{"as_of":"2026-08-09T17:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:241999a01c532bc9ba156c44f59009118cf2389b3c2db3d1b8b4a22a3aeadbeb","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:32:08.417157Z","state":"measured"},{"denominator":70,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":70,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:23:09.928240Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T11:20:11.282375Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.13750","snapshot_observed_at":"2026-08-06T18:23:09.928240Z","title":"Test3R: Learning to Reconstruct 3D at Test Time,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.08448","last_updated":"2025-07-11T09:41:54Z","snapshot_observed_at":"2026-08-08T11:04:41.526877Z","submitted_at":"2025-07-11T09:41:54Z","title":"Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T18:23:09.928240Z"},"links":{"cited_paper":"/paper/2506.13750","citing_paper":"/paper/2507.08448"},"observation_digest":"sha256:79dde9720ac541b3bfc8ce7eb73489a6700b81f491a295e74119af9da802297b","observation_id":"f591ffa9-f648-49e2-90a6-30a3a2925c35","resolution":{"observed_at":"2026-08-06T18:23:09.928240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"cited_work":{"arxiv_id":"2506.13750","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.13750","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Test3r: Learning to reconstruct 3d at test time","venue":null,"work_id":"90a0a067-f162-4fd4-bd10-ea42ca2ce470","year":2025},"citing_paper":{"arxiv_id":"2604.15239","last_updated":"2026-04-16T17:12:37Z","snapshot_observed_at":"2026-07-06T23:02:49.302337Z","submitted_at":"2026-04-16T17:12:37Z","title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-10T11:11:45.176020Z"},"links":{"cited_paper":"/paper/2506.13750","citing_paper":"/paper/2604.15239"},"observation_digest":"sha256:1a508f377d7d951fe0b7fe523aafa50df1fe9ed7bd850b8efac26da1ee4d005c","observation_id":"ac5f74aa-9d9d-4083-a001-aae1379000d0","resolution":{"observed_at":"2026-05-10T11:20:11.285190Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.13750/citation-record","integrity":"/paper/2506.13750/integrity","json":"/paper/2506.13750/citation-record.json","paper":"/paper/2506.13750"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:32:09.652516Z","title":"D2-net: A trainable cnn for joint description and detection of local features","venue":null,"work_id":"75ca5f01-6ce0-4f7e-aec7-960adffe4f10","year":2019},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.339412Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:f428c3903f8a3dc9342ab8103108c53a69ffa87453324d71903048dcf5a0b241","observation_id":"04865b96-d4d3-4185-a666-cd8623e9a09b","resolution":{"observed_at":"2026-08-07T00:32:09.655826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.642442Z","title":"Superpoint: Self-supervised interest point detection and description","venue":null,"work_id":"8d4fd647-6b0c-4a1b-b431-473dd989c574","year":2018},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.442152Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:f02098a4a4beb50cd5ec7708805df0f63dcf3da856384fa5ca0845439893ee87","observation_id":"b405b583-41f9-43a8-986d-390496f0fbeb","resolution":{"observed_at":"2026-08-07T00:32:09.645658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:04.556466Z","title":"Distinctive image features from scale-invariant keypoints","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.556466Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:d19ddb8cc835fe3ff864be6d8434573cd124f4cd35c9f1b7740b144ed1560e49","observation_id":"50cb39df-083a-42a1-a013-059fd1576e25","resolution":{"observed_at":"2026-08-07T00:32:04.556466Z","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":"2026-08-07T00:32:09.623430Z","title":"Neural-guided ransac: Learning where to sample model hypotheses","venue":null,"work_id":"54e49b5b-4ce7-4e1b-8b2b-5e885289f12b","year":2019},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.634227Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:8adab3fa864e9a287b0740fdee1f796bf0982061b9b3d6d928b3ea8b13255ce0","observation_id":"fdd274ab-2b63-4d17-a9ae-f0b7a03842c6","resolution":{"observed_at":"2026-08-07T00:32:09.626819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.612811Z","title":"Lightglue: Local feature matching at light speed","venue":null,"work_id":"cb68d76e-f6f1-427a-8156-35b3bd9ccc7f","year":2023},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.725086Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:c82400f3ff7938a539d895cf25140016b499d52020cbda691835d7b449115ad3","observation_id":"7d10c04c-0919-40d5-8ca9-b9410c643dee","resolution":{"observed_at":"2026-08-07T00:32:09.616247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.602038Z","title":"Progressive correspondence pruning by consensus