{"as_of":"2026-08-10T02:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fb01988638b088961fdeb9f2817c40fe1c4555294afef3135395b7d98cc599f5","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:22:58.067260Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T10:24:06.548319Z","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":"2026-05-18T01:55:37.906296Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"cited_work":{"arxiv_id":"2506.14271","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.14271","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leader360V: The large-scale, real-world 360 video dataset for multi-task learning in diverse environment","venue":null,"work_id":"06c5b988-19ce-4ee4-8aa7-1bb1b13b9ec0","year":2025},"citing_paper":{"arxiv_id":"2511.00510","last_updated":"2026-05-04T13:20:29Z","snapshot_observed_at":"2026-08-08T08:36:44.199995Z","submitted_at":"2025-11-01T11:28:05Z","title":"OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-05-18T01:55:04.637365Z"},"links":{"cited_paper":"/paper/2506.14271","citing_paper":"/paper/2511.00510"},"observation_digest":"sha256:3781718d4c0c84bd388604b38c1bdd6da3fc179760bccd707ea435a4ff740661","observation_id":"de96d08c-0454-4990-b45c-25a70f39f877","resolution":{"observed_at":"2026-05-18T01:55:37.909623Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"cited_work":{"arxiv_id":"2506.14271","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.14271","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leader360V: The large-scale, real-world 360 video dataset for multi-task learning in diverse environment","venue":null,"work_id":"06c5b988-19ce-4ee4-8aa7-1bb1b13b9ec0","year":2025},"citing_paper":{"arxiv_id":"2604.07901","last_updated":"2026-04-09T07:17:47Z","snapshot_observed_at":"2026-07-06T22:57:09.435331Z","submitted_at":"2026-04-09T07:17:47Z","title":"PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-10T18:27:39.914591Z"},"links":{"cited_paper":"/paper/2506.14271","citing_paper":"/paper/2604.07901"},"observation_digest":"sha256:ceb778d232c0dc967eb856caf6e869af5fbfbda0e935a51ce54c144a739d0428","observation_id":"5c84c75e-8362-439f-9619-9cc8152fcb2c","resolution":{"observed_at":"2026-05-11T00:30:55.195963Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.14271","snapshot_observed_at":"2026-08-08T10:24:06.548319Z","title":"Zhang, D","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.05570","last_updated":"2026-08-06T03:42:50Z","snapshot_observed_at":"2026-08-09T23:11:05.507081Z","submitted_at":"2026-08-06T03:42:50Z","title":"A Multi-Layer System for Ultra-High-Resolution Static 360-Degree Telepresence","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T10:24:06.548319Z"},"links":{"cited_paper":"/paper/2506.14271","citing_paper":"/paper/2608.05570"},"observation_digest":"sha256:491e78334d882decd909fd83963538a00b985b8f6a80f2c21ded1e584478216d","observation_id":"1aa4f28b-3ea2-41d8-b754-e20c269719dd","resolution":{"observed_at":"2026-08-08T10:24:06.548319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.14271/citation-record","integrity":"/paper/2506.14271/integrity","json":"/paper/2506.14271/citation-record.json","paper":"/paper/2506.14271"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:22:52.604763Z","title":"Panacea: Panoramic and controllable video generation for autonomous driving","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:52.604763Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:83b97834e23cb109234be816f889409a5d2a3986d7a4509484253c169efa2cb5","observation_id":"d7c58b17-c086-48c4-944d-9a60b1c2ccff","resolution":{"observed_at":"2026-08-07T00:22:52.604763Z","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":"2026-08-07T00:23:02.156228Z","title":"Openmpd: An open multimodal perception dataset for autonomous driving.IEEE Transactions on Vehicular Technology, 71(3):2437–2447, 2022","venue":null,"work_id":"3f473b62-df9e-4b69-8fe7-59c424e89a72","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:52.653218Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:1a9bb0c21ad3e0e600b2d4f898d6ae2308c943cd1c3ad6b49883adcdfeead310","observation_id":"569b06f8-0076-4af1-8db1-9ea84fe7b94e","resolution":{"observed_at":"2026-08-07T00:23:02.160227Z","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":"2026-08-07T00:23:02.145817Z","title":"Semantic cameras for 360-degree environment perception in automated urban driving.IEEE Transactions on Intelligent Transportation Systems, 23(10):17271–17283, 