{"as_of":"2026-08-19T15:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ca1723411dac8249b624946450db9b3388f7d4b36da2500e0c85b3e03504061a","coverage":[{"denominator":92,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":92,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T17:36:33.214505Z","state":"measured"},{"denominator":94,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":94,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T05:29:29.172448Z","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":"2026-05-13T19:58:11.989376Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.10897","snapshot_observed_at":"2026-08-03T05:29:29.172448Z","title":"Human-in-context: Unified cross-domain 3d human motion modeling via in-context learning.arXiv preprint arXiv:2508.10897, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.02401","last_updated":"2026-07-07T06:51:43Z","snapshot_observed_at":"2026-08-13T10:34:19.282675Z","submitted_at":"2026-02-02T17:59:01Z","title":"Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T05:29:29.172448Z"},"links":{"cited_paper":"/paper/2508.10897","citing_paper":"/paper/2602.02401"},"observation_digest":"sha256:c2e37dd9f05a3cdb79ca7da9671329ded905b29d0f2ce2171355b6fe7ebc049c","observation_id":"5ffbc221-2af1-4fc3-9a49-a61b4280d17a","resolution":{"observed_at":"2026-08-03T05:29:29.172448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"cited_work":{"arxiv_id":"2508.10897","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.10897","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Human-in-context: Unified cross-domain 3d human motion modeling via in-context learning","venue":null,"work_id":"6310ae9b-186c-4b4c-b339-abbdc1b2fbdc","year":2025},"citing_paper":{"arxiv_id":"2604.02845","last_updated":"2026-04-03T08:01:51Z","snapshot_observed_at":"2026-08-02T13:19:20.548556Z","submitted_at":"2026-04-03T08:01:51Z","title":"Deformation-based In-Context Learning for Point Cloud Understanding","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-13T19:57:08.451707Z"},"links":{"cited_paper":"/paper/2508.10897","citing_paper":"/paper/2604.02845"},"observation_digest":"sha256:5a6d416bedf0c35fd2c95a8e5d54a40039c2c5b034d8b6b73ef5d78f121fd48b","observation_id":"4808795d-35ad-42a0-882a-45353585adf6","resolution":{"observed_at":"2026-05-13T19:58:11.996724Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.10897/citation-record","integrity":"/paper/2508.10897/integrity","json":"/paper/2508.10897/citation-record.json","paper":"/paper/2508.10897"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:36:32.776600Z","title":"Enhanced skeleton visualization for view invariant human action recognition,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.776600Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:3477d93b5543cfd8817ee1cbd7c60ae00f7e79cec3effb413dd0ed84b80da07a","observation_id":"f2234ee6-dafd-46fd-a37c-0f5db742eae6","resolution":{"observed_at":"2026-08-15T17:36:32.776600Z","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":"2026-08-15T17:36:32.782714Z","title":"3d human pose estimation= 2d pose estimation+ matching,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.782714Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:448cdde8877ec05264513f1dc8660303999fb6f9094e451760507ab14df450db","observation_id":"4b9c7f81-fa6e-4925-8463-87c633696868","resolution":{"observed_at":"2026-08-15T17:36:32.782714Z","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":"2026-08-15T17:36:32.787608Z","title":"Pose2mesh: graph convolutional network for 3d human pose and mesh recovery from a 2d human pose,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.787608Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:4b7b85ede1ae5489af0b46d997c0824882123065640b7605bebf8329c9dfb6c9","observation_id":"da2ee21b-0fca-4357-9078-a540e263bbe5","resolution":{"observed_at":"2026-08-15T17:36:32.787608Z","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":"2026-08-15T17:36:32.792438Z","title":"Recognizing human actions as the evolution of pose estimation maps,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.792438Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:6d3594bee5d8473f1956fe6ed6030c1f4f717af0ee84289914d0259ae9ece9ea","observation_id":"fbbc0f2c-2d8d-428f-9b62-f7907d84ba26","resolution":{"observed_at":"2026-08-15T17:36:32.792438Z","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":"2026-08-15T17:36:32.797389Z","title":"Milnet: multiplex interactive learning network for rgb-t semantic segmentation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.797389Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:64785441f02589299139eabb304b2dab17f1b2f14214204eff0f186bde8a0879","observation_id":"2a50ac69-9789-421b-898a-1d123724ba1a","resolution":{"observed_at":"2026-08-15T17:36:32.797389Z","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":"2026-08-15T17:36:32.802616Z","title":"Dynamic dense graph convolutional network for skeleton-based human motion prediction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.802616Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:823c979241b1d4caf47c5a5d7a56b65b27275afa40eb88ee73b05a58bc34f8d4","observation_id":"a7002d79-835b-482f-a795-2ecf15cbadd8","resolution":{"observed_at":"2026-08-15T17:36:32.802616Z","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":"2026-08-15T17:36:32.808047Z","title":"Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.808047Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:3f66429e6c1c3d78c7882933b0c951b90a30cc6bcc1b76d2923c83bca7c5b3cb","observation_id":"d121e9e2-1ac7-40c8-838c-a59427f1e9ea","resolution":{"observed_at":"2026-08-15T17:36:32.808047Z","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":"2026-08-15T17:36:32.813478Z","title":"Tcpformer: learning temporal correlation with implicit pose proxy for 3d human pose estimation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.813478Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:a0d7d6a80d788335645982555b4dadb58dd864392f1fc204db1320d52bfb4c5c","observation_id":"c48b03aa-99e4-4a32-a1e1-378264fb9858","resolution":{"observed_at":"2026-08-15T17:36:32.813478Z","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":"2026-08-15T17:36:32.818283Z","title":"Hourglass