{"as_of":"2026-08-09T19:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cf7231f6286c748f854ab28d36460e2337855ef674061ce3420c59ae0f9914e2","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T19:01:14.949549Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.17121/citation-record","integrity":"/paper/2607.17121/integrity","json":"/paper/2607.17121/citation-record.json","paper":"/paper/2607.17121"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1801.07481","last_updated":"2018-01-23T11:03:37Z","snapshot_observed_at":"2026-08-07T06:02:59.570517Z","submitted_at":"2018-01-23T11:03:37Z","title":"Survey on Emotional Body Gesture Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.07481","snapshot_observed_at":"2026-08-01T19:01:14.890570Z","title":"Survey on emotional body gesture recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.890570Z"},"links":{"cited_paper":"/paper/1801.07481","citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:05e48e655af85b005d365e7a63496bf385f77523dfc8a88fba5b886e86c3a35d","observation_id":"563ead22-830c-4aee-867e-ccc333547c32","resolution":{"observed_at":"2026-08-01T19:01:14.890570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1402.5047","last_updated":"2014-02-20T15:42:32Z","snapshot_observed_at":"2026-07-06T03:36:32.333089Z","submitted_at":"2014-02-20T15:42:32Z","title":"Real-time Automatic Emotion Recognition from Body Gestures","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1402.5047","snapshot_observed_at":"2026-08-01T19:01:14.893890Z","title":"Real- time automatic emotion recognition from body gestures,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.893890Z"},"links":{"cited_paper":"/paper/1402.5047","citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:6fde40f0eca1ae366faca0a7fea7b5f12b9ff36ec9cd1de2ddda50b41b7fe687","observation_id":"2342d618-6d26-4604-acef-f3306195e1b4","resolution":{"observed_at":"2026-08-01T19:01:14.893890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.18026","last_updated":"2025-07-24T01:58:57Z","snapshot_observed_at":"2026-08-07T18:55:34.922969Z","submitted_at":"2025-07-24T01:58:57Z","title":"Emotion Recognition from Skeleton Data: A Comprehensive Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.18026","snapshot_observed_at":"2026-08-01T19:01:14.896692Z","title":"Emotion recognition from skeleton data: A comprehensive survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.896692Z"},"links":{"cited_paper":"/paper/2507.18026","citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:ba755ab52fd4668e49421c334c877331790470012178f96828173197c3424f9a","observation_id":"b8fa7255-0992-4c7e-9ed2-d3fd67a1bf92","resolution":{"observed_at":"2026-08-01T19:01:14.896692Z","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":"2026-08-01T19:01:14.899414Z","title":"Asian emotional body movement database: Diverse Intercultural E- Motion Database of Asian Performers (DIEM-A),","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.899414Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:83415b4a26b992eedcdf6c12e45e6f0aa0650a572b3a37c9d243d77b0533c601","observation_id":"49dc3bfd-491a-4ead-842f-40bd58aeaf86","resolution":{"observed_at":"2026-08-01T19:01:14.899414Z","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":"2026-08-01T19:01:14.901788Z","title":"MMAC@ACII 2026 Challenge,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.901788Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:cad82a6ca64d3ea3ec4e37e320650afea0c3c752dc9a7e8f5d58e61d93d790bc","observation_id":"d04378e9-1acb-4de1-bffc-9caf3b486842","resolution":{"observed_at":"2026-08-01T19:01:14.901788Z","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":"2026-08-01T19:01:14.904322Z","title":"Human action recognition via dataset condensation,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.904322Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:1d9766d732776fc72108ce0b5005f2465a373ecc7dd515b7e8f22f511ebf6b72","observation_id":"0f3d7353-1105-42f9-8595-c48918705ce5","resolution":{"observed_at":"2026-08-01T19:01:14.904322Z","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":"2026-08-01T19:01:14.906737Z","title":"Few-shot human action anomaly detection via a unified contrastive learning framework,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.906737Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:d0b02d66f9f64b9ff13297e797b077eb36a3da1f24c9dbb344c59d4f4b5de7b9","observation_id":"d2ab6789-2425-414b-b87d-304fc61959d9","resolution":{"observed_at":"2026-08-01T19:01:14.906737Z","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":"2026-08-01T19:01:14.908867Z","title":"Orientation-aware