2022","venue":null,"work_id":"123fd867-0221-4253-b1d7-b94628c96ae4","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:52.768926Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:ada6d63283859a6d8ccb5ba09a46cb268fa84d35d30c8944abf483b2e130f38c","observation_id":"8d5dfdb8-5c68-4b29-b19c-39ed164a7e14","resolution":{"observed_at":"2026-08-07T00:23:02.149744Z","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":"2403.16370","last_updated":"2024-03-25T02:30:32Z","snapshot_observed_at":"2026-07-06T17:49:52.751335Z","submitted_at":"2024-03-25T02:30:32Z","title":"GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.16370","snapshot_observed_at":"2026-08-07T00:22:52.868408Z","title":"Goodsam: Bridging domain and capacity gaps via segment anything model for distortion-aware panoramic semantic segmentation.arXiv preprint arXiv:2403.16370, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:52.868408Z"},"links":{"cited_paper":"/paper/2403.16370","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:bf544a7ad56827a85b2ca616b75e0898e0ff678c7c8282a92f8b51c1cf112587","observation_id":"7bac5d7d-4809-4d7b-8402-9adf3c473ab3","resolution":{"observed_at":"2026-08-07T00:22:52.868408Z","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":"2026-08-07T00:23:02.136567Z","title":"Panovos: Bridging non-panoramic and panoramic views with transformer for video segmentation","venue":null,"work_id":"2b75febc-bfeb-44f6-b05e-9f6eb0f3ae4b","year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:52.956061Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:4f50e707a0ef8158fe551b724fbf54e1b7b7d0af995a945ebd838d71a816a7e8","observation_id":"4417cf9c-b941-4c78-b1b0-01b3ef51558a","resolution":{"observed_at":"2026-08-07T00:23:02.139705Z","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":"2026-08-07T00:23:02.124993Z","title":"Detection thresholds for rotation and translation gains in 360 video-based telepresence systems.IEEE transactions on visualization and computer graphics, 24(4):1671–1680, 2018","venue":null,"work_id":"a3a5d281-f7e7-4655-b17b-b80c738d81bb","year":2018},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.064780Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:7ef63a6f6aae065f205de1d5af38a364481bc08dd7feb055079577f39daf27d6","observation_id":"b353ac7b-3645-4986-8073-7b5d4f29874e","resolution":{"observed_at":"2026-08-07T00:23:02.128973Z","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":"2026-08-07T00:23:02.082426Z","title":"360vo: Visual odometry using a single 360 camera","venue":null,"work_id":"75bceea7-ae9a-43ed-b24d-fb069a91dc2e","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.166453Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:05c42c4a3faecb4c63153ee591b0b2dc3512351676c04c6c5f7ce566ecab38ca","observation_id":"3fad7eae-c29e-452f-a593-5f2977d60cd9","resolution":{"observed_at":"2026-08-07T00:23:02.092191Z","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":"2026-08-07T00:23:02.028901Z","title":"360+ x: A panoptic multi-modal scene understanding dataset","venue":null,"work_id":"ef19f5dc-345a-4d03-94dc-3f144a6a074c","year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.298547Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:2d5567f8de2d63391f69241ff46f5b1065dfd7e932ca84859576a2c86ff790e3","observation_id":"66256b51-5712-48b1-a080-a02872424e96","resolution":{"observed_at":"2026-08-07T00:23:02.056086Z","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":"2026-08-07T00:23:01.999521Z","title":"Omniscribe: Authoring immersive audio descriptions for 360 videos","venue":null,"work_id":"e90bfa2e-ea64-4b5a-8db2-7f6a37827ea2","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.382994Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:0a7d7c19b966f2afd6cec740c350e719efa982b8e05eed111b9fc55157a1a25c","observation_id":"06247cfc-c312-405c-be68-35677fcef8f0","resolution":{"observed_at":"2026-08-07T00:23:02.012052Z","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":"2404.13953","last_updated":"2025-06-20T09:16:26Z","snapshot_observed_at":"2026-08-08T15:22:18.287027Z","submitted_at":"2024-04-22T07:54:53Z","title":"360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13953","snapshot_observed_at":"2026-08-07T00:22:53.464307Z","title":"360vots: Visual object tracking and segmentation in omnidirectional videos.ArXiv, abs/2404.13953, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.464307Z"},"links":{"cited_paper":"/paper/2404.13953","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:a7b9c03022bbaa525fb80ea33268acac3eeae6a598bafc55b8250e0a96e43922","observation_id":"91d8456a-ab46-404b-8c9f-5d72b32d0860","resolution":{"observed_at":"2026-08-07T00:22:53.464307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.04565","last_updated":"2025-03-23T11:58:13Z","snapshot_observed_at":"2026-08-07T17:24:20.264990Z","submitted_at":"2025-03-06T15:53:42Z","title":"Omnidirectional Multi-Object