tokenizer for efficient transformer-based 3d human pose estimation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.818283Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:a2447c6f4c70ca7873de32dd06f3437c1d62615a5efbd1702e66d5655da5e873","observation_id":"efdc6811-d3ed-4ba1-b849-729e945a7d1f","resolution":{"observed_at":"2026-08-15T17:36:32.818283Z","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":"2026-08-15T17:36:32.823165Z","title":"Feature boosting network for 3d pose estimation,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.823165Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:131fef9895a2da1be69416da18a5aa1075f27a15a7d48c66f9adbe6b6c4835bf","observation_id":"abec7183-60f0-440c-ab27-850da2a3e975","resolution":{"observed_at":"2026-08-15T17:36:32.823165Z","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":"2026-08-15T17:36:32.827977Z","title":"Arts: semi-analytical regressor using disentangled skeletal representations for human mesh recovery from videos,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.827977Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:2a01ab747c4be5dddd04a28a249ffd775b1c338ba1623db1bd1f03ff275c2575","observation_id":"4d1848ec-188a-459f-a387-49acf865db0d","resolution":{"observed_at":"2026-08-15T17:36:32.827977Z","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":"2026-08-15T17:36:32.833025Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.833025Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:4d9e050b043a8d7fdd910693bf1e10163eca4b84aeb5598022cd1452e0f11792","observation_id":"3c6b6d50-15af-491c-97cf-0dcf85c8723c","resolution":{"observed_at":"2026-08-15T17:36:32.833025Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-15T17:36:32.837808Z","title":"An image is worth 16x16 words: transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.837808Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:d4e38ec4725d63401309e16ab6d48aba2604eb1147fad3b351a6edf091a59ea6","observation_id":"96b0b821-a7a6-4557-9c9f-cb8a1a45c071","resolution":{"observed_at":"2026-08-15T17:36:32.837808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09417","last_updated":"2024-11-14T02:00:33Z","snapshot_observed_at":"2026-08-14T11:12:31.002605Z","submitted_at":"2024-01-17T18:56:18Z","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.09417","snapshot_observed_at":"2026-08-15T17:36:32.843433Z","title":"Vision mamba: efficient visual representation learning with bidirectional state space model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.843433Z"},"links":{"cited_paper":"/paper/2401.09417","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:8666ae7e448b760f348978a52210405a2887f92695c07f99b3e2008087ed3725","observation_id":"bf386c47-8156-41a1-84c9-f3bfd4949508","resolution":{"observed_at":"2026-08-15T17:36:32.843433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-15T17:36:32.848396Z","title":"Bert: pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.848396Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:db3f95b3d26f9fa44f4af530cb5647d5eac7760e0e8273298bad138e3a4d3ee6","observation_id":"ec706d76-1894-4980-ab49-df3a1b7c972c","resolution":{"observed_at":"2026-08-15T17:36:32.848396Z","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":"2026-08-15T17:36:34.695886Z","title":"Language models are few-shot learners,","venue":null,"work_id":"e0bbf0d6-a2bc-45b1-bfda-033bda4ced86","year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.853416Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:34e364512128b68beb35946ec3f153224c686a322ec3f83a3ee64a8dad986834","observation_id":"6d637a48-858f-44a3-9f84-2c5d03e130f3","resolution":{"observed_at":"2026-08-15T17:36:34.700427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.681815Z","title":"Spatial temporal graph convolutional networks for skeleton-based action recognition,","venue":null,"work_id":"965a54b2-02e0-40dd-8da1-283ba1948f5f","year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.858474Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:35071fe15c370aac874271f91885663b91bff3b74d42695709c1c8224d816bfe","observation_id":"b03bc53c-ada6-4357-b3d5-dc9575a25b2b","resolution":{"observed_at":"2026-08-15T17:36:34.686254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.667273Z","title":"Motionbert: a unified perspective on learning human motion representations,","venue":null,"work_id":"bb566318-5243-472f-8938-b5a3adc21fcc","year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.863404Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:8c509347970009b02f8056b1b220d644bccba5c2675c1aeae11237d67c058dc7","observation_id":"51ca7f08-3935-4ab6-8f16-8d7775c4f218","resolution":{"observed_at":"2026-08-15T17:36:34.672321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.639552Z","title":"Unified pose sequence modeling,","venue":null,"work_id":"c3f3c737-68a6-4b8a-888a-0482cca2455e","year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.873331Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:cd493ed565c1c066e79c04856671f0f7b04085d96ec535de012960fba3ac9139","observation_id":"b29937ce-19d0-4e8e-8231-a961e47014e6","resolution":{"observed_at":"2026-08-15T17:36:34.644652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.624056Z","title":"Large motion model for unified multi-modal motion generation,","venue":null,"work_id":"aba40917-2cc9-42ae-bf91-457205eae53e","year":2025},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.877797Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:20d6e46840e8303130b8772308ab8096746538a41eb8b25dc33eff92788c7dbd","observation_id":"b321b7c5-5832-4523-b7e3-3a055c08baab","resolution":{"observed_at":"2026-08-15T17:36:34.628872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.609950Z","title":"Unihcp: a unified model for human-centric perceptions,","venue":null,"work_id":"643123a4-4fce-48ed-9eb1-9046f02ae983","year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.882281Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:833b5d6592e76d532679e0f5653f6b1a937a094a3593b11f0989a33607755fa3","observation_id":"34ae6273-930f-4ebb-a379-c00bff8496ed","resolution":{"observed_at":"2026-08-15T17:36:34.614793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.595588Z","title":"Macdiff: unified skeleton modeling with