learning","venue":null,"work_id":"db9b8950-a447-4e88-8ac7-fad142c95e56","year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.796389Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:efdf27264c4e1f44bd012a6681133b2c29245829e2a205cc6a461e2444d83dd6","observation_id":"aa2b0864-4f8e-4b0d-8f2f-86a2d2ae91b6","resolution":{"observed_at":"2026-08-07T00:32:09.605869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.591675Z","title":"Sfm with mrfs: Discrete- continuous optimization for large-scale structure from motion","venue":null,"work_id":"2f56cb82-fc9e-4f50-b665-80a46a0cd233","year":2012},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.837339Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:4c1fcab07f88391ad6c1a3d8ebe8402928cefef108e8eac250d990326906551f","observation_id":"c50178f3-a061-4eb1-a8ec-c5399079a83e","resolution":{"observed_at":"2026-08-07T00:32:09.594993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.581460Z","title":"Pixel-perfect structure- from-motion with featuremetric refinement","venue":null,"work_id":"4f43429f-1b29-4aad-92b0-7cbd00bb14d6","year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:04.924217Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:2e432eba954f3700e685732feef8387c606a72909009c33c61ece89b58aecaca","observation_id":"76213e0c-9a39-447e-b57c-7d29c2042265","resolution":{"observed_at":"2026-08-07T00:32:09.584689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:05.043280Z","title":"Structure-from-motion revisited","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.043280Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:fbb2bc0554bd8aa98817ff01063e3e8460eefc307952e8eda4b75d821716c8bd","observation_id":"eaacd2ae-1dbc-4b04-801f-05d02da57ec0","resolution":{"observed_at":"2026-08-07T00:32:05.043280Z","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":"2026-08-07T00:32:09.563483Z","title":"Cascade cost volume for high-resolution multi-view stereo and stereo matching","venue":null,"work_id":"96243872-0e3e-45f8-a499-91905f8b0f8b","year":2020},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.128670Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:916dc24098ed9399ef50c253a161569df5b221dcca7b7338f599e74906304d32","observation_id":"f1362ba9-6870-45da-b9db-71439f53f5a2","resolution":{"observed_at":"2026-08-07T00:32:09.567023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.552708Z","title":"Pixelwise view selection for unstructured multi-view stereo","venue":null,"work_id":"acdc4d74-9c69-43ac-9acb-633ff328f6c8","year":2016},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.167352Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:a09794aa8eeff72e34c42890f52b9902d8ddcbf11169ebd18bb82c9b6dc37e3b","observation_id":"ba2ebcaf-3259-4a36-9ab1-36fea13361cc","resolution":{"observed_at":"2026-08-07T00:32:09.556305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:05.241429Z","title":"Dust3r: Geometric 3d vision made easy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.241429Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:861a2cf19fc93b916ee8ccb6484c33174fbc009761d922a6afd2615991bfc097","observation_id":"5066e2cd-467a-460a-9da0-650c12ddadaa","resolution":{"observed_at":"2026-08-07T00:32:05.241429Z","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":"2026-08-07T00:32:05.313570Z","title":"Grounding image matching in 3d with mast3r","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.313570Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:0ea25afa93a336690dffdaac5bfbcc5d4b9f45d737cd05d62099f3cad59d14bc","observation_id":"05f6cd91-b0dc-44d3-878c-d89d4eb18abe","resolution":{"observed_at":"2026-08-07T00:32:05.313570Z","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":"2026-08-07T00:32:09.526875Z","title":"A multiple-baseline stereo","venue":null,"work_id":"3aacf4f0-e103-4de6-b991-6817560ba64b","year":1993},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.403179Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:8b0aa0c8f1a3fe335ab074200a00cd7603d73edcfd0cc337c4f0a5a846e3d36d","observation_id":"1d3c2144-ed35-4161-9819-b8f2a1538b51","resolution":{"observed_at":"2026-08-07T00:32:09.530369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.516326Z","title":"Visual prompt tuning","venue":null,"work_id":"63a0ede8-bcf1-49b0-baa1-af052e2fca9e","year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.461711Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:a3f6f479ae0d52f364c61dd9acc8e50b4f3a9bb47f27467c36769b8ae76a9dab","observation_id":"341a91b7-4d98-46c4-953e-cbb615b95e86","resolution":{"observed_at":"2026-08-07T00:32:09.519753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03825","last_updated":"2025-05-08T08:32:16Z","snapshot_observed_at":"2026-07-06T19:28:08.374354Z","submitted_at":"2024-10-04T18:00:07Z","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03825","snapshot_observed_at":"2026-08-07T00:32:05.524753Z","title":"Monst3r: A