Tracking","version":2},"cited_work":{"arxiv_id":"2503.04565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.04565","snapshot_observed_at":"2026-08-07T00:22:58.831540Z","title":"Omnidirectional Multi-Object Tracking","venue":"cs.CV","work_id":"48f9ccfe-f676-4790-aa76-e644a9618482","year":2025},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.527835Z"},"links":{"cited_paper":"/paper/2503.04565","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:001819eaea9fa76e0b2d85641fbec2c9c23a9fe98893a68d9f012d244e751bc0","observation_id":"e02fb3ff-d445-498e-b96a-377672ca6181","resolution":{"observed_at":"2026-08-07T00:22:58.909005Z","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":{"arxiv_id":"2408.00714","last_updated":"2024-10-28T16:37:57Z","snapshot_observed_at":"2026-07-06T18:55:41.459417Z","submitted_at":"2024-08-01T17:00:08Z","title":"SAM 2: Segment Anything in Images and Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00714","snapshot_observed_at":"2026-08-07T00:22:53.620449Z","title":"Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloé Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross B","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.620449Z"},"links":{"cited_paper":"/paper/2408.00714","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:0bf90de56cc184cd6618a7451cd388cd8b7c019cb944ddb26ba4ff5465e5a8d2","observation_id":"9a237f0d-a4e0-4632-a507-b639494d5029","resolution":{"observed_at":"2026-08-07T00:22:53.620449Z","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":"2026-08-07T00:23:01.896958Z","title":"360vot: A new benchmark dataset for omnidirectional visual object tracking.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 20509–20519, 2023","venue":null,"work_id":"1f020ec3-1682-4d9f-8e1d-faffa970540d","year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.707160Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:908d088319eac9defaa91f5c8e43681be7e9e87fab94b430d4e2839793a5fbf0","observation_id":"e0dfdec1-a005-4198-9593-074dd8e6a814","resolution":{"observed_at":"2026-08-07T00:23:01.948176Z","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":"2026-08-07T00:23:01.773945Z","title":"High quality entity segmentation","venue":null,"work_id":"cea9353b-3bd4-4e92-8b9f-281d7703ba81","year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.860437Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:e014ef7f06416f14fa8d31ee41d1d8f40bdbb457ffbe113e25856355962e89bb","observation_id":"2a900ec0-3d77-4105-8ea5-05fa41716145","resolution":{"observed_at":"2026-08-07T00:23:01.819696Z","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":"2026-08-07T00:22:53.925483Z","title":"Oneformer: One transformer to rule universal image segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:53.925483Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:71a393ce2851cfbba9e96b3ee7bec4abbf5b2405e01d4e5b9c55b6fb8145ac24","observation_id":"0f4e18fc-a3ff-4a62-9813-9c85ad7320c1","resolution":{"observed_at":"2026-08-07T00:22:53.925483Z","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":"2026-08-07T00:23:01.657568Z","title":null,"venue":null,"work_id":"4eac913b-9538-4904-814c-82a8933b154a","year":2021},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.000080Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:51aaee94e9f18396aa4ae188f84413a5cf9bad9e2988cca17a1f999e7bcdeae2","observation_id":"b1946e14-6c4d-41c0-9ac3-753681585161","resolution":{"observed_at":"2026-08-07T00:23:01.733741Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2206.07704","last_updated":"2022-06-15T17:57:28Z","snapshot_observed_at":"2026-08-03T18:35:11.771332Z","submitted_at":"2022-06-15T17:57:28Z","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","version":1},"cited_work":{"arxiv_id":"2206.07704","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.07704","snapshot_observed_at":"2026-08-07T00:22:58.690884Z","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","venue":"cs.CV","work_id":"b59f7922-9590-4ebc-8207-2fa7ea6ec4b7","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.047920Z"},"links":{"cited_paper":"/paper/2206.07704","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:fbd334e431f1b4ec649e081cfbc5ac91c498cf0734b8e380479a987eaaa2b5ab","observation_id":"0d054efd-2320-42c3-a9e3-4f07d0fe7990","resolution":{"observed_at":"2026-08-07T00:22:58.745329Z","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":"2026-08-07T00:23:01.526487Z","title":"Fine-grained perception in panoramic scenes: A novel task, dataset, and method for object importance ranking","venue":null,"work_id":"9354919a-b72f-445a-81a8-bc71e4912a88","year":2025},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.117015Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:47852ef6585d2ee24f096ccc742a6a13e1fd1fd4307a9cdc74304ca18d8cd937","observation_id":"aa963aaf-a609-4431-9be7-b3f2bf68c65b","resolution":{"observed_at":"2026-08-07T00:23:01.588095Z","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":"2026-08-07T00:23:01.493025Z","title":"Lvos: A benchmark for long-term video object segmentation.