation,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.058684Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:e8767abb6bfcf6886b3115bc305762db05d6e6b9d41f744be042499b8eced3ef","observation_id":"0ecbe7dc-9a91-4554-9441-4c93d07229ce","resolution":{"observed_at":"2026-08-10T23:34:15.058684Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.462575Z","title":"3d pack- ing for self-supervised monocular depth estimation,","venue":null,"work_id":"ddfb4454-a37c-4806-9dc5-6d38345f9077","year":2020},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.065043Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:d88bd2dd55044eacdc2ab3657f26b22ef3f31aa2e70089b3acfcfddb21113448","observation_id":"7f48dd3e-81a4-4d74-bcd7-88d740930d48","resolution":{"observed_at":"2026-08-10T23:34:15.470799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.432184Z","title":"Self-supervised monocular depth estimation in the dark: Towards data distribution compensation,","venue":null,"work_id":"6d4d0b46-c47d-459f-bc96-29ba82e3ba13","year":2024},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.071207Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:ee66eababd69974f2f1f4804ce6c962b91ea7c17d6b1dcd91844a6c1625199c6","observation_id":"a029d4f6-bcec-4a81-9713-05372d098105","resolution":{"observed_at":"2026-08-10T23:34:15.438913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.407746Z","title":"nuscenes: A multi- modal dataset for autonomous driving,","venue":null,"work_id":"be71070b-1412-4416-a38f-1a1e8c9f4a29","year":2020},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.079222Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:7dc6857121dcf901bc4420a1a9a66231e99ac573e7e10e3308ea5d2487f06a72","observation_id":"b440253e-dd11-411b-8133-3efb0b8c9974","resolution":{"observed_at":"2026-08-10T23:34:15.417846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.086071Z","title":"1 year, 1000 km: The oxford robotcar dataset,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.086071Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:c15468b1f1e1796bf6cc300d05010df8b7fe685d40e2be3a841ec5e8f1f562cc","observation_id":"b0ac228c-fb13-4be7-86b8-82aab7021e3f","resolution":{"observed_at":"2026-08-10T23:34:15.086071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:34:15.356754Z","title":"When the sun goes down: Repairing photometric losses for all-day depth estimation,","venue":null,"work_id":"0323cd6f-238e-485e-a797-6097c1a3f56a","year":2023},"citing_paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T23:34:15.094294Z"},"links":{"citing_paper":"/paper/2412.20162"},"observation_digest":"sha256:e7f4f94ae125006b987fe0f43fd5e8dc70afadd44b7062289dfe7366b91116c6","observation_id":"3fa54803-7bf9-4647-9729-0ce88204b5f2","resolution":{"observed_at":"2026-08-10T23:34:15.367435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.20162","last_updated":"2024-12-28T14:23:58Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T21:57:39.283884Z","submitted_at":"2024-12-28T14:23:58Z","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":27},"total_outbound_references":44},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2412.20162."}