masked conditional diffusion,","venue":null,"work_id":"f5c254c9-6b63-4f37-8bf2-b167b48c0527","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.886595Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:71b412b23766e89c7d0402490cfa77c2368d78b017af95b2e0aa86cf48594bc2","observation_id":"d7e9cc2c-0402-44d0-9737-088958a68ce8","resolution":{"observed_at":"2026-08-15T17:36:34.600362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.581752Z","title":"History repeats itself: Human motion prediction via motion attention,","venue":null,"work_id":"99f73a5b-1580-4c3c-8f0e-70bcebdb2e51","year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.891003Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:5acf139abb8a56b514c352baec5f66c4a05357e2513301acd148a27c3549b115","observation_id":"37d9d7df-fe86-42bd-acb6-c0928d4953b3","resolution":{"observed_at":"2026-08-15T17:36:34.586429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.567801Z","title":"Gcnext: towards the unity of graph convolutions for human motion prediction,","venue":null,"work_id":"c33ef41a-1aff-43b2-a499-65df3f156e3d","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.895430Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:e1b3c1a4c7371f2b5fe42a00e69555dc7729739ef5aff54457046e80ca67b1d9","observation_id":"e813fba3-e40e-4ab0-ba66-c251a5b89e42","resolution":{"observed_at":"2026-08-15T17:36:34.572534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.552454Z","title":"Towards accurate 3d human motion prediction from incomplete observations,","venue":null,"work_id":"118a4547-5cc7-4a7a-baf4-ae2acb298984","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.899908Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:a8dfe1ae25eff2c1eccb44f2cd935f691c51b4ee9f2dbd380b24557ed6e5273b","observation_id":"09c5bfd1-d94c-49e4-abe1-da24b53d089f","resolution":{"observed_at":"2026-08-15T17:36:34.557799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06804","last_updated":"2021-01-17T23:38:40Z","snapshot_observed_at":"2026-08-16T18:51:47.106761Z","submitted_at":"2021-01-17T23:38:40Z","title":"What Makes Good In-Context Examples for GPT-$3$?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06804","snapshot_observed_at":"2026-08-15T17:36:32.904301Z","title":"What makes good in-context examples for gpt-3?","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.904301Z"},"links":{"cited_paper":"/paper/2101.06804","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:2971200b4aacad4ba39ea968535b2a20bd15803c49006a3b544226628f62fa8b","observation_id":"c001674a-5665-4228-8f4c-64229b7284c6","resolution":{"observed_at":"2026-08-15T17:36:32.904301Z","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":"2026-08-15T17:36:34.538076Z","title":"What makes good examples for visual in-context learning?","venue":null,"work_id":"6c7011cf-a7b0-4224-b4bc-5cc655833b16","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.909599Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:b12f6b3de7d009154d10f0c989d520f468409f20e649688a7b48fbe28d3c3a16","observation_id":"5c9d2085-66ca-4888-b396-55d16a93f082","resolution":{"observed_at":"2026-08-15T17:36:34.542677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.523411Z","title":"Images speak in images: a generalist painter for in-context visual learning,","venue":null,"work_id":"5f027d68-dc5a-4b47-b246-1f6675b4c911","year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.913979Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:c8dcfe56e37949cfa798d3fa4cc75e7a9f8e92faae40484b2f5e696125c520b4","observation_id":"941d44bc-0ce0-4e77-a9c6-d25309e9d4fd","resolution":{"observed_at":"2026-08-15T17:36:34.528380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.509120Z","title":"Explore in-context learning for 3d point cloud understanding,","venue":null,"work_id":"4b83e8bb-4153-4417-81e1-8ead185e067d","year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.918484Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:5a4e561dac6cdd26d16fdb9bd7cc81ef0ec695ae758698e20b3e103ab55a9300","observation_id":"21ba3675-5d85-489c-9ee8-568ec4c39c57","resolution":{"observed_at":"2026-08-15T17:36:34.514022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.492342Z","title":"Skeleton-in-context: unified skeleton sequence modeling with in-context learning,","venue":null,"work_id":"48b78fbe-33f7-4d67-8582-5c07ec8bd191","year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.922769Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:f47445bf996a825e45061c2887bee3779b5c7d83dab503c75cff0b111e9252f1","observation_id":"958268ff-8ca2-4a8a-b5b6-bac1d3d6c128","resolution":{"observed_at":"2026-08-15T17:36:34.498802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.477845Z","title":"On human motion prediction using recurrent neural networks,","venue":null,"work_id":"f97a6eb5-5544-46f7-bbb3-93be0263152a","year":2017},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.927351Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:0fb36b1ecb0c02943b175f9fa42ca4e1162b5dd06c6e4ba2c6a76fa8455c5a2f","observation_id":"ccdd0062-2e61-4492-934a-e44244a24b2b","resolution":{"observed_at":"2026-08-15T17:36:34.482319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.462972Z","title":"Convolutional sequence to sequence model for human dynamics,","venue":null,"work_id":"8af4748a-22a0-4664-92b7-086e4dc25607","year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.931664Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:94021f7f9cbbac22bfd9641793204e5e50d59321f62ced8b6e7cf5ef15081e09","observation_id":"69598f5b-f8a0-43c2-b644-522e264599f9","resolution":{"observed_at":"2026-08-15T17:36:34.467782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.448180Z","title":"Multiscale spatio-temporal graph neural networks for 3d skeleton-based motion prediction,","venue":null,"work_id":"58b72384-d7a0-4eb5-bfeb-29efae814e28","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.936299Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:194c9078a0e212801a3e8c3702e6e0be566b388bc425f0f75491d57f617e7d2e","observation_id":"cc315047-919b-42a5-a863-6ea349f95b1c","resolution":{"observed_at":"2026-08-15T17:36:34.453089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.433152Z","title":"Learning trajectory dependen- cies