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 13434–13446, 2022","venue":null,"work_id":"040af064-cf5e-4954-b67a-e24f9509857a","year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.188017Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:9b3dd3d4fb4de2adab70607d424570a1794c497d912091341cc815da049eb7e9","observation_id":"e668ce63-2e37-4191-a8e3-1d83e3038256","resolution":{"observed_at":"2026-08-07T00:23:01.496524Z","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":"2026-08-07T00:23:01.394682Z","title":"Large-scale video panoptic segmentation in the wild: A benchmark.2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21001–21011, 2022","venue":null,"work_id":"d4a6615d-6492-4d37-bb1f-e432fbe7048b","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.285067Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:70d5f370b71c0f58a40b43707024423eca39c579dc6ae2b1637aef74cb560a6d","observation_id":"34f1981c-517b-4249-9162-e96b3cb592f3","resolution":{"observed_at":"2026-08-07T00:23:01.484254Z","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":"2026-08-07T00:23:01.270199Z","title":"Openannotate2: Multi-modal auto-annotating for autonomous driving.IEEE Transactions on Intelligent Vehicles, 2024","venue":null,"work_id":"89fe82c9-f6d3-41a5-b673-7bbf2f0b4d3c","year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.287919Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:c5e0096508c692d0abaa17041c424beed240d965f168a3b27bf6b6a6bb0a14ba","observation_id":"9cd0ee89-f47a-49a4-a547-72de4f33dfe0","resolution":{"observed_at":"2026-08-07T00:23:01.326822Z","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":"2026-08-07T00:23:01.193612Z","title":"Algpt: Multi-agent cooperative framework for open-vocabulary multi-modal auto-annotating in autonomous driving.IEEE Transactions on Intelligent Vehicles, 2024","venue":null,"work_id":"4a2bb813-6fee-4892-9ebe-9ea7710c2458","year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.365441Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:add08f162e7f0a8687270933647307f4690ada6f08fd81928d468c4bae9b67b5","observation_id":"4a389f63-5180-4ed7-a899-2439008c1c83","resolution":{"observed_at":"2026-08-07T00:23:01.236961Z","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":"2026-08-07T00:23:01.028185Z","title":"Mevis: A large-scale benchmark for video segmentation with motion expressions.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 2694–2703, 2023","venue":null,"work_id":"db5cacac-c5eb-4195-89b8-1b3f9d32480c","year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.509780Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:fc0efba7862aa20e63b3d2be6a411c0184b06d16c35b6f2ca627e466fb2dc1e3","observation_id":"d52358ba-2c5a-4b29-a5b7-da0582df5375","resolution":{"observed_at":"2026-08-07T00:23:01.104090Z","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":"1803.10794","last_updated":"2018-03-28T18:30:17Z","snapshot_observed_at":"2026-07-06T06:30:45.384040Z","submitted_at":"2018-03-28T18:30:17Z","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.10794","snapshot_observed_at":"2026-08-07T00:22:54.592843Z","title":"Trackingnet: A large-scale dataset and benchmark for object tracking in the wild.ArXiv, abs/1803.10794, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.592843Z"},"links":{"cited_paper":"/paper/1803.10794","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:3536f8f72c601a9333c5480a7eb368c957417ad6afb8c11c8b676efbaad2a439","observation_id":"93aa1c42-0e3b-4b8a-a83f-dbbcfe28bbee","resolution":{"observed_at":"2026-08-07T00:22:54.592843Z","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":"2026-08-07T00:23:00.966601Z","title":"Lasot: A high-quality benchmark for large-scale single object tracking.2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5369–5378, 2018","venue":null,"work_id":"3fc56933-9b42-4656-869e-1e7b556e17d0","year":2019},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.681041Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:175060893a72ead77a6cf2f6eeca6cba7a804e08a5816aa092427c62b2781084","observation_id":"cd0f1257-7d32-402a-94d9-db25b96565bf","resolution":{"observed_at":"2026-08-07T00:23:00.970262Z","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":"2005.10356","last_updated":"2020-05-20T21:07:28Z","snapshot_observed_at":"2026-08-03T18:29:55.243573Z","submitted_at":"2020-05-20T21:07:28Z","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.10356","snapshot_observed_at":"2026-08-07T00:22:54.842927Z","title":"Tao: A large-scale benchmark for tracking any object.ArXiv, abs/2005.10356, 2020","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.842927Z"},"links":{"cited_paper":"/paper/2005.10356","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:ed122cec651c4d822fe1c2ac1d1fdcad664045c9efcce90567f3fefd8c9305cd","observation_id":"75722301-3209-4ecb-b65b-ab95655578a4","resolution":{"observed_at":"2026-08-07T00:22:54.842927Z","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":"2026-08-07T00:23:00.850680Z","title":"360dvd: Controllable panorama video generation with 360-degree video diffusion model","venue":null,"work_id":"2be2fd16-9396-4bcc-a6bd-2a0b0ef4e84d","year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:54.899455Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:9381da79250cc8eeb9805a948040381a9e93e14c571f62409725f683afb43bdf","observation_id":"92c21d98-db00-4d5f-8eea-4702228ae477","resolution":{"observed_at":"2026-08-07T00:23:00.923252Z","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":"2412.03552","last_updated":"2024-12-04T18:50:08Z","snapshot_observed_at":"2026-08-09T05:24:52.517595Z","submitted_at":"2024-12-04T18:50:08Z","title":"Imagine360: Immersive 360 Video Generation from Perspective Anchor","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.03552","snapshot_observed_at":"2026-08-07T00:22:55.015238Z","title":"Imagine360: Immersive 360 video generation from perspective anchor.arXiv preprint arXiv:2412.03552, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.015238Z"},"links":{"cited_paper":"/paper/2412.03552","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:78abcf4049504df5e83cc9c2722b62efbcf7125db07b418b4a5b575dbc2c33e0","observation_id":"08e313f8-ecab-473b-a5ab-c79c7d7c37e6","resolution":{"observed_at":"2026-08-07T00:22:55.015238Z","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":"2026-08-07T00:22:55.163913Z","title":"Segment anything","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.163913Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:fd7d8b42a6b384c87368156e64f57227a79f5a4fcad9a57d9b3993dd10389e16","observation_id":"aad441d2-a39b-4d6e-8477-3e56909f2363","resolution":{"observed_at":"2026-08-07T00:22:55.163913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12094","last_updated":"2025-03-15T11:41:33Z","snapshot_observed_at":"2026-08-07T17:02:04.605853Z","submitted_at":"2025-03-15T11:41:33Z","title":"E-SAM: Training-Free Segment Every Entity Model","version":1},"cited_work":{"arxiv_id":"2503.12094","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.12094","snapshot_observed_at":"2026-08-07T00:22:58.558456Z","title":"E-SAM: Training-Free Segment Every Entity Model","venue":"cs.CV","work_id":"8ddccd33-6dcb-4e44-a0cc-715bf84e8e61","year":2025},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.291778Z"},"links":{"cited_paper":"/paper/2503.12094","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:5c4497fc79f86c6c29b6e8901173b18c6d67a025a207bd9e239ee21eeb0bc5a1","observation_id":"4ee85755-71a1-4937-bd58-add4fa29e15d","resolution":{"observed_at":"2026-08-07T00:22:58.601228Z","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":"2026-08-07T00:23:00.709083Z","title":"Schwing, Alexander Kirillov, and Rohit Girdhar","venue":null,"work_id":"4ea484f9-c4da-422b-a730-5667af25875b","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.411924Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:2a6ba20475c0c162384703aede7038612a69a6d3ab62aa4549c484f20ccc3de0","observation_id":"4f7cbf1f-068a-4d3e-99be-c0a02b6dfde5","resolution":{"observed_at":"2026-08-07T00:23:00.781062Z","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":"2026-08-07T00:22:55.498293Z","title":"Schwing, and Alexander Kirillov","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.498293Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:75bc2b76087c41e8a88228c512a440ecb83d7fb51df4de7cd5c91a51fcfc9301","observation_id":"2389bea0-ac7a-4b09-b953-65a5ae613035","resolution":{"observed_at":"2026-08-07T00:22:55.498293Z","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":"2026-08-07T00:23:00.578326Z","title":"Omg-seg: Is one model good enough for all segmentation? InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 27948–27959, 