{"as_of":"2026-08-16T13:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a847d62667d62a6eced5f88daaf4827bd817036c5572da4b18592f41c0d17269","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T17:46:47.327709Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:58:57.767017Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-15T22:58:58.026974Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"cited_work":{"arxiv_id":"2412.08507","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.08507","snapshot_observed_at":"2026-08-15T22:58:58.026974Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","venue":"cs.HC","work_id":"5fd99ae6-3afa-4d0b-a9f2-3a039b165f0a","year":2024},"citing_paper":{"arxiv_id":"2505.06325","last_updated":"2025-05-09T06:17:46Z","snapshot_observed_at":"2026-08-15T22:53:18.648265Z","submitted_at":"2025-05-09T06:17:46Z","title":"Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:58:57.767017Z"},"links":{"cited_paper":"/paper/2412.08507","citing_paper":"/paper/2505.06325"},"observation_digest":"sha256:b4172e2850d8610e5905ae1497e8e7637ca9f35c33a70bbd81f2f7856090d556","observation_id":"dc0a58ea-00e2-4b0d-af36-ff5082f59d0a","resolution":{"observed_at":"2026-08-15T22:58:58.031350Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.08507/citation-record","integrity":"/paper/2412.08507/integrity","json":"/paper/2412.08507/citation-record.json","paper":"/paper/2412.08507"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:46:47.134349Z","title":"A survey on human activity recognition using wearable sensors,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.134349Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:4e6c18f82e1950dae87ef8871664b7c8e159e0eb190cf0df9b3e3d6eb08feb58","observation_id":"4e4ba62a-b323-4700-9cc9-6cdaf940c9f0","resolution":{"observed_at":"2026-08-11T17:46:47.134349Z","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":"2026-08-11T17:46:47.140961Z","title":"Deep learning for sensor-based activity recognition: A survey,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.140961Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:99826898b1c256e3665602bbdd7b04b0e1247de79b38dc67a90f28a43c208ee2","observation_id":"d584b154-d8da-499a-8737-b24dc3606bb5","resolution":{"observed_at":"2026-08-11T17:46:47.140961Z","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":"2026-08-11T17:46:47.977924Z","title":"Activity recognition us- ing cell phone accelerometers,","venue":null,"work_id":"c09d0f2a-197a-47ff-a3d5-432c54f85276","year":2011},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.147648Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:2fc322b5ca2ca8fa94b3dbf67391e774f36df5c2cd43cf60073604d47253e90b","observation_id":"e76ad806-208a-4357-8290-827e32d95a67","resolution":{"observed_at":"2026-08-11T17:46:47.985202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.153595Z","title":"imove: Exploring bio-impedance sensing for fitness activity recogni- tion,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.153595Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:7fffcee539d5241c54947a8dd8b4ba38d067299feeeb9d19bfcd05f253994752","observation_id":"87d9bbfb-7c39-4b53-872d-361ed7371b1e","resolution":{"observed_at":"2026-08-11T17:46:47.153595Z","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":"2026-08-11T17:46:47.939490Z","title":"Embedding textile capacitive sensing into smart wearables as a versatile solution for human motion capturing,","venue":null,"work_id":"20b7250b-ff22-42e2-b55b-0a8c11c0effa","year":2024},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.162692Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:098018033ce439d2ba38450bab45c287936980e5fba085b346ae818cc2bf7349","observation_id":"efc95809-4392-4c61-a2a8-71f509dd1d0f","resolution":{"observed_at":"2026-08-11T17:46:47.947924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.170504Z","title":"The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.170504Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:fd2d8b5aae4a584eef7d292fc098bb4c87722525e7334ffef8821234f6766549","observation_id":"9e7bac83-8b68-4da2-8c25-8bb8b9bc5f8d","resolution":{"observed_at":"2026-08-11T17:46:47.170504Z","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":"2026-08-11T17:46:47.901228Z","title":"A survey of methods for explaining black box models,","venue":null,"work_id":"0599a3be-3f70-4aa3-807b-25959fbcca97","year":2018},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.178270Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:f57e066d4735afb1d11ed024887034da4d6e8299a3977b22efaf7ce6a76e9cea","observation_id":"3ae9c5fe-bbf5-4cee-b112-6ef78186abd0","resolution":{"observed_at":"2026-08-11T17:46:47.909292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.185004Z","title":"” why should i trust you?","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.185004Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:3133fc74afc25d52a233df2eb595dd8146178dd7f9f8bfcab4cbe56a3fe68019","observation_id":"3bed1c67-b74a-4c92-9f9e-78e764948255","resolution":{"observed_at":"2026-08-11T17:46:47.185004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01851","last_updated":"2024-10-05T06:13:26Z","snapshot_observed_at":"2026-08-13T04:49:27.393232Z","submitted_at":"2024-01-03T17:44:17Z","title":"The