simple approach for estimating geometry in the presence of motion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.524753Z"},"links":{"cited_paper":"/paper/2410.03825","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:a34b9d17d94114fb4f2782ca3c3dfd2b8d7581449167a1f0be54a7f8a925b3c6","observation_id":"d0ac0ee0-46ee-4c40-96f9-ad69613a6b62","resolution":{"observed_at":"2026-08-07T00:32:05.524753Z","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":"2026-08-07T00:32:09.505389Z","title":"The interpretation of structure from motion","venue":null,"work_id":"42d5c149-d268-4504-afdb-24532aec7a49","year":1979},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.591566Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:468be9fb490193a35ec598e57f83b26fd92118eb868d96ab82448670ac2e4a0e","observation_id":"e14c3fdb-759d-4c25-aa40-270bb1fbd55d","resolution":{"observed_at":"2026-08-07T00:32:09.508990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:05.631350Z","title":"Multi-view stereo: A tutorial","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.631350Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:d082f3e95e0d13653169066b3fa41bb748dbb2bb29301dca7253b06e7a0dbdb4","observation_id":"e822f2df-8441-4862-9f7d-c7df5d0c9f08","resolution":{"observed_at":"2026-08-07T00:32:05.631350Z","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":"2026-08-07T00:32:05.695439Z","title":"Massively parallel multiview stereopsis by surface normal diffusion","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.695439Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:e47b73002636817bcc0a36464f2326dac1d73c80daf38a321d7548807348301e","observation_id":"9127d532-c1db-4a83-9749-7ee0fa6da606","resolution":{"observed_at":"2026-08-07T00:32:05.695439Z","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":"2026-08-07T00:32:09.479517Z","title":"Adaptive patch deformation for textureless-resilient multi-view stereo","venue":null,"work_id":"77f854f3-26d7-4b60-ac31-0790bd451859","year":2023},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.767296Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:c2f331b530ded979b578c2d9b12da4e29a4c332dcdb018026416960e38d93c09","observation_id":"13e4d071-9b92-4180-a773-c0ec0f9b64e5","resolution":{"observed_at":"2026-08-07T00:32:09.483150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.467634Z","title":"Geo-neus: Geometry-consistent neural implicit surfaces learning for multi-view reconstruction","venue":null,"work_id":"8717591c-1d13-4a1f-bfd3-2f2732d11bec","year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.824422Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:5b653be47a0f002fb3a725e9a6bd39c5713ecfcd0aed82820676eb70581749ea","observation_id":"a8483674-83e6-4e9e-8ade-a22eceb9c54a","resolution":{"observed_at":"2026-08-07T00:32:09.472013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.456978Z","title":"Differentiable volumetric rendering: Learning implicit 3d representations without 3d supervision","venue":null,"work_id":"9c5e2ce1-f4f4-496f-8de3-a3d75cfc57f6","year":2020},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.897637Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:867314135900fd508c07bfb8ce11158d596bc268ef1896e3e23cd6ca11fb33b3","observation_id":"f4453242-d554-4c29-82e3-ec3d56600bfd","resolution":{"observed_at":"2026-08-07T00:32:09.460371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.445723Z","title":"Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo","venue":null,"work_id":"107a2d28-02d9-4319-bcc0-e32f164d4633","year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.955939Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:da15aa9df73aa2ce68c0a9bb837c182b542ccc19aaa009db13d11b7795028930","observation_id":"48eb0c14-45b5-44d0-a5b1-e3e454e988c8","resolution":{"observed_at":"2026-08-07T00:32:09.449213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:05.994727Z","title":"Multiview neural surface reconstruction by disentangling geometry and appearance","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:05.994727Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:a44fad9fdda6fcd12d05d93a39c2834cb2a1d5d108c04253f9a3ab291afd9219","observation_id":"170c5e92-068f-4eff-b08c-4b19a49ad143","resolution":{"observed_at":"2026-08-07T00:32:05.994727Z","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":"2026-08-07T00:32:09.427486Z","title":"Multiview stereo with cascaded epipolar raft","venue":null,"work_id":"81343620-7caf-4f0c-a699-60724fd49d22","year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.070886Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:6003873ea0eb1fd2fe5df92a6961e14bdc1e2dc7b3abbdc2bb09ecd3f3fb622b","observation_id":"8aed3c46-39c3-4338-94e1-45a9cd883f06","resolution":{"observed_at":"2026-08-07T00:32:09.430953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.416672Z","title":"Rethinking