2024","venue":null,"work_id":"583e1546-f945-418f-9d6c-d55074ac94f6","year":2024},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.605680Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:bec0bd2b45764d8e851540bb42814fb5dde31ea145482659805de76d9e80e425","observation_id":"231ceb61-b745-4761-bb72-5782681e1ca1","resolution":{"observed_at":"2026-08-07T00:23:00.629004Z","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":"2026-08-07T00:22:55.733093Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.733093Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:6c1b85bcffee241ce1071e9f86934366a17a9357d2c3e02741d05bda3fc27d66","observation_id":"944be81a-307a-40bc-942f-d7c15af473dd","resolution":{"observed_at":"2026-08-07T00:22:55.733093Z","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":"2026-08-07T00:23:00.459027Z","title":"Semantic understanding of scenes through the ade20k dataset.International Journal of Computer Vision, 127(3):302–321, 2019","venue":null,"work_id":"a3ee0b0a-3113-4f63-bf6b-b6a475060cca","year":2019},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.803030Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:670c7a47f1d2a0beeb4868d44b0348c464e12030b7275940dbd894149b727eee","observation_id":"c7d69616-e5f7-4caf-ba5f-8fbcd986c48c","resolution":{"observed_at":"2026-08-07T00:23:00.521545Z","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":"2026-08-07T00:22:55.888999Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.888999Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:19376eedc2b582f1888c2edfc986b9c392ca610acdc30f2db9b5574b38b0300d","observation_id":"2e32027b-75ed-4c3b-a538-89ccaaeee341","resolution":{"observed_at":"2026-08-07T00:22:55.888999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07256","last_updated":"2025-01-13T12:11:07Z","snapshot_observed_at":"2026-08-03T10:14:57.910041Z","submitted_at":"2025-01-13T12:11:07Z","title":"EdgeTAM: On-Device Track Anything Model","version":1},"cited_work":{"arxiv_id":"2501.07256","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.07256","snapshot_observed_at":"2026-08-07T00:22:58.435677Z","title":"EdgeTAM: On-Device Track Anything Model","venue":"cs.CV","work_id":"f5048b95-f60e-4418-a94a-ce78b3adcf8e","year":2025},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:55.958866Z"},"links":{"cited_paper":"/paper/2501.07256","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:3f00b9d82e4e99ecafbc8ace1220dbff8ca515db43c4cd92393f028c5024e0d1","observation_id":"68212246-3fd3-4cb3-8f5f-b51a55832f38","resolution":{"observed_at":"2026-08-07T00:22:58.507437Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:22:56.099146Z","title":"Sam2mot: A novel paradigm of multi-object tracking by segmentation.arXiv preprint arXiv:2504.04519, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.099146Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:b4f83a019c09d38d1c6e40233b54cb556462f4a14dce95273ef36759b86879e5","observation_id":"8bd98fa8-741e-4cd0-a0fe-e750603b1b46","resolution":{"observed_at":"2026-08-07T00:22:56.099146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T00:22:56.206226Z","title":"Gpt-4 technical report.arXiv preprint arXiv:2303.08774, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.206226Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:e1bbc795e9a3c333f409d16351fd13f601708c72ee741bd8ff4765741229a8da","observation_id":"e0014d18-0136-465d-943e-9bb9f9859aca","resolution":{"observed_at":"2026-08-07T00:22:56.206226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03048","last_updated":"2023-10-04T01:15:21Z","snapshot_observed_at":"2026-08-06T10:14:06.161139Z","submitted_at":"2023-05-04T17:59:36Z","title":"Personalize Segment Anything Model with One Shot","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.03048","snapshot_observed_at":"2026-08-07T00:22:56.344291Z","title":"Personalize segment anything model with one shot.arXiv preprint arXiv:2305.03048, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.344291Z"},"links":{"cited_paper":"/paper/2305.03048","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:dc97294bdc8b6261f40d2c6606b83bc5f69fe34c89c3a3517712ea1369483f7b","observation_id":"bd1525d8-a887-43ca-b199-8ba7e4e41105","resolution":{"observed_at":"2026-08-07T00:22:56.344291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01197","last_updated":"2023-12-03T23:57:43Z","snapshot_observed_at":"2026-07-06T15:49:47.586513Z","submitted_at":"2023-07-03T17:58:01Z","title":"Segment Anything Meets Point Tracking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01197","snapshot_observed_at":"2026-08-07T00:22:56.472923Z","title":"Segment anything meets point tracking.arXiv:2307.01197, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.472923Z"},"links":{"cited_paper":"/paper/2307.01197","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:252464af2dd4dd0e964eafc4b9f5702c08c8c6cb8c3beb9b2a64b60bc77d530f","observation_id":"618ebf3b-5551-4bdf-8149-05bb271a269b","resolution":{"observed_at":"2026-08-07T00:22:56.472923Z","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":"2026-08-07T00:22:56.563895Z","title":"A benchmark dataset