for human motion prediction,","venue":null,"work_id":"39499a86-5bf5-4877-9c0d-7a07756dac68","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.940659Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:33c0d5ce8cdc620fd8b7aba1ac30434aaf88a275b4a3fea62d8a36a025efeed5","observation_id":"cef44e3c-d47d-47f9-a6fb-f7a26e77d735","resolution":{"observed_at":"2026-08-15T17:36:34.438004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.418397Z","title":"Spatiotemporal co- attention recurrent neural networks for human-skeleton motion prediction,","venue":null,"work_id":"153bc63a-68c8-4b9a-b3e0-a568bf336a6b","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.944882Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:faf03764fd634b7f62bf029d61d1ae8135f6a8193aa64a9cca380be256dbddca","observation_id":"5ad5db41-1888-4b45-8a92-3ea482347748","resolution":{"observed_at":"2026-08-15T17:36:34.423180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.403942Z","title":"A simple yet effective baseline for 3d human pose estimation,","venue":null,"work_id":"6e925390-d112-42e0-92f5-ef41ecbf782c","year":2017},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.949375Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:ceb3cf119a92f94620b442a62c0ade7920a7de13d52a73896362d0f60dd24441","observation_id":"1352af83-154a-4e51-a6f9-1ea3a36fe958","resolution":{"observed_at":"2026-08-15T17:36:34.408763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.389607Z","title":"Mixste: seq2seq mixed spatio-temporal encoder for 3d human pose estimation in video,","venue":null,"work_id":"b7e3de7e-140f-45cf-986e-16fb261687af","year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.953720Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:fea7020558c9e8153b9a1dd783a159c314eda4353b357b7a34f4cc39fcf74cc3","observation_id":"fc8c304f-c0a5-4bb6-ad88-e831860551b2","resolution":{"observed_at":"2026-08-15T17:36:34.394345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.375345Z","title":"Mhformer: multi- hypothesis transformer for 3d human pose estimation,","venue":null,"work_id":"044900ce-6e25-43a2-b954-91a0bbef6ba7","year":2022},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.959018Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:a8f0aef84937771ca4f7d0b51ef3697542e1a1556c7a8ec14abe4297a25070ff","observation_id":"6c8c58c0-afbe-4de4-ba7d-9c1cb4577015","resolution":{"observed_at":"2026-08-15T17:36:34.380010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.360625Z","title":"Diffpose: toward more reliable 3d pose estimation,","venue":null,"work_id":"5d13b384-1cc2-4d1b-bf97-c4add5bc98a1","year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.964357Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:2d4bcc4b25a9ba1c1bb29103d6ff0c50c0fc93dac9770408e9c6ee8d7973f798","observation_id":"34dc57c4-79d5-4e09-a425-2860570be418","resolution":{"observed_at":"2026-08-15T17:36:34.365353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.346052Z","title":"App: adaptive pose pooling for 3d human pose estimation from videos,","venue":null,"work_id":"e724274a-0f86-49df-b068-6c747ff8a08e","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.968870Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:a074edf8bedd9e98c37c9e49ddfe1faf9b01aa682ff5ecbafabb30f1dbfa399a","observation_id":"b4dabecc-d2b9-48c1-b6e5-08e3915daf91","resolution":{"observed_at":"2026-08-15T17:36:34.350790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.331137Z","title":"Finepose: fine-grained prompt-driven 3d human pose estimation via diffusion models,","venue":null,"work_id":"99b6421e-0e85-4aa5-9cc2-4f03468a0341","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.974218Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:c7c57b33eb05172c30dfa7b10ef78980a0d5732127bd3a09a04bf41e26357ca4","observation_id":"4bec8d95-9931-4f9b-a7b3-a05cdf7eb5cb","resolution":{"observed_at":"2026-08-15T17:36:34.336239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.316227Z","title":"Hybrik: a hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation,","venue":null,"work_id":"a53af6ec-4332-46bf-b3cb-2256dd649ff4","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.978902Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:1c044c2200b512ddab8cdd2144b6dfeaab37bae913e79543ace17ba1bc536bd1","observation_id":"465b2311-dac8-43c6-a95c-b21f44e9ce93","resolution":{"observed_at":"2026-08-15T17:36:34.321187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.300417Z","title":"Skeleton2mesh: kinematics prior injected unsupervised human mesh recovery,","venue":null,"work_id":"4eb962f8-a560-4c3e-950d-ddf83de265a1","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.983175Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:ba9a7f25976bd6bf11a175ae489687bc721cd1c47e9ac00209353c3644ecab63","observation_id":"229aad97-cb21-482f-be89-27e4c0ce0049","resolution":{"observed_at":"2026-08-15T17:36:34.305175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.285828Z","title":"Convolutional sequence generation for skeleton-based action synthesis,","venue":null,"work_id":"9cef3047-977d-41ba-9bf4-8eddabf1535c","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.988498Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:77c347c1e15ec2039971fd7d33e02352a23c6d16d3995fa29c9669f796f24b87","observation_id":"fe4b286f-76d0-476a-8924-01c6ed1db2f8","resolution":{"observed_at":"2026-08-15T17:36:34.290924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.08891","last_updated":"2020-05-28T05:36:46Z","snapshot_observed_at":"2026-08-09T11:44:11.824890Z","submitted_at":"2020-05-18T17:04:34Z","title":"Generative Tweening: Long-term Inbetweening of 3D Human Motions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.08891","snapshot_observed_at":"2026-08-15T17:36:32.993234Z","title":"Generative tweening: long-term inbetweening of 3d human motions,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.993234Z"},"links":{"cited_paper":"/paper/2005.08891","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:ecbbf0f16d9e8f60cafd356c09b408df1762ff85ba160b73f9b43a0eb6a34d25","observation_id":"d15e8113-9986-41e5-88df-78712f1e606f","resolution":{"observed_at":"2026-08-15T17:36:32.993234Z","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":"2026-08-15T17:36:34.270586Z","title":"Convolutional