depth estimation for multi-view stereo: A unified representation","venue":null,"work_id":"0fe8a449-2a0a-453b-b189-2d6c5b2e4392","year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.139346Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:22aad36209c7a2759405f5bde06a383461840735a5f7f05df4925bac1195a803","observation_id":"cab40be3-91ed-4812-8206-4b02fb11d2ec","resolution":{"observed_at":"2026-08-07T00:32:09.420334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:06.186189Z","title":"Mvsnet: Depth inference for unstructured multi-view stereo","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.186189Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:bb3a168129d99441deb728be4c7259e85b852b68c7bf3d67075f21c66f5812ee","observation_id":"6f0f8482-690a-4eb9-9ded-2d968066433e","resolution":{"observed_at":"2026-08-07T00:32:06.186189Z","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":"2026-08-07T00:32:06.275869Z","title":"Geomvsnet: Learning multi-view stereo with geometry perception","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.275869Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:d6ab23208a0700ccd5b70472452e2c267f936f4af4e560e027dbaa14439bd0e2","observation_id":"ace77ee4-b69b-41eb-82d0-a7e7373231b6","resolution":{"observed_at":"2026-08-07T00:32:06.275869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.11651","last_updated":"2025-03-14T17:59:47Z","snapshot_observed_at":"2026-08-07T17:03:09.355801Z","submitted_at":"2025-03-14T17:59:47Z","title":"VGGT: Visual Geometry Grounded Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.11651","snapshot_observed_at":"2026-08-07T00:32:06.332826Z","title":"Vggt: Visual geometry grounded transformer","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.332826Z"},"links":{"cited_paper":"/paper/2503.11651","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:7289cff76fbedd18dffb2c5943d4cb79f3a5cb7b5c348f60fbe3b8c88db164aa","observation_id":"e945b7ed-c03b-457b-89d6-32e96b981d73","resolution":{"observed_at":"2026-08-07T00:32:06.332826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09401","last_updated":"2025-03-23T17:01:39Z","snapshot_observed_at":"2026-08-06T20:02:23.012237Z","submitted_at":"2024-12-12T16:08:03Z","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09401","snapshot_observed_at":"2026-08-07T00:32:06.416651Z","title":"Slam3r: Real-time dense scene reconstruction from monocular rgb videos","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.416651Z"},"links":{"cited_paper":"/paper/2412.09401","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:d3c41e9e6d10f19ee3e39b38daf6c258044b3779920530272840c56e8c72a2b8","observation_id":"26147945-52da-4f2d-8c8a-dfe064cf5c5e","resolution":{"observed_at":"2026-08-07T00:32:06.416651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.16061","last_updated":"2024-08-28T18:01:00Z","snapshot_observed_at":"2026-08-06T09:17:41.634492Z","submitted_at":"2024-08-28T18:01:00Z","title":"3D Reconstruction with Spatial Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.16061","snapshot_observed_at":"2026-08-07T00:32:06.497884Z","title":"3d reconstruction with spatial memory","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.497884Z"},"links":{"cited_paper":"/paper/2408.16061","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:f885bdbb46a65400890d9caf1313d4a4ceadc610f6cfb3f8515221547af2bdb6","observation_id":"1f5d0c28-2107-40c4-8b50-45ace5b50c97","resolution":{"observed_at":"2026-08-07T00:32:06.497884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.17316","last_updated":"2025-03-21T17:12:30Z","snapshot_observed_at":"2026-08-07T16:45:58.858649Z","submitted_at":"2025-03-21T17:12:30Z","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.17316","snapshot_observed_at":"2026-08-07T00:32:06.591511Z","title":"Pow3r: Em- powering unconstrained 3d reconstruction with camera and scene priors","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.591511Z"},"links":{"cited_paper":"/paper/2503.17316","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:e9093ace0849afcff7c542a2c9865e68ad60a66842b246f4d0fac864fba78288","observation_id":"468a1c6e-e58b-405b-93be-d4e940af0588","resolution":{"observed_at":"2026-08-07T00:32:06.591511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.03079","last_updated":"2024-12-05T14:16:07Z","snapshot_observed_at":"2026-07-06T20:01:23.373458Z","submitted_at":"2024-12-04T07:09:59Z","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.03079","snapshot_observed_at":"2026-08-07T00:32:06.656226Z","title":"Align3r: Aligned monocular depth estimation for dynamic videos","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.656226Z"},"links":{"cited_paper":"/paper/2412.03079","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:89c1fcbc578be5931986855cc40c378777ebc5704f41163d36b3164135f84564","observation_id":"cf16062e-cb89-48a1-bd3e-67ffda8276b3","resolution":{"observed_at":"2026-08-07T00:32:06.656226Z","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":"2026-08-07T00:32:06.701380Z","title":"Easi3r: Estimating disentangled motion from dust3r without training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.701380Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:1b427bf425c8a6fc55434b720854e0e58db539bc40883f24d9a28f6267d273ec","observation_id":"487f076a-92ba-435a-81c2-ac75e9465c13","resolution":{"observed_at":"2026-08-07T00:32:06.701380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12387","last_updated":"2025-01-21T18:59:23Z","snapshot_observed_at":"2026-07-06T20:24:03.105038Z","submitted_at":"2025-01-21T18:59:23Z","title":"Continuous 3D Perception Model with Persistent State","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12387","snapshot_observed_at":"2026-08-07T00:32:06.778222Z","title":"Continuous 3d perception model with persistent state","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.778222Z"},"links":{"cited_paper":"/paper/2501.12387","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:7f33696f04662d67c2832cd8c56e97ddd1a2376b03a031696b37e95ae38ed982","observation_id":"6c7f0fc5-d77d-4e87-b382-5f3698c6912f","resolution":{"observed_at":"2026-08-07T00:32:06.778222Z","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":"2026-08-07T00:32:09.389279Z","title":"Gflow: Recovering 4d world from monocular video","venue":null,"work_id":"5801b7f0-b714-4e13-9c7b-57d3598f5b21","year":2025},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.848871Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:b46c650c8138fd3efb213c480ebe65178e9ec62f64a187d3120e7c46b3f401b5","observation_id":"d1d3b104-aae9-434e-9fa1-2337d3787953","resolution":{"observed_at":"2026-08-07T00:32:09.393872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:06.883350Z","title":"Pe3r: Perception-efficient 3d reconstruction","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.883350Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:cad045002b70c6c8bdd596d38e8fd21b0912559e21a4de2603a2ffc6f161f14a","observation_id":"f1a7a62d-2d5c-47b7-92dc-4e6711d53337","resolution":{"observed_at":"2026-08-07T00:32:06.883350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13928","last_updated":"2025-03-19T19:35:52Z","snapshot_observed_at":"2026-07-06T20:25:08.527025Z","submitted_at":"2025-01-23T18:59:55Z","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.13928","snapshot_observed_at":"2026-08-07T00:32:06.934080Z","title":"Fast3r: Towards 3d reconstruction of 1000+ images in one forward pass","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:06.934080Z"},"links":{"cited_paper":"/paper/2501.13928","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:d7a463ecce9524cf44ce934bb21b06e224954982c8d2d40a9cdbf3d3772eeb5e","observation_id":"bab4a09d-6704-4e82-a92f-f57e48442c2c","resolution":{"observed_at":"2026-08-07T00:32:06.934080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1301.7375","last_updated":"2013-01-30T15:03:47Z","snapshot_observed_at":"2026-07-06T03:05:16.172234Z","submitted_at":"2013-01-30T15:03:47Z","title":"Learning by Transduction","version":1},"cited_work":{"arxiv_id":"1301.7375","doi":null,"metadata_source":"pith","pith_arxiv_id":"1301.7375","snapshot_observed_at":"2026-08-07T00:32:08.564492Z","title":"Learning by Transduction","venue":"cs.LG","work_id":"fbc2e92a-56a8-44bf-a007-f88bffbeb708","year":2013},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.043860Z"},"links":{"cited_paper":"/paper/1301.7375","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:3c7c338e870e8187de24fa574d50582c524ad316b2e493517c9e6b203016cb37","observation_id":"bb21bbc6-ca08-41de-96b4-4abc845fd01f","resolution":{"observed_at":"2026-08-07T00:32:08.569013Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.378469Z","title":"Estimation of dependences based on empirical data","venue":null,"work_id":"d2ff379a-46cf-4aca-a6b0-3aeaa9ca7947","year":2006},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.081108Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:9d2839539de376c0fa837ac9a26b86b8074414524803c245d64e91843ac4e844","observation_id":"b07c4ee8-fcd3-42a2-b244-fedf0abc59e2","resolution":{"observed_at":"2026-08-07T00:32:09.382027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:07.166722Z","title":"Large scale transductive svms","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.166722Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:fe3a0b674ba4be0f1f66d7f6d499018d63905fd984d247bbdaba15a9a351999b","observation_id":"3655257e-41a2-4965-b359-cc1d1b589974","resolution":{"observed_at":"2026-08-07T00:32:07.166722Z","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":"2026-08-07T00:32:07.217960Z","title":"Learning to classify text using support vector machines, volume 