and evaluation methodology for video object segmentation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.563895Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:501b05a71275c42dcdbb5169d8ffb57e69b32184a327c709f7ae2c2336d20b7e","observation_id":"bdb8656e-897a-4c91-9ff3-b5eb01142d43","resolution":{"observed_at":"2026-08-07T00:22:56.563895Z","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":"2026-08-07T00:23:00.383038Z","title":"Xmem: Long-term video object segmentation with an atkinson- shiffrin memory model","venue":null,"work_id":"20698a1d-6fd4-4020-9219-cb17565986a9","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.694456Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:c3a98882a9f8254a2ddc9d95d862f31a3cffa4bdd06de4ebc378051a69dec1d6","observation_id":"d73deb9f-aeef-4f28-861c-2caf8ae37b0f","resolution":{"observed_at":"2026-08-07T00:23:00.437304Z","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":"2026-08-07T00:23:00.280226Z","title":"Associating objects with transformers for video object segmentation.Advances in Neural Information Processing Systems, 34:2491–2502, 2021","venue":null,"work_id":"05e88bec-d181-4bd1-a829-32765f666904","year":2021},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.791227Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:1d46a5d3bc2e9a0bd6d9a99e596206795432c1a0f93020e54cdb7c2415383f12","observation_id":"af555073-3486-42df-89be-14d25a42f5a2","resolution":{"observed_at":"2026-08-07T00:23:00.317167Z","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":"2026-08-07T00:23:00.130197Z","title":"Siamx: An efficient long-term tracker using cross-level feature correlation and adaptive tracking scheme","venue":null,"work_id":"b630ebd8-d5d5-45aa-9073-d68901f83c6f","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:56.913363Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:516c5e41867b59d730ba708b04829505d0ea2c11a088bdbb31a8dc6276b1a236","observation_id":"ee084777-40d0-468a-9e44-e004a9a8bfcc","resolution":{"observed_at":"2026-08-07T00:23:00.211436Z","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":"2026-08-07T00:22:59.986517Z","title":"Aiatrack: Attention in attention for transformer visual tracking","venue":null,"work_id":"29acb75e-4b8e-4e02-8759-a67acb1fb6b6","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.024645Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:516edd35b024e91fdd5529fad5a6c36a5da6db0d414155e0da80e77b40b7e3d7","observation_id":"63f584fb-8841-4e70-b9c6-4d90d5978a12","resolution":{"observed_at":"2026-08-07T00:23:00.047737Z","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":"2026-08-07T00:22:59.921626Z","title":"Procontext: Exploring progressive context transformer for tracking","venue":null,"work_id":"ad94cde2-71b8-4b2b-910f-028c57897ce4","year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.142428Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:5513345b5755b3157cbf18b965fce0b18b893542821f14b5cdcafa092b3faa59","observation_id":"0ece874b-6082-4f21-9912-7a81a418d137","resolution":{"observed_at":"2026-08-07T00:22:59.925280Z","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":"2203.05328","last_updated":"2022-07-15T23:55:42Z","snapshot_observed_at":"2026-08-08T20:33:27.764159Z","submitted_at":"2022-03-10T12:20:58Z","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","version":2},"cited_work":{"arxiv_id":"2203.05328","doi":null,"metadata_source":"pith","pith_arxiv_id":"2203.05328","snapshot_observed_at":"2026-08-07T00:22:58.182099Z","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","venue":"cs.CV","work_id":"1e91892b-580c-41f9-b5c8-a8e451a627a3","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.229131Z"},"links":{"cited_paper":"/paper/2203.05328","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:3e9ffb3a969aa9336015db145fe82d235d28160192c57d81e893098a374c1b37","observation_id":"2068a037-4b76-4a78-9247-7ed121555190","resolution":{"observed_at":"2026-08-07T00:22:58.247446Z","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":"2026-08-07T00:22:59.853825Z","title":"Siamx: An efficient long-term tracker using cross-level feature correlation and adaptive tracking scheme","venue":null,"work_id":"d920982c-49b5-466a-9d94-c490e10f5e23","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.315517Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:1bab7572a7bbbbb8e11609972d92f57c70e323f65969017315cd75964a5ecaa6","observation_id":"087641a3-f792-4db5-8f1f-5cbfe7ec02e1","resolution":{"observed_at":"2026-08-07T00:22:59.884957Z","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":"1809.03327","last_updated":"2018-09-06T04:19:45Z","snapshot_observed_at":"2026-07-06T07:00:12.122241Z","submitted_at":"2018-09-06T04:19:45Z","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.03327","snapshot_observed_at":"2026-08-07T00:22:57.450779Z","title":"Youtube-vos: A large-scale video object segmentation benchmark.arXiv preprint arXiv:1809.03327, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.450779Z"},"links":{"cited_paper":"/paper/1809.03327","citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:62232069082f0694fd0cdf966c8f010cb167b38c7931bd4af8a03688e1cb3a34","observation_id":"afaa8d40-10ce-4a60-8327-f4b0eeb0b72a","resolution":{"observed_at":"2026-08-07T00:22:57.450779Z","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":"2026-08-07T00:22:59.767285Z","title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","venue":null,"work_id":"2fb2beab-b9b6-45dd-8414-6678278f9786","year":2021},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.588166Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:9d2e9ca2f8df909953e6168344259d348c0a690e2a7edc57888f2749c685d413","observation_id":"8fa477c3-07fe-4129-bda8-4713764a2b1a","resolution":{"observed_at":"2026-08-07T00:22:59.773121Z","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":"2026-08-07T00:22:59.627568Z","title":"Recurrent dynamic embedding for video object segmentation","venue":null,"work_id":"171f59f6-dc83-4a68-a618-26a33d9f5791","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.715822Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:54e1c00e3c2041ac2aecfccb37df984ec707b3754957ddf91a059771968e3f8e","observation_id":"1ec1e8bb-74a9-4ea4-a72c-4584b259b4f0","resolution":{"observed_at":"2026-08-07T00:22:59.682293Z","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":"2026-08-07T00:22:59.485802Z","title":"Xmem++: Production-level video segmentation from few annotated frames","venue":null,"work_id":"baa817de-31e3-4e8c-8582-2a40d575a16c","year":2023},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.766572Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:f88b6e121e95fce834343a14b7e379e2055b087ef6128d37c5a0007036f244ab","observation_id":"eccbcea3-f1d2-4fa8-8431-748a783b8405","resolution":{"observed_at":"2026-08-07T00:22:59.568125Z","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":"2026-08-07T00:22:59.373177Z","title":"Trackingnet: A large-scale dataset and benchmark for object tracking in the wild","venue":null,"work_id":"ba01587d-3765-4b8d-adad-9d8658dc5ebe","year":2018},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.772013Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:728705d00d07e9ec1bd75765d8c78534d90806308b8444a25b241035b3c6fe81","observation_id":"e366422b-cc4f-4d92-b38e-26d96297829d","resolution":{"observed_at":"2026-08-07T00:22:59.425042Z","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":"2026-08-07T00:22:59.258766Z","title":"Pct”: percentage of selected data.“Sel","venue":null,"work_id":"472c4406-82ae-4cc6-9c14-0384d7cd4cb8","year":2022},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.840459Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:331de385925dddb4964f5aed49a2ef8860c2a4ca182878860057385ae388edb0","observation_id":"175c3128-b6c2-4c55-b59b-99a4d097eae9","resolution":{"observed_at":"2026-08-07T00:22:59.287178Z","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":"2026-08-07T00:22:59.173827Z","title":"an uneven and unreasonable distribution of labels","venue":null,"work_id":"cbf87a17-7082-4f1e-bb66-0d1010bea43d","year":null},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:57.938891Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:6939736a17f9041bfe893d3d438cfc2cb5522a0c5e0730adbe430db530f28525","observation_id":"ece2e793-46d8-4fc7-9b2c-dcd0eb67bad1","resolution":{"observed_at":"2026-08-07T00:22:59.249662Z","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":"2026-08-07T00:22:59.096447Z","title":"penguin\" or","venue":null,"work_id":"dd041957-10ae-4260-acb5-e384c11fad1f","year":null},"citing_paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T00:22:58.067260Z"},"links":{"citing_paper":"/paper/2506.14271"},"observation_digest":"sha256:98b3b03d387f181363e82d2b1a0c9726021d09f306b92d359bbee325d089d65d","observation_id":"85f5739b-967a-4a42-bfb3-e9378a7853de","resolution":{"observed_at":"2026-08-07T00:22:59.165623Z","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"}}],"paper":{"arxiv_id":"2506.14271","last_updated":"2025-06-17T07:37:08Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T15:22:50.772049Z","submitted_at":"2025-06-17T07:37:08Z","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":5,"verified_fuzzy":33},"total_outbound_references":57},"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 10 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 3 inbound Pith citation observations for arXiv:2506.14271."}