leg movement learning for action-driven human motion prediction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.908867Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:d618a20d17a87de2f9762b893768368952802e82ba08d8a214059eea433b7f22","observation_id":"088ab420-ac3e-4e64-860e-e8d2e40f1db8","resolution":{"observed_at":"2026-08-01T19:01:14.908867Z","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":"2026-08-01T19:01:14.911125Z","title":"Spatial temporal graph convolutional networks for skeleton-based action recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.911125Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:19ccc49a34e30c385e2011ea856b6c874fbab7517ae8dbdcadfef385df68d10a","observation_id":"9abba628-fb51-4c54-b0b1-234c5c771195","resolution":{"observed_at":"2026-08-01T19:01:14.911125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.09443","last_updated":"2022-05-19T09:58:32Z","snapshot_observed_at":"2026-07-06T13:11:32.691554Z","submitted_at":"2022-05-19T09:58:32Z","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.09443","snapshot_observed_at":"2026-08-01T19:01:14.913119Z","title":"PYSKL: Towards good prac- tices for skeleton action recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.913119Z"},"links":{"cited_paper":"/paper/2205.09443","citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:e4b6151e8f147341902a021435480cd27ef64faaed9dd1e2a905696a93eb3be6","observation_id":"6c2ad2e5-7974-4ea0-ac73-f8f14da6e2bb","resolution":{"observed_at":"2026-08-01T19:01:14.913119Z","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":"2026-08-01T19:01:14.915621Z","title":"On the continuity of rotation representations in neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.915621Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:67756db182b027fc50bff3b78eaadc1e08da34baebaf6f5ecce114015f1335c9","observation_id":"b9f97320-52c6-4895-a157-4a978a6a95e3","resolution":{"observed_at":"2026-08-01T19:01:14.915621Z","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":"2026-08-01T19:01:14.917831Z","title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.917831Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:8afc6bdac0148388f1f129231d2d3f392d26872f48d15d9948795d34539e4da3","observation_id":"36e68b7f-9c81-4887-a235-ff758147a9ca","resolution":{"observed_at":"2026-08-01T19:01:14.917831Z","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":"2026-08-01T19:01:14.921160Z","title":"Skeleton-based action recog- nition with multi-stream adaptive graph convolutional networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.921160Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:5d9ac6c5105b18d063b3f55f93fc78581bcc925d60950180a685df22a1de0ad5","observation_id":"785c5cd0-36f1-4837-9f73-dc8bbb2f78b8","resolution":{"observed_at":"2026-08-01T19:01:14.921160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.05775","last_updated":"2022-08-11T12:12:07Z","snapshot_observed_at":"2026-08-03T17:59:41.693010Z","submitted_at":"2022-08-11T12:12:07Z","title":"PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.05775","snapshot_observed_at":"2026-08-01T19:01:14.923711Z","title":"PSUMNet: Unified modality part streams are all you need for efficient pose-based action recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.923711Z"},"links":{"cited_paper":"/paper/2208.05775","citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:b276fd68d46143edbe1bda31aa4ebeb1996b01acf69db724376c1c39a6d873ab","observation_id":"fe6345d2-a8bf-4dc6-b394-768dde6ab51e","resolution":{"observed_at":"2026-08-01T19:01:14.923711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03288","last_updated":"2023-12-06T04:36:58Z","snapshot_observed_at":"2026-08-09T02:23:06.166251Z","submitted_at":"2023-12-06T04:36:58Z","title":"STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03288","snapshot_observed_at":"2026-08-01T19:01:14.926086Z","title":"STEP CATFormer: Spatial-temporal effective body-part cross attention transformer for skeleton-based action recognition,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.926086Z"},"links":{"cited_paper":"/paper/2312.03288","citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:2050cf92618fe974850355580dfb426665345c315fe24b7f08944b2a3932e2da","observation_id":"cb086cd7-8cb2-42dc-b264-501111ef93b2","resolution":{"observed_at":"2026-08-01T19:01:14.926086Z","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":"2026-08-01T19:01:14.928635Z","title":"Frequency- guided multi-level human action anomaly detection with normalizing