668","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.217960Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:262f722688c688099a0480c766116f2d2abf8ac6d50e19728b07bd8ab3e9fc08","observation_id":"19d5f298-f514-4c48-8abd-26af199a63c8","resolution":{"observed_at":"2026-08-07T00:32:07.217960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18466","last_updated":"2024-02-02T20:28:27Z","snapshot_observed_at":"2026-08-04T19:50:24.574752Z","submitted_at":"2023-05-29T08:03:28Z","title":"Test-Time Training on Nearest Neighbors for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18466","snapshot_observed_at":"2026-08-07T00:32:07.253775Z","title":"Test-time training on nearest neighbors for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.253775Z"},"links":{"cited_paper":"/paper/2305.18466","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:1adf9457162b2a02bf654036f6a7f3c4f7ef786ce5db366b91bd93c513044b82","observation_id":"5fcf264d-ad9f-4ece-ac5b-9c7d9b182164","resolution":{"observed_at":"2026-08-07T00:32:07.253775Z","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":"2026-08-07T00:32:09.353032Z","title":"Local learning algorithms","venue":null,"work_id":"91798707-bd06-42f5-b440-0774f9936e8a","year":1992},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.305492Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:f612c5375fa1ca7d7a679197af816a6e8ee4ca0eac5509ecef7bf60c81f8a515","observation_id":"b445c651-9f90-42f3-a8b6-232f7b915113","resolution":{"observed_at":"2026-08-07T00:32:09.356730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.342119Z","title":"Svm-knn: Discriminative nearest neighbor classification for visual category recognition","venue":null,"work_id":"dfde882a-8137-43bb-bc3c-f68eaff665aa","year":2006},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.380193Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:afac7e1094baf1dd5a307adfbd47867bf57dbd6a2da06036aacebddaae47b080","observation_id":"8f8c2048-8c73-4f13-8cf4-ceb0a09f93fd","resolution":{"observed_at":"2026-08-07T00:32:09.345355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.331239Z","title":"Test-time training with self-supervision for generalization under distribution shifts","venue":null,"work_id":"aefd9a63-28af-4e4f-8a03-c2b9e4a73d0b","year":2020},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.444980Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:8e64d037fa0b2c503b5e7f7a2bdec1d90bc55cbae25b30ffb5ce282a5273d4ec","observation_id":"ec6ea554-8aa4-4571-9c37-385b4a9bbc45","resolution":{"observed_at":"2026-08-07T00:32:09.334869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.04309","last_updated":"2021-04-09T02:47:39Z","snapshot_observed_at":"2026-08-09T01:41:50.099348Z","submitted_at":"2020-07-08T17:56:27Z","title":"Self-Supervised Policy Adaptation during Deployment","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.04309","snapshot_observed_at":"2026-08-07T00:32:07.450534Z","title":"Self-supervised policy adaptation during deployment","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.450534Z"},"links":{"cited_paper":"/paper/2007.04309","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:02c603c68847e0b3c7176010db605ae645c11fffdf6fcfee3dbc5f7dc6f99869","observation_id":"6191a1ef-ce87-4cd1-8462-4548b21a191f","resolution":{"observed_at":"2026-08-07T00:32:07.450534Z","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":"2026-08-07T00:32:09.320278Z","title":"Online learning of unknown dynamics for model-based controllers in legged locomotion","venue":null,"work_id":"e3b08357-4a14-46cf-95b8-9092f9fba7fb","year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.611101Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:ff5cc1a4d033763e9b690d994db8d92516d8784fc85235e7d918164bb2938931","observation_id":"e9e098db-6306-45eb-939c-c1441895994e","resolution":{"observed_at":"2026-08-07T00:32:09.323905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:07.676630Z","title":"Ttt++: When does self-supervised test-time training fail or thrive? Advances in Neural Information Processing Systems, 34:21808–21820, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.676630Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:e38f6c723d7efbdb8d08a9f3db0b52d991a9369f473f56a9f6cc6d4a6c7f48a7","observation_id":"d9a53a50-f2b9-425d-b70b-d0cee6130cf5","resolution":{"observed_at":"2026-08-07T00:32:07.676630Z","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":"2026-08-07T00:32:09.299563Z","title":"Robust test-time adaptation in dynamic