{"as_of":"2026-08-10T15:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:af50ec8bc1852897bb5765a2f16cd80f5c20bbba7dc84d0408fda24d8b7b4815","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":"2026-08-04T16:06:51.468152Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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":"2026-06-28T10:25:47.256701Z","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":"2026-07-02T02:56:29.669563Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"cited_work":{"arxiv_id":"2509.16909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2509.16909","snapshot_observed_at":"2026-07-28T02:23:18.112933Z","title":"SLAM- Former: Putting SLAM into One Transformer","venue":null,"work_id":"2694b016-f0dd-4b6f-98e1-2bacebecb0ad","year":2025},"citing_paper":{"arxiv_id":"2605.17327","last_updated":"2026-05-17T08:35:02Z","snapshot_observed_at":"2026-08-02T12:25:38.315077Z","submitted_at":"2026-05-17T08:35:02Z","title":"Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-20T13:03:41.389071Z"},"links":{"cited_paper":"/paper/2509.16909","citing_paper":"/paper/2605.17327"},"observation_digest":"sha256:e88faf4bc627b840b0b1e366cd910423f167a567ab4eda2d0d476f495d6c668b","observation_id":"f6790194-255a-45be-b8cc-3d668a46d7f0","resolution":{"observed_at":"2026-07-28T02:23:18.112933Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"cited_work":{"arxiv_id":"2509.16909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2509.16909","snapshot_observed_at":"2026-07-28T02:23:18.112933Z","title":"SLAM- Former: Putting SLAM into One Transformer","venue":null,"work_id":"2694b016-f0dd-4b6f-98e1-2bacebecb0ad","year":2025},"citing_paper":{"arxiv_id":"2606.03287","last_updated":"2026-06-02T07:51:14Z","snapshot_observed_at":"2026-08-07T04:53:37.585041Z","submitted_at":"2026-06-02T07:51:14Z","title":"BA-T: An Iterative Transformer for Two-View Bundle Adjustment","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-28T10:25:47.256701Z"},"links":{"cited_paper":"/paper/2509.16909","citing_paper":"/paper/2606.03287"},"observation_digest":"sha256:d63418a230917ece0d119e150928ce3a0864139b50761165cc42a3b4f36e273e","observation_id":"3857705a-5b5b-4736-9e3e-823d8b5d3a0e","resolution":{"observed_at":"2026-07-28T02:23:18.112933Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2509.16909/citation-record","integrity":"/paper/2509.16909/integrity","json":"/paper/2509.16909/citation-record.json","paper":"/paper/2509.16909"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T16:06:49.404237Z","title":"Orb- slam: A versatile and accurate monocular slam system,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.404237Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:d78ce29c5aad9fca2c44080c98fa5901b9d16dfc5156baa3ef1b06cb0208a2ce","observation_id":"2e555092-5185-4d2c-b81b-51593a6de651","resolution":{"observed_at":"2026-08-04T16:06:49.404237Z","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":"2026-08-04T16:06:49.452633Z","title":"Lsd-slam: Large-scale direct monocular slam,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.452633Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:0575beaded98db39b5aed77e4e2ed36f1cb5cff818b153eaa51cf96b2ef5173c","observation_id":"10243952-d24e-41a9-b03b-af8c5901eaea","resolution":{"observed_at":"2026-08-04T16:06:49.452633Z","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":"2026-08-04T16:06:49.530376Z","title":"One billion points in the cloud–an octree for efficient processing of 3d laser scans,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.530376Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:99b94dde6b14df50e16e3ed329ef5624f9daea5b510be4ddcc78999ef142eb04","observation_id":"3e923cbb-01c4-4f88-b065-48bf3928ce88","resolution":{"observed_at":"2026-08-04T16:06:49.530376Z","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":"2026-08-04T16:06:49.612740Z","title":"Kinectfusion: Real-time dense surface map- ping and tracking,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.612740Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:ed841be31a988a38de240c73dfcd46ad016b861689ccfa48016342dd986da638","observation_id":"bef30888-50c3-4f8d-927e-246990abed1b","resolution":{"observed_at":"2026-08-04T16:06:49.612740Z","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":"2026-08-04T16:06:49.692675Z","title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.692675Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:c3c432165e9e506f8b52e3d38e05212fc61e35397702cb509a9e96e6a3aeb484","observation_id":"a348ec34-9768-45ab-8576-667abfa03577","resolution":{"observed_at":"2026-08-04T16:06:49.692675Z","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":"2026-08-04T16:06:49.773006Z","title":"Scenefactory: A workflow-centric and unified framework for incremental scene modeling,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.773006Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:4bf7b04376c243bcdd9e1e9238aa032ab0c855d5ffce6240f609999bc6255894","observation_id":"e1747c82-dea6-46cd-acc8-adabdde53348","resolution":{"observed_at":"2026-08-04T16:06:49.773006Z","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":"2026-08-04T16:06:49.855641Z","title":"Mast3r-slam: Real-time dense slam with 3d reconstruction priors,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.855641Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:0d6369e9fa04328eac359cc0eb8fe3676a9112822444e08d793996cab8c1a76b","observation_id":"0f64b2da-6113-4436-9052-aacf774ad507","resolution":{"observed_at":"2026-08-04T16:06:49.855641Z","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":"2026-08-04T16:06:49.910299Z","title":"Vggt-slam: Dense rgb slam optimized on the sl(4) manifold,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.910299Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:c052e7831b863344d68a1ce820da9625f8b6e95c31ebc9a9bee5aaddce5b6e03","observation_id":"f4c34eb2-bea5-46b7-af73-8681217efd3f","resolution":{"observed_at":"2026-08-04T16:06:49.910299Z","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":"2026-08-04T16:06:49.964135Z","title":"Dust3r: Geometric 3d vision made easy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:49.964135Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:b50cacdbf204d97a8e15e30375c11faf7e3660ba10639589dcfa08a1d6521afa","observation_id":"b7867f40-e48b-4904-9a8b-ce988e609bc8","resolution":{"observed_at":"2026-08-04T16:06:49.964135Z","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":"2026-08-04T16:06:50.011770Z","title":"Vggt: Visual geometry grounded transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.011770Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:9667b61a3be61ae5ae835f9a41b2b19f7e84d45b32a4595f7d51dc31062ff3e1","observation_id":"29d3b7fe-49bc-4fe9-a5ba-c353792b244c","resolution":{"observed_at":"2026-08-04T16:06:50.011770Z","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":"2026-08-04T16:06:50.074083Z","title":"Streaming 4d visual geometry transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.074083Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:cfe724db322c44eb45b0f2a627f363195afd8397b623ff2364fa71d75bbfc65f","observation_id":"e0197dd6-7846-4cb8-ba3e-082951b898f1","resolution":{"observed_at":"2026-08-04T16:06:50.074083Z","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":"2026-08-04T16:06:50.156167Z","title":"Stream3r: Scalable sequen- tial 3d reconstruction with causal transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.156167Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:f78b9980493523fcbaceb9492a0f0f68d181d4ed6c6f92cd2e7896155d78ad5a","observation_id":"620530b2-46b0-4e11-bed6-b7fdf39e7f96","resolution":{"observed_at":"2026-08-04T16:06:50.156167Z","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":"2026-08-04T16:06:50.236153Z","title":"Nicer-slam: Neural implicit scene encoding for rgb slam,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.236153Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:d5cbbfa099cb86a76f21a709fbd72cc4acf6678906102236824251295060fe77","observation_id":"3c6695b3-d9c3-48c2-b7a1-24c2be7a2e81","resolution":{"observed_at":"2026-08-04T16:06:50.236153Z","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":"2026-08-04T16:06:50.305182Z","title":"Codeslam - learning a compact, optimisable representation for dense visual slam,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.305182Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:b3dd43ae28993fa5413c66b4170159496a7b2bbdc4ef609e6fc8f7bdb16d2521","observation_id":"aaaaa258-a1c8-45dc-9890-9aeb8a970bfb","resolution":{"observed_at":"2026-08-04T16:06:50.305182Z","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":"2026-08-04T16:06:50.365427Z","title":"Deepfactors: Real-time probabilistic dense monocu- lar slam,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.365427Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:fd4b5c682a5797521d52ec6b3900c58953f5ce9b85dfb0644e2746052e71fced","observation_id":"4a7c6fb8-c734-46de-8897-8721ec5e22ea","resolution":{"observed_at":"2026-08-04T16:06:50.365427Z","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":"2026-08-04T16:06:50.465717Z","title":"Mvsnet: Depth inference for unstructured multi-view stereo,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.465717Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:521047ed373fe50fdef383ed8125767b614611a46fba9a32a55ad8860501035b","observation_id":"b407af49-2730-4960-90a0-9d22885283c6","resolution":{"observed_at":"2026-08-04T16:06:50.465717Z","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":"2026-08-04T16:06:50.515487Z","title":"Tandem: Tracking and dense mapping in real-time using deep multi- view stereo,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.515487Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:7ba827a5510e69ac910b3afe69fcb3a8946f6810bc0cb0bf67a1653563de098a","observation_id":"3eb9c1d8-7976-4577-94fd-59d59550802c","resolution":{"observed_at":"2026-08-04T16:06:50.515487Z","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":"2026-08-04T16:06:50.591666Z","title":"Nerf: Representing scenes as neural radiance fields for view synthesis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.591666Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:a780a529a4b3938d5b21c406926548bb7501342c806300ef824b4cca1eaa5d9f","observation_id":"ffd0e1b0-567c-48e6-b3c5-2624d2fd2809","resolution":{"observed_at":"2026-08-04T16:06:50.591666Z","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":"2026-08-04T16:06:50.700360Z","title":"3d gaussian splatting for real-time radiance field rendering,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.700360Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:7667394fc37e4f86c96d409c0ea309f5b94053fba20915b7dcf8f09bd8720fd2","observation_id":"537c6d69-dbef-4a52-80b3-94259e674b26","resolution":{"observed_at":"2026-08-04T16:06:50.700360Z","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":"2026-08-04T16:06:50.789999Z","title":"Nerf-slam: Real- time dense monocular slam with neural radiance fields,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.789999Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:e1b971fcfe26d036bd8347b19cb32cf2760e8b8f816c4f35a84f9ff7e1f0683b","observation_id":"8f337d70-6ea7-4b22-ade6-a9e632d9ec45","resolution":{"observed_at":"2026-08-04T16:06:50.789999Z","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":"2026-08-04T16:06:50.914767Z","title":"Gs-slam: Dense visual slam with 3d gaussian splatting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:50.914767Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:0cd607708b7aeae0b460b04ea2c803a5b55f0f61887f8394648546161c07bc34","observation_id":"510a1280-760c-45dc-970c-0cc21fc12711","resolution":{"observed_at":"2026-08-04T16:06:50.914767Z","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":"2026-08-04T16:06:51.065601Z","title":"Grounding image matching in 3d with mast3r,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.065601Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:c31301408281a9cffa533854eb49047c8e210129227a68fb88d6c2f9c654d54a","observation_id":"f8a2ba70-fd82-43e0-8d2e-51c206bf3a20","resolution":{"observed_at":"2026-08-04T16:06:51.065601Z","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":"2026-08-04T16:06:51.187069Z","title":"Fast3r: Towards 3d recon- struction of 1000+ images in one forward pass,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.187069Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:5c274874032fad026fa75643231b4b7430bf6ec8917c8c8f34bc8d1931751bb7","observation_id":"18ca41b5-d227-4aa5-9b17-13c415dfd30a","resolution":{"observed_at":"2026-08-04T16:06:51.187069Z","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":"2026-08-04T16:06:51.335630Z","title":"π 3: Scalable permutation- equivariant visual geometry learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.335630Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:c4c30b38a10e8329dddf1dfba3dad4f334b2e6e198745779ce816ced428ab584","observation_id":"a81503d3-ad4b-429c-955d-1efe0f5ccd5c","resolution":{"observed_at":"2026-08-04T16:06:51.335630Z","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":"2026-08-04T16:06:51.421709Z","title":"3d reconstruction with spatial memory,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.421709Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:c46ff4a941bbd15a3c4a43ce8fa27297c4052b22dde03cb925399bd77eb5c436","observation_id":"0536bce7-9bee-458e-8b81-2a66bcf0ea59","resolution":{"observed_at":"2026-08-04T16:06:51.421709Z","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":"2026-08-04T16:06:51.424170Z","title":"Continuous 