autoencoders for human motion infilling,","venue":null,"work_id":"fd8fde5d-6c0f-48b8-ab19-3987bc65da2c","year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.998346Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:96aabfa6738d7dcb5f5fc82645d8a20cba8cdc26fdb2a8809ebf9324b11cbd48","observation_id":"698a9f31-d72c-49ab-b83e-d04ee89e3d54","resolution":{"observed_at":"2026-08-15T17:36:34.275710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.255584Z","title":"Human motion prediction via spatio-temporal inpainting,","venue":null,"work_id":"6e48dd81-a3c2-4200-a381-1e36c9c43771","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.002759Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:e55dc7c9fc8e2a66adb27d9102b669928e6192f1cc283d8c8211a52f4f121329","observation_id":"75bc0eb0-0881-40f4-9e11-fd6092ee5f96","resolution":{"observed_at":"2026-08-15T17:36:34.260643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.239621Z","title":"Coupled action recognition and pose estimation from multiple views,","venue":null,"work_id":"b9ccb963-9cb5-4629-89e7-778ecc7ab983","year":2012},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.007119Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:5091d65c1f8f5ae3e21147fefb6d441053785066d2f6f6064edc3919a171797b","observation_id":"8d12a375-b6ef-4d92-85b2-cb4031f204dc","resolution":{"observed_at":"2026-08-15T17:36:34.244679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.224550Z","title":"SMPL: a skinned multi-person linear model,","venue":null,"work_id":"de0607a4-a8a1-46e8-8ee9-5b39d3fd1f17","year":2015},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.011937Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:86301d79db70b994e9797d5354176738876d55b5a5268b94bce0c8b872048658","observation_id":"0fa20059-9aa4-4be8-a84b-e69000053c79","resolution":{"observed_at":"2026-08-15T17:36:34.229367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.209115Z","title":"Keep it smpl: automatic estimation of 3d human pose and shape from a single image,","venue":null,"work_id":"f64ae0dc-d492-45aa-b1bf-3be01efffe1d","year":2016},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.017403Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:6c09e8282664824eb1b0f357f16789ac1e3bdafccbc8e31f816cf352fb29198b","observation_id":"9c0acd44-8cee-4334-8bed-2328e4032352","resolution":{"observed_at":"2026-08-15T17:36:34.214218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.192261Z","title":"Unsupervised learning of view-invariant action representations,","venue":null,"work_id":"399f9683-48f0-49d4-b0f5-25a3d68f709e","year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.022249Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:11edf5fb986f6e9d47d0bbc1710ac82b8ad43ce55a61a45ef10cfde8325f3c75","observation_id":"5ee82fdd-8b67-44cc-9f26-f2f34be607a2","resolution":{"observed_at":"2026-08-15T17:36:34.197664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.177113Z","title":"Motion guided 3d pose estimation from videos,","venue":null,"work_id":"78c3591b-7fea-4c67-8ffa-f2e646f6a2f0","year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.026623Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:35a22a7147de7e01b80dc25827411558e1387e0cc3c7ba35f818bcd0f1b9b58d","observation_id":"1673257c-c979-451c-8156-38ee36121916","resolution":{"observed_at":"2026-08-15T17:36:34.181970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.162001Z","title":"Human3. 6m: large scale datasets and predictive methods for 3d human sensing in natural environments,","venue":null,"work_id":"72b7b752-a80c-469b-a2ba-2e9669ec71ac","year":2013},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.031204Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:d2e7fd5791787611db242297168c85db0608b89badfcd7c19e1349451e00a6cb","observation_id":"09c253df-4757-4e23-890b-69039fd05a9b","resolution":{"observed_at":"2026-08-15T17:36:34.167412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.147128Z","title":"Recovering accurate 3d human pose in the wild using imus and a moving camera,","venue":null,"work_id":"7b004594-4776-4363-ad4b-0d1cca3e872a","year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.035576Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:df86e43ea7ddd1f1748b8fabc823c1fb38418ef9711478a5a87b5d17578cb8ed","observation_id":"79d580d8-3bab-4f80-94eb-fa0e9e93dabb","resolution":{"observed_at":"2026-08-15T17:36:34.151861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.132453Z","title":"Amass: archive of motion capture as surface shapes,","venue":null,"work_id":"322305a7-d0e3-415f-ad82-9968a7026377","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.039945Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:00dfa6b13029e416e7b02c41ab6e96e023f86342de1fd6596d82c78bf318552a","observation_id":"4b284715-f235-4aad-9cb9-9822e7e6eaf9","resolution":{"observed_at":"2026-08-15T17:36:34.137159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.118216Z","title":"Freeman: towards benchmarking 3d human pose estimation under real-world conditions,","venue":null,"work_id":"9ffe7de3-4afd-401b-9d4e-89e9c94917ed","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.044133Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:26334ee1767c791ab26f3a34c7b648b857686e1d72132eeea6018f705ace755e","observation_id":"76e1f000-4b66-4096-8043-73f1126f787f","resolution":{"observed_at":"2026-08-15T17:36:34.122712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.102691Z","title":"Ntu rgb+ d: a large scale dataset for 3d human activity analysis,","venue":null,"work_id":"7ce472f7-5dcf-411b-8e31-63044b7e9b11","year":2016},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.048927Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:1fecc250cccd5e83d82012fea9be83faa137a9496a0f8e976907b1df1837ca62","observation_id":"5926cb96-246c-446e-adde-60b35539f9b0","resolution":{"observed_at":"2026-08-15T17:36:34.107823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.087415Z","title":"Ntu rgb+ d 120: a large-scale benchmark for 3d human activity