scenarios","venue":null,"work_id":"28d05d94-c42c-489a-a203-b2c70d736351","year":2023},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.752887Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:fa5779ccd64001fa20fb7b42107e2e9b87dffe2bcd527829106db0b3edfed8a8","observation_id":"bc3b0edb-9c2d-4613-a898-39d8ab0b4578","resolution":{"observed_at":"2026-08-07T00:32:09.303672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-07T00:32:07.881392Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.881392Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:81e63b17ec8c1a51d994396697821deaf4baa01de2e0457c3c5832e95413fdfb","observation_id":"1f45e688-671e-4e8e-a34d-8ee3014f6ed1","resolution":{"observed_at":"2026-08-07T00:32:07.881392Z","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":"2026-08-07T00:32:07.922310Z","title":"How can we know what language models know? Transactions of the Association for Computational Linguistics, 8:423–438, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:07.922310Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:7d8f6da001704f52c0e1c02e1b7a829ce81c7821b8d3ef56073f755373eb30e6","observation_id":"7bd04bbc-e25c-4145-9091-421cd23b57d5","resolution":{"observed_at":"2026-08-07T00:32:07.922310Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.15980","last_updated":"2020-11-07T05:33:35Z","snapshot_observed_at":"2026-08-05T14:17:34.026911Z","submitted_at":"2020-10-29T22:54:00Z","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.15980","snapshot_observed_at":"2026-08-07T00:32:08.047299Z","title":"Autoprompt: Eliciting knowledge from language models with automatically generated prompts","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.047299Z"},"links":{"cited_paper":"/paper/2010.15980","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:71a31b4659b45dde1bbdf5d4cd48d1f30936c1a384727ea820fc8d4cd5fb8664","observation_id":"5a442b19-344c-4f3f-a1d9-23ee46068bcb","resolution":{"observed_at":"2026-08-07T00:32:08.047299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-07T00:32:08.118223Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.118223Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:25eff8dc6601860b8465fcab8127efbff22796f13977bc78b8fa241e73a77111","observation_id":"34c15793-480f-4f0c-8171-0cc1c61ed8be","resolution":{"observed_at":"2026-08-07T00:32:08.118223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-07-06T10:29:18.734092Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-07T00:32:08.190417Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.190417Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:630358f0bbd8a818eb98e12bc5c6abc803aba29fdaa38b341a1133e53b8fbd40","observation_id":"c0df7c76-b8a0-4e50-b374-0fa7a111501a","resolution":{"observed_at":"2026-08-07T00:32:08.190417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07602","last_updated":"2022-03-20T15:13:08Z","snapshot_observed_at":"2026-08-08T11:15:37.346201Z","submitted_at":"2021-10-14T17:58:47Z","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07602","snapshot_observed_at":"2026-08-07T00:32:08.307818Z","title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.307818Z"},"links":{"cited_paper":"/paper/2110.07602","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:10b14bf4ec9b5a42422e2d0f60456f44282ac3ccc55eb9f87a4ea7b7973c06e8","observation_id":"712e8857-7bed-48e4-a9ec-92e57aa3073c","resolution":{"observed_at":"2026-08-07T00:32:08.307818Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-07T00:32:08.362346Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.362346Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:58f6656e4bbf4d770348986b7c5394bf67cbd9cd6ecee551fe838bb7c22e1b65","observation_id":"26312a19-e5ea-4353-b3ad-27598cfe3910","resolution":{"observed_at":"2026-08-07T00:32:08.362346Z","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":"2026-08-07T00:32:08.386890Z","title":"Large-scale data for multiple-view stereopsis","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.386890Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:330bdc22b33c15c42c71e86d5c74b390ba5d3b92842b34907b02cf1591773f51","observation_id":"a37f8f84-b8a2-458b-8a1f-57deac6bdb48","resolution":{"observed_at":"2026-08-07T00:32:08.386890Z","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":"2026-08-07T00:32:09.214282Z","title":"A multi-view stereo benchmark with high-resolution images and multi- camera videos","venue":null,"work_id":"a548826a-f457-499d-84a0-5bd3cfaa03d8","year":2017},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.389968Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:b38722ac69aa0aecd216a3f4a6b29edac31dc891419da947bcb0f600fd7b9aaa","observation_id":"188d8bd9-281a-45be-ac12-6ff250847423","resolution":{"observed_at":"2026-08-07T00:32:09.247341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.04831","last_updated":"2022-11-30T19:22:22Z","snapshot_observed_at":"2026-08-04T13:02:31.952282Z","submitted_at":"2022-10-10T16:45:13Z","title":"Visual Prompt Tuning for Test-time Domain Adaptation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.04831","snapshot_observed_at":"2026-08-07T00:32:08.393324Z","title":"Visual prompt tuning for test-time domain