3d perception model with per- sistent state,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.424170Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:e5617209cf3ddccc1c9d79d19294b6b3de24f714284184ed4fe3ee514b64a74c","observation_id":"54ecab08-7b0d-4efa-a325-9dd71fb8bfa0","resolution":{"observed_at":"2026-08-04T16:06:51.424170Z","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":"2026-08-04T16:06:51.426449Z","title":"Long3r: Long sequence streaming 3d reconstruction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.426449Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:36a2cf049683302b288db27f06ffbdb08758b3e814253c004e7561ede8459fc4","observation_id":"2f141395-cb64-41f0-94e4-6830b69f029e","resolution":{"observed_at":"2026-08-04T16:06:51.426449Z","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":"2026-08-04T16:06:51.428935Z","title":"Deepv2d: Video to depth with differ- entiable structure from motion,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.428935Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:78031d110eda5756132b19be8bcfea86482b9ac168be7248a91a9b0357b5bd94","observation_id":"5fc5422b-7dbd-42ea-b534-80e525712875","resolution":{"observed_at":"2026-08-04T16:06:51.428935Z","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":"2026-08-04T16:06:51.431489Z","title":"Deep patch visual slam,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.431489Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:c820637918e4bb2816009ed76fbf76037084d9ddb90c64d54ba86f9985a5aea7","observation_id":"c687eb76-8256-48cd-b0be-45fd66020898","resolution":{"observed_at":"2026-08-04T16:06:51.431489Z","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":"2026-08-04T16:06:51.434047Z","title":"Go-slam: Global optimization for consistent 3d instant reconstruction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.434047Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:5de06c8d47aeefcbfc5f2acaad94b63da8665095512b9e616d7bca201c6069ac","observation_id":"5c43d292-3582-4e98-9112-6d466af01c58","resolution":{"observed_at":"2026-08-04T16:06:51.434047Z","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":"2026-08-04T16:06:51.436915Z","title":"A benchmark for the evaluation of rgb-d slam sys- tems,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.436915Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:dd138752bb902e68d38a7ae0edb910a6ff8cf518a109603bb3a91d8dde3c753e","observation_id":"eea03207-17a9-40f6-a0bc-0907c7f8d509","resolution":{"observed_at":"2026-08-04T16:06:51.436915Z","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":"2026-08-04T16:06:51.439105Z","title":"Real- time rgb-d camera relocalization,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.439105Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:2f432efcd2cec0f7643573db5c3e6c6fe8ee62b327c97326cb9f14c070c10842","observation_id":"b1bfca93-03b2-41c2-b25d-9971c5a58774","resolution":{"observed_at":"2026-08-04T16:06:51.439105Z","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":"2026-08-04T16:06:51.441551Z","title":"Slam3r: Real-time dense scene reconstruction from monocular rgb videos,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.441551Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:f92a729845fdf98a8a8ec60c47b21504842ac4ff1a36ea56479fdc716e40eb1f","observation_id":"dde61634-9f3e-478b-995f-25015325de59","resolution":{"observed_at":"2026-08-04T16:06:51.441551Z","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":"2026-08-04T16:06:51.443868Z","title":"The replica dataset: A digital replica of indoor spaces,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.443868Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:1e8d60402abac3a2c85b86bdbeabd76e032ce878923510e493d03550f13fd6f1","observation_id":"2f9f2843-df0f-4b69-9e1f-748815739c53","resolution":{"observed_at":"2026-08-04T16:06:51.443868Z","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":"2026-08-04T16:06:51.446499Z","title":"Arkitscenes: A diverse real-world dataset for 3d in- door scene understanding using mobile rgb-d data,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.446499Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:a9c27c9964b06bd35b79d526300981cacebe7dff3888dfbdb94b2f861351cb8c","observation_id":"8630b2aa-00e8-4efd-959c-df4c6b2c53ed","resolution":{"observed_at":"2026-08-04T16:06:51.446499Z","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":"2026-08-04T16:06:51.448921Z","title":"Scannet: Richly-annotated 3d reconstruc- tions of indoor scenes,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.448921Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:87e662d4535f94d2676bef14ca7e72fa23390aa8d3a34142c197c2ede3b2937e","observation_id":"46e02da9-9a52-4303-a3ca-f10af6777e55","resolution":{"observed_at":"2026-08-04T16:06:51.448921Z","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":"2026-08-04T16:06:51.451508Z","title":"Scan- net++: A high-fidelity dataset of 3d indoor scenes,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.451508Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:bee37eb42e0905b094e8d01cd5262a5d26d3b5c40081fa0e803e74c572294d4e","observation_id":"a73d273e-8dae-45e4-81a4-02758b50a991","resolution":{"observed_at":"2026-08-04T16:06:51.451508Z","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":"2026-08-04T16:06:51.453787Z","title":"Hy- persim: A photorealistic synthetic dataset for holistic indoor scene understanding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.453787Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:69998c3230cd6daafbbbadcb9744054aece5f63e59a00c9fffb6ea6e6104b083","observation_id":"fb54d606-5fe9-40d9-acf5-32545130f673","resolution":{"observed_at":"2026-08-04T16:06:51.453787Z","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":"2026-08-04T16:06:51.456443Z","title":"Blendedmvs: A large-scale dataset for generalized multi-view stereo networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.456443Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:ff6209614e47b2304e2f51854eaf1b978ec5052c0fda59d10b6c9b7589ddcf95","observation_id":"996a99e5-1739-4338-a110-5cbb0c98d13c","resolution":{"observed_at":"2026-08-04T16:06:51.456443Z","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":"2026-08-04T16:06:51.458781Z","title":"Megadepth: Learning single-view depth prediction from internet photos,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.458781Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:42c8525ebb8b6630e6de74fb90237a33cf6d9adf420c81fa2542df7b4d236d79","observation_id":"de9d48bf-a729-4502-b777-8ad178bfb4af","resolution":{"observed_at":"2026-08-04T16:06:51.458781Z","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":"2026-08-04T16:06:51.460958Z","title":"Deepmvs: Learning multi-view stereopsis,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.460958Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:9676374bc5e0c696dc49279002b05589d8e1340be149de03226dda39e77b9169","observation_id":"d4d9e6d3-22fe-4a13-a46d-cee35335a3e7","resolution":{"observed_at":"2026-08-04T16:06:51.460958Z","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":"2026-08-04T16:06:51.463152Z","title":"Orb-slam3: An accurate open-source li- brary for visual, visual–inertial, and multimap slam,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.463152Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:7044174d43773029b7dd0828ce67d81ac81ff00ccba46bc62e5e67e150e56957","observation_id":"79fcf76b-3567-41bc-a98d-a7a6e1a43174","resolution":{"observed_at":"2026-08-04T16:06:51.463152Z","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":"2026-08-04T16:06:51.465435Z","title":"Dense rgb slam with neural implicit maps,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.465435Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:cab6fe1fcbc969811fe00b837d30754c96c02afa366423079b5d48e7ec849c65","observation_id":"618682a2-735d-40cf-ab77-87db874eba47","resolution":{"observed_at":"2026-08-04T16:06:51.465435Z","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":"2026-08-04T16:06:51.468152Z","title":"A benchmark for rgb-d visual odometry, 3d reconstruction and slam,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T16:06:51.468152Z"},"links":{"citing_paper":"/paper/2509.16909"},"observation_digest":"sha256:946995cfd647d6d655458635285e99c451e67821cb6dae16e9c9cd8d8c936257","observation_id":"75e43fac-7cfd-4552-a0e9-3d901ad8490e","resolution":{"observed_at":"2026-08-04T16:06:51.468152Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.16909","last_updated":"2026-07-27T07:54:30Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T22:52:21.188780Z","submitted_at":"2025-09-21T04:04:47Z","title":"SLAM-Former: Putting SLAM into One Transformer"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":44,"verified_exact":0,"verified_fuzzy":0},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2509.16909."}