understanding,","venue":null,"work_id":"a5026dd4-d040-4974-a3c4-23573bf2ad29","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.054414Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:12b4abc47e1ea5c0e7c8d46b5a04341731e5d469b67f829bbfd4073f5287c327","observation_id":"4a071d6d-5357-4651-89ec-d43fd002eb15","resolution":{"observed_at":"2026-08-15T17:36:34.092245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.071960Z","title":"Disentangling and unifying graph convolutions for skeleton-based action recognition,","venue":null,"work_id":"a1c05885-73e8-496e-8f3a-7f210b0f2594","year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.058996Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:f2108d950f1f7b115841e1ecaf0c43b5c9458c1bd0bf0240a0f4f2d2ca357d4c","observation_id":"c9339566-c42f-4990-a0a9-40f6e13705b9","resolution":{"observed_at":"2026-08-15T17:36:34.076844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.056716Z","title":"Vg4d: vision- language model goes 4d video recognition,","venue":null,"work_id":"e049a7ea-d556-4570-bc09-8d4832ad3ea1","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.063540Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:81f4acfb23af2e2a17e32c8373b5d60e20d897ec1ecf8d3d45044c78aed1c9f0","observation_id":"8902fd96-a278-4cc9-96b7-3d4bac2f63c5","resolution":{"observed_at":"2026-08-15T17:36:34.061638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.041655Z","title":"A comprehensive study of weight sharing in graph networks for 3d human pose estimation,","venue":null,"work_id":"5f9d9076-a52f-4f71-aa8d-a4053ab34d86","year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.067928Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:ce615a4666551a2fdd100a71421e1f0b9996b4f66381b22d0a15e55c969958c5","observation_id":"f55d2071-0ffb-4ee4-9114-443819550db7","resolution":{"observed_at":"2026-08-15T17:36:34.046662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.027044Z","title":"Progressively generating better initial guesses towards next stages for high-quality human motion prediction,","venue":null,"work_id":"caced736-3d76-4096-8a1c-cc43bda24d3e","year":2022},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.072308Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:28a057920e6592b84f65c6d28b8365289c8a6d149dfc6afa381f3941656f4598","observation_id":"9ae664b1-a258-4ab3-9ab4-8a5f5c6d3076","resolution":{"observed_at":"2026-08-15T17:36:34.031940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.012104Z","title":"Graph stacked hourglass networks for 3d human pose estimation,","venue":null,"work_id":"94c6f765-33ff-4f06-b8a6-53a87ab267b3","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.076823Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:3a677a8766cb0fc2d58d93245fe5cd42ba238910ec1435983c9eab1509b15015","observation_id":"2dcf241b-0530-4d07-8c28-84146619e7db","resolution":{"observed_at":"2026-08-15T17:36:34.017162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.996830Z","title":"Back to mlp: a simple baseline for human motion prediction,","venue":null,"work_id":"a2ac3832-5dbc-46c4-ad33-ba06071edf92","year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.081404Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:223a16b55232951e83cd60cd27585db3f580a5d8a48d0ca18835aa7f83b0577e","observation_id":"1123d608-5cb4-47f8-b850-8c8934311254","resolution":{"observed_at":"2026-08-15T17:36:34.001620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.981269Z","title":"3d human pose estimation in video with temporal convolutions and semi-supervised training,","venue":null,"work_id":"0f17a7ec-dc7e-4061-bb05-6b4615018293","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.086684Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:e859b926a5d6105e9c1110fef3ba2ca06b808fd9d5d5593438ece7cefacdd437","observation_id":"93cf7b89-bcb8-4c72-bc13-3c23f4c01524","resolution":{"observed_at":"2026-08-15T17:36:33.986124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.966357Z","title":"Co- occurrence feature learning for skeleton based action recognition using regularized deep lstm networks,","venue":null,"work_id":"ee87ee41-96c7-4dbe-81dd-dba9bfe5c24e","year":2016},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.091550Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:90e823f9ba958a9714f461cdd8c1c6754c0f3131d988f5ce4dca0bfbe245e36a","observation_id":"d812e2ca-d1f5-4dcf-b722-5adcc1f98092","resolution":{"observed_at":"2026-08-15T17:36:33.971243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.951514Z","title":"Spatio-temporal lstm with trust gates for 3d human action recognition,","venue":null,"work_id":"3486c6f0-8fb7-4fad-8ae9-4a2d0bc9df53","year":2016},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.097477Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:fb65c5d9ee49a0d30873bf493b4c71c4d2aa4b08bc487474e77e2361a9d85ce9","observation_id":"3a179ec5-2435-4001-a86a-b1d76cb588be","resolution":{"observed_at":"2026-08-15T17:36:33.956141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.937863Z","title":"Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks,","venue":null,"work_id":"01e4dbe3-b04b-45f4-b0f5-9b9f65bdb4c0","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.102137Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:a9ca6597a1912033dd7674240442a4834282fee17857d011107d2aed888b1c44","observation_id":"e6ce61b4-7998-4d85-99e1-6cc3ab76b2b1","resolution":{"observed_at":"2026-08-15T17:36:33.942375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.923550Z","title":"Learning dynamic relationships for 3d human motion prediction,","venue":null,"work_id":"9b3f8c25-ed99-4914-b500-7733fd9a4715","year":2020},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.106815Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:19d206e3e81a04a75ad14fc902d0a0fdd48c0504a807b829a8ef7dc7185f6761","observation_id":"f66cf77c-7716-4be0-8b5b-28e4b9649e8e","resolution":{"observed_at":"2026-08-15T17:36:33.928248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.909672Z","title":"3d human pose estimation with spatial and temporal transformers,","venue":null,"work_id":"6bcf0d76-206f-4abf-b19e-a65c0c3270ac","year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.112282Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:d3e5b47dad8454d529c627205e60110cdc2eb93a9135a93a10e084390fbd3291","observation_id":"617b3566-bdf9-4e40-941e-0f853ef2a8d4","resolution":{"observed_at":"2026-08-15T17:36:33.914303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.895824Z","title":"Graformer: graph-oriented transformer for 3d pose estimation,","venue":null,"work_id":"9b0b45f8-1487-40ed-bcd8-f647ddc74278","year":2022},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.116907Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:ef3aaea6a6021c6f99bd1380cfa196bd067c076f5dcb14a7dc4a4da8e31a7976","observation_id":"17c609b1-5e7f-4f4f-ad14-0324f8b184c9","resolution":{"observed_at":"2026-08-15T17:36:33.900458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.881873Z","title":"Motionagformer: enhancing 3d human pose estimation with a transformer-gcnformer network,","venue":null,"work_id":"eee08fda-607d-47f4-ad5d-93e7dd747e91","year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.121710Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:eafe05bcaf58a57281c9f69bb486293471939eec5b4132db63b5d95f69709265","observation_id":"73f99403-e17c-46c4-9837-1b25946377ef","resolution":{"observed_at":"2026-08-15T17:36:33.886426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-08-17T20:47:46.242385Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-15T17:36:33.126609Z","title":"Mamba: linear-time sequence modeling with selective state spaces,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.126609Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:e893da8fa735e33914e406b70a765ed0d48ed5d432482628cf3e6b5955d3665b","observation_id":"64a660f3-39d9-40f3-9bf8-478469c56129","resolution":{"observed_at":"2026-08-15T17:36:33.126609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.02922","last_updated":"2025-02-26T03:17:49Z","snapshot_observed_at":"2026-08-16T13:28:18.358174Z","submitted_at":"2024-08-06T03:15:18Z","title":"Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.02922","snapshot_observed_at":"2026-08-15T17:36:33.131548Z","title":"Pose magic: efficient and temporally consistent human pose estimation with a hybrid mamba- gcn network,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.131548Z"},"links":{"cited_paper":"/paper/2408.02922","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:2a875d98281c23482d2aab3c051f91f9bf713f3b8b238aeb7556b3721805235b","observation_id":"a976ad5a-181f-4238-ae9a-9b398d03db53","resolution":{"observed_at":"2026-08-15T17:36:33.131548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07645","last_updated":"2024-04-11T11:07:57Z","snapshot_observed_at":"2026-08-16T14:01:48.042355Z","submitted_at":"2024-04-11T11:07:57Z","title":"Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07645","snapshot_observed_at":"2026-08-15T17:36:33.137387Z","title":"Simba: mamba augmented u-shiftgcn for skeletal action recognition in videos,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.137387Z"},"links":{"cited_paper":"/paper/2404.07645","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:2de48f992ce4d502c3103a3bb3b517161d39a107c1c8e28a65184765678f2689","observation_id":"5cd1ee38-c0fd-4a69-a0e7-b74ceb9a8fa5","resolution":{"observed_at":"2026-08-15T17:36:33.137387Z","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":"2026-08-15T17:36:33.868412Z","title":"Omg-seg: is one model good enough for all segmentation?","venue":null,"work_id":"1a94bd6c-4d45-4da0-8bef-314deba5daa2","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.142919Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:577779a2926debe7ba66144149ec02d38e5793d9b7a17ac492a8a9f3a75c8bc4","observation_id":"beb3cd44-ab18-493d-a34b-d2c53bf2b91d","resolution":{"observed_at":"2026-08-15T17:36:33.872885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.854802Z","title":"Seggpt: towards segmenting everything in context,","venue":null,"work_id":"05a00ff8-b6ce-41e0-8009-6a9f755aadc3","year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.147464Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:c929ea73183aa24e07c54a41d567dd29c9b8d26f257c3bbdb33b474efe5b9a2d","observation_id":"d26f3f1f-f117-45b5-8aec-1af7ce36af71","resolution":{"observed_at":"2026-08-15T17:36:33.859384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.840446Z","title":"Learning to reconstruct 3d human pose and shape via model-fitting in the loop,","venue":null,"work_id":"c9fd76b4-e046-4e4a-9886-7ea01c1af827","year":2019},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.153051Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:3dff67ceb4a48192ae55274ce3f14782ede06e0d9c6175ae27ef9d69b032fcc3","observation_id":"3ad8f957-958a-40a7-8dad-15f7c65d3ce2","resolution":{"observed_at":"2026-08-15T17:36:33.845145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.825740Z","title":"2d/3d pose estimation and action recognition using multitask deep learning,","venue":null,"work_id":"5e0925b5-c4bb-4427-a643-cbe7ea4143cd","year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.157440Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:6bd14144743df917aee7215df78d379d6b681eb2cb4e2d88e9158f220cef33c7","observation_id":"43d5e94f-bd20-4b01-97bd-d34d1d9c32e4","resolution":{"observed_at":"2026-08-15T17:36:33.830670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.811076Z","title":"A unified 3d human motion synthesis model via conditional variational auto-encoder,","venue":null,"work_id":"4789f784-0648-4548-aaea-dc20c9fd38e2","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.162669Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:079a057c3e13e73dc038a496ec5509685adcc6285b80d285dc8b129e84341f3f","observation_id":"c32b1851-7cee-4741-aec2-103370443433","resolution":{"observed_at":"2026-08-15T17:36:33.815717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.08633","last_updated":"2022-05-08T05:17:15Z","snapshot_observed_at":"2026-08-18T14:41:38.679885Z","submitted_at":"2021-12-16T05:17:56Z","title":"Learning To Retrieve Prompts for In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.08633","snapshot_observed_at":"2026-08-15T17:36:33.167288Z","title":"Learning to retrieve prompts for in-context learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.167288Z"},"links":{"cited_paper":"/paper/2112.08633","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:a215d2f348e3ca5d66babe980f3d82beb04b1025d37584dddba4a4c47c0721e0","observation_id":"050e2942-5ebe-43e6-8be5-c6b8d60d8e73","resolution":{"observed_at":"2026-08-15T17:36:33.167288Z","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":"2026-08-15T17:36:33.796938Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"59f41c4e-0b5c-40eb-8efd-e524e63797fc","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.171865Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:4a155d1fde25db47df1222f8bbc1f32dc1f012c9652ff4f73ec2ad176a3abd70","observation_id":"3ddf966e-6d26-4663-84fc-07562f836212","resolution":{"observed_at":"2026-08-15T17:36:33.801631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.01115","last_updated":"2023-10-18T21:56:31Z","snapshot_observed_at":"2026-08-16T15:36:25.191825Z","submitted_at":"2023-05-01T23:03:37Z","title":"In-Context Learning Unlocked for Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.01115","snapshot_observed_at":"2026-08-15T17:36:33.176358Z","title":"In-context learning unlocked for diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.176358Z"},"links":{"cited_paper":"/paper/2305.01115","citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:69ef2a93ae4e0b4bd9c8444af1312018ae5519566d813ee3ceaf59b7f1554d33","observation_id":"af196910-2a15-4e4d-96ac-42bc8d1ae89a","resolution":{"observed_at":"2026-08-15T17:36:33.176358Z","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":"2026-08-15T17:36:33.782527Z","title":"Visual prompting via image inpainting,","venue":null,"work_id":"34b19157-08e0-42af-92c9-2017333ed0ab","year":2022},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.182216Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:b44835478272ecb2292aeb7c66e3eb94c6efcddfa274cadf1ea6db2172c5ae29","observation_id":"36a8222a-7f05-4915-aad5-f97852e8da3c","resolution":{"observed_at":"2026-08-15T17:36:33.787305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.766568Z","title":"Explore in-context segmentation via latent diffusion models,","venue":null,"work_id":"066899b8-5990-4d22-b555-aff913c49702","year":2025},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.187239Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:20b45c29563b80157734973e25e31b59fff988bbf90d873a80b65165f038aea1","observation_id":"96b51abc-e8dc-4d0e-828f-5c50e44cfc2a","resolution":{"observed_at":"2026-08-15T17:36:33.771610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.750999Z","title":"Towards large-scale 3d representation learning with multi-dataset point prompt training,","venue":null,"work_id":"3f7abfe6-6dbb-4f94-b0c8-12551cf503ad","year":2024},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.191933Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:b739f05c8da5b1cebfa51faa38638d686e78e78c7d68e296925db94874eb8fce","observation_id":"5bd2917e-76fa-4a3c-b4f7-a75115614151","resolution":{"observed_at":"2026-08-15T17:36:33.755852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.196620Z","title":"Exploring effec- tive factors for improving visual in-context learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.196620Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:be1d6eb91d314094be0e4e4297831d499d83043d8450e1b6c903309a6044819f","observation_id":"07377822-500e-4326-91ba-ecdc7e7e790c","resolution":{"observed_at":"2026-08-15T17:36:33.196620Z","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":"2026-08-15T17:36:33.736793Z","title":"Mosh: motion and shape capture from sparse markers","venue":null,"work_id":"5a8d4c75-5b59-43f9-8634-00ded3678127","year":2014},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.201179Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:ba0d1b2a5359b7417b452f922bd135e5d382564c7a2f1ac01ee692ddf87df037","observation_id":"af5435d5-86cc-4e28-a71f-dab41346e8d9","resolution":{"observed_at":"2026-08-15T17:36:33.741525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.722307Z","title":"End-to-end recovery of human shape and pose,","venue":null,"work_id":"62862fe6-167b-4b0b-b897-379cc9393fe7","year":2018},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.205864Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:e74aa08f5d42e9a413132d0aac2aeb83e24eee0dfcc5f965f248396f69eff1e9","observation_id":"1c86798c-4f2e-45ae-bf97-7867659da004","resolution":{"observed_at":"2026-08-15T17:36:33.726808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.707380Z","title":"Pymaf: 3d human pose and shape regression with pyramidal mesh alignment feedback loop,","venue":null,"work_id":"3b1debc7-7af4-4f3b-866e-9e62b09f6ec8","year":2021},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.210218Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:70a2c880c4b1bdd19ad876358b8eaf73ccb78b440b2f904bde8bf2b7cf51c318","observation_id":"f2c0bbc6-8a48-4050-849a-726bf76f6de1","resolution":{"observed_at":"2026-08-15T17:36:33.712347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:33.577408Z","title":"3d human pose estimation via non-causal retentive networks,","venue":null,"work_id":"6aab5d57-b04e-4868-a2ac-fe01cae1b0be","year":2025},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:33.214505Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:6f0dba91ba09126bb9dbd57013dca293a4c00d95334dc357758a873a0e413d97","observation_id":"23310898-392b-403d-94f4-2845505148d9","resolution":{"observed_at":"2026-08-15T17:36:33.584061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:36:34.654051Z","title":null,"venue":null,"work_id":"fed09365-3375-4236-a715-2da4cfa73710","year":null},"citing_paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T17:36:32.868723Z"},"links":{"citing_paper":"/paper/2508.10897"},"observation_digest":"sha256:b69d46df07b2da890a9e0ddd46cd8870855abe1d76d686521d5d4cabf99872ef","observation_id":"2f53832f-e6b1-4184-8dea-fa1621a6ba88","resolution":{"observed_at":"2026-08-15T17:36:34.658235Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.10897","last_updated":"2025-08-14T17:59:23Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T17:27:34.998439Z","submitted_at":"2025-08-14T17:59:23Z","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning"},"reference_resolution":{"displayed":92,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":23,"verified_exact":0,"verified_fuzzy":68},"total_outbound_references":92},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 92 of 92 outbound references and 2 inbound Pith citation observations for arXiv:2508.10897."}