adaptation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.393324Z"},"links":{"cited_paper":"/paper/2210.04831","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:62914c467c51503c4b02bcaedab3185a3eae1c9d13fb4212ee0ba6bbf1b3f154","observation_id":"ed55fa40-a8ca-4ea1-936f-ddf1cd977a8b","resolution":{"observed_at":"2026-08-07T00:32:08.393324Z","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":"2026-08-07T00:32:09.109563Z","title":"Demon: Depth and motion network for learning monocular stereo","venue":null,"work_id":"e394d032-d274-4aee-ab41-f92d00b44970","year":2017},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.396342Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:cc8fbda7c4f3c2900b086e55ea8c1ca69fd9c92b09acd404e5bfafae5c76819b","observation_id":"31b0d295-c038-42f8-a08a-eded372e8e7a","resolution":{"observed_at":"2026-08-07T00:32:09.169095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.04605","last_updated":"2020-04-27T19:17:43Z","snapshot_observed_at":"2026-07-06T07:20:36.957156Z","submitted_at":"2018-12-11T18:47:12Z","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.04605","snapshot_observed_at":"2026-08-07T00:32:08.399100Z","title":"Deepv2d: Video to depth with differentiable structure from motion","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.399100Z"},"links":{"cited_paper":"/paper/1812.04605","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:097ecfe2e50be459ba0cb56a90dca32b9317a62c56c5415352e188b106e005b9","observation_id":"ba02c823-0148-4038-b47a-6c42f662e34a","resolution":{"observed_at":"2026-08-07T00:32:08.399100Z","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":"2026-08-07T00:32:09.069844Z","title":"A benchmark and a baseline for robust multi-view depth estimation","venue":null,"work_id":"be76a801-3bc9-42c8-ab1e-9f71b3d19bdc","year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.401792Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:d240ac7ce0ddef4fc1b201cb42da5813279a30a42263055e5cad0af0cabb44ec","observation_id":"1559ea93-bd58-4d02-bc04-f14448fbe29c","resolution":{"observed_at":"2026-08-07T00:32:09.085491Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:09.055716Z","title":"Vis-mvsnet: Visibility-aware multi-view stereo network","venue":null,"work_id":"44214097-00d7-4869-ad91-66de5e7b69c0","year":2023},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.404901Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:97817ba87f2393c2c191221bfe87f86dfcab0a3d6dfe6e587f26eacfd696bc19","observation_id":"00eee936-5643-4764-9156-39cda516a1dd","resolution":{"observed_at":"2026-08-07T00:32:09.063411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:08.956792Z","title":"Mvs2d: Efficient multi-view stereo via attention- driven 2d convolutions","venue":null,"work_id":"6794297c-e162-4309-98c7-802524c8e115","year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.407829Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:b9b5ba1039026bbbd5c44223e293175e6db764370ca8891db22b3e1fa76bf868","observation_id":"86e9c875-9c0f-4b2a-9610-1fbe37adfa00","resolution":{"observed_at":"2026-08-07T00:32:09.023105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:08.826233Z","title":"Scene coordinate regression forests for camera relocalization in rgb-d images","venue":null,"work_id":"a53fa1e2-b576-4a34-9bdd-2adc4d05e9a1","year":2013},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.410685Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:ddd4aecb844a0a1d2f468c82a83f198e5609d833c9c5663fc265db9135fca6df","observation_id":"cf04d769-5d9b-4b1d-b0f4-9bfdc2fea161","resolution":{"observed_at":"2026-08-07T00:32:08.878698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:32:08.413988Z","title":"Neural rgb-d surface reconstruction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.413988Z"},"links":{"citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:9deace594c0f6103167473b835f9e267ff941cfeca3f623bd5cec56d30b966ee","observation_id":"a5156f4d-9d00-4a77-a80e-e4365d54cb3d","resolution":{"observed_at":"2026-08-07T00:32:08.413988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-07T00:32:08.417157Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T00:32:08.417157Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2506.13750"},"observation_digest":"sha256:feeeb771185a8923366269a8ac836e4fe01d48f627138f7df98ab0553eeda9ce","observation_id":"f09dbfdd-dcfa-4843-9a4b-ffd141c0a897","resolution":{"observed_at":"2026-08-07T00:32:08.417157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.13750","last_updated":"2025-06-16T17:56:22Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T16:56:18.576968Z","submitted_at":"2025-06-16T17:56:22Z","title":"Test3R: Learning to Reconstruct 3D at Test Time"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":1,"verified_fuzzy":31},"total_outbound_references":68},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 2 inbound Pith citation observations for arXiv:2506.13750."}