flows,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.928635Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:c1ed6499752ab033cefa58d6682d45e98fe201bf9521c1662a8000d44d5bbbfb","observation_id":"243a37b9-f9cf-4e15-ab55-e1ba07bea5ef","resolution":{"observed_at":"2026-08-01T19:01:14.928635Z","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":"2026-08-01T19:01:14.930881Z","title":"Label distribution learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.930881Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:da4e718d9ca82c91cdfd825629f3b4e58a819371152da1abb72901004d286d0c","observation_id":"72f128c2-6f35-4744-88de-25650e5467c8","resolution":{"observed_at":"2026-08-01T19:01:14.930881Z","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":"2026-08-01T19:01:14.932894Z","title":"When does label smoothing help?","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.932894Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:d232f767e57bf4744dae12f493ddeb298ce668b3ab214c1eef82c79f8835cedd","observation_id":"ed172963-0f1d-4e52-8c16-bc8cf39cb308","resolution":{"observed_at":"2026-08-01T19:01:14.932894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16071","last_updated":"2024-09-24T13:12:29Z","snapshot_observed_at":"2026-07-06T19:21:12.262008Z","submitted_at":"2024-09-24T13:12:29Z","title":"Learning with Confidence: Training Better Classifiers from Soft Labels","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16071","snapshot_observed_at":"2026-08-01T19:01:14.934918Z","title":"Learning with confidence: Training better classifiers from soft labels,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.934918Z"},"links":{"cited_paper":"/paper/2409.16071","citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:51a1bb322ca48c3ee7fbf1f501c4d8b73b71ec8e5b144cfc367ccca79a316189","observation_id":"36689358-d7ba-4339-a00c-a7b5070c3537","resolution":{"observed_at":"2026-08-01T19:01:14.934918Z","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":"2026-08-01T19:01:14.937570Z","title":"Learning to recognize per-rater’s emotion perception using co-rater training strategy with soft and hard labels,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.937570Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:73e56ca4e9eb7346aa8d9f7ec08d5dbcff499ed4d5da5ad46cde9c4a3c75d9b6","observation_id":"7ccf9b61-90e6-4539-9578-9641d2da7a01","resolution":{"observed_at":"2026-08-01T19:01:14.937570Z","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":"2026-08-01T19:01:14.940102Z","title":"Emotion profile refinery for speech emotion classification,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.940102Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:9e192a2cb6a509bf25f4664fb99c19815423a584908d5deb99e4fc6ddce674a1","observation_id":"fcbf59ab-6cbb-404a-ae51-4a60fe61aff7","resolution":{"observed_at":"2026-08-01T19:01:14.940102Z","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":"2026-08-01T19:01:14.942327Z","title":"End-to-end label uncertainty modeling in speech emotion recognition using bayesian neural networks and label distribution learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.942327Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:b20da1a899b51241f2dce23136707ecdca7b1e5a82ed9a3d5da7610f9ed8127e","observation_id":"dd97cdd8-bec1-4de2-9ab5-3cb63d51f6e1","resolution":{"observed_at":"2026-08-01T19:01:14.942327Z","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":"2026-08-01T19:01:14.947500Z","title":"Uncertainty-aware label distribution learning for facial expression recognition,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.947500Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:b20dde70b434ec3b00ff9115944c478966aba92f14583d5bef994b57ac90c1a8","observation_id":"9dbb727f-3e40-40ef-918f-4841630fc8b0","resolution":{"observed_at":"2026-08-01T19:01:14.947500Z","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":"2026-08-01T19:01:14.949549Z","title":"AmbER 2: Dual ambiguity- aware emotion recognition applied to speech and text,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T19:01:14.949549Z"},"links":{"citing_paper":"/paper/2607.17121"},"observation_digest":"sha256:96c14147ca702d3cc183fc5ef99673a393036b963c11fc16b69c5e0fd784eca0","observation_id":"6ddb163f-243c-4aa8-b49e-9dc3bedd3ff3","resolution":{"observed_at":"2026-08-01T19:01:14.949549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.17121","last_updated":"2026-07-19T08:13:31Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T06:29:47.334511Z","submitted_at":"2026-07-19T08:13:31Z","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":24},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.17121."}