Power of Training: How Different Neural Network Setups Influence the Energy Demand","version":4},"cited_work":{"arxiv_id":"2401.01851","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.01851","snapshot_observed_at":"2026-08-11T17:46:47.488337Z","title":"The Power of Training: How Different Neural Network Setups Influence the Energy Demand","venue":"cs.LG","work_id":"903520d8-4927-4c53-b714-b30eeb5e91fd","year":2024},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.191975Z"},"links":{"cited_paper":"/paper/2401.01851","citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:c2754b7b3facf41ef15760a005fe276f9a73696001e9f4d11754679bc0ec776c","observation_id":"20e616b7-f2d9-4f73-b760-966572965bd6","resolution":{"observed_at":"2026-08-11T17:46:47.497277Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08608","last_updated":"2017-03-02T19:32:10Z","snapshot_observed_at":"2026-08-13T03:10:58.738032Z","submitted_at":"2017-02-28T02:19:20Z","title":"Towards A Rigorous Science of Interpretable Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.08608","snapshot_observed_at":"2026-08-11T17:46:47.199011Z","title":"Towards a rigorous science of interpretable machine learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.199011Z"},"links":{"cited_paper":"/paper/1702.08608","citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:46e9cfa99dde2fae4e0e9706e04ad75ccf003e61db6d941f4a0497bf182ced5b","observation_id":"eb45a585-ff35-4e8b-be80-e4cb96de1a79","resolution":{"observed_at":"2026-08-11T17:46:47.199011Z","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":"2026-08-11T17:46:47.863920Z","title":"Interactive slice visualiza- tion for exploring machine learning models,","venue":null,"work_id":"07816b76-ddce-414a-bd29-90a236e51e7e","year":2021},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.205564Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:65c21c3f0f1cda1b6051b3c2535887dfcac429f74e317a0baf81b1d52731c8a4","observation_id":"6e9c929e-f617-4f6b-9540-37fa6bf2c9fc","resolution":{"observed_at":"2026-08-11T17:46:47.872524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.838770Z","title":"Latent inspector: an interactive tool for probing neural network behaviors through arbitrary latent activation,","venue":null,"work_id":"d6361659-84df-4fdd-9fb1-bd6b0d48bfc7","year":2023},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.211497Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:ad6c2536857c9dfab3328226ef0abee3af3a73d42778eda0f847deb1f4242ce7","observation_id":"8c728ae8-1f01-4163-8d73-4bb9386d57c8","resolution":{"observed_at":"2026-08-11T17:46:47.848084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.813261Z","title":"Visualizing dataflow graphs of deep learning models in tensorflow,","venue":null,"work_id":"3d50420a-1510-4f7d-965f-bf8c4731dbf0","year":2018},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.217120Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:7a256805b33ba8441d20850fc6d23ee619a429f536ba236156411014527b8048","observation_id":"e98aa0a1-fa7b-4cda-b890-afcdf369270c","resolution":{"observed_at":"2026-08-11T17:46:47.821888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.790786Z","title":"Visualizing the hidden activity of artificial neural networks,","venue":null,"work_id":"72eb8701-8ad7-4290-bcf3-55f270096159","year":2017},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.222728Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:d4e653b862cf7279ed98b824f820eda56a2093b3828a4f436d94697b8af54e8b","observation_id":"6d60d628-f86b-4cb6-bf86-565a883e4cfe","resolution":{"observed_at":"2026-08-11T17:46:47.796473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.770368Z","title":"Visual human+machine learn- ing,","venue":null,"work_id":"9a53818a-20fc-48bc-8f77-71c8ae531565","year":2009},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.227870Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:9c6b4d3d8efcc17ddcac569caedd22b1ce9efd22ff0d4f2afb7feb1567d5aef1","observation_id":"ebbacfeb-962d-4a41-97b2-69066f9ee489","resolution":{"observed_at":"2026-08-11T17:46:47.777583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.749227Z","title":"What you see is what you can change: Human- centered machine learning by interactive visualization,","venue":null,"work_id":"98756e25-858b-4331-a88b-c60e9198850a","year":2017},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.232944Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:f5289afb8e5f352d9d7be5e905f84aa29a5ecae8cb103306f516a4255e8ba41d","observation_id":"5423edcb-a378-4563-8aaf-b678676c84a7","resolution":{"observed_at":"2026-08-11T17:46:47.754689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.728874Z","title":"Fine-tuning deep neural networks by interactively refining the 2d latent space of ambiguous images","venue":null,"work_id":"73dc2c89-b13e-47fd-90a9-41da1daf0659","year":2022},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.238678Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:aeeccfcb36cdd774f66719f5f4301a94f6f852662e374e5bb443f23060a22e13","observation_id":"8419109a-914a-42d6-b5f7-22c4883b16c8","resolution":{"observed_at":"2026-08-11T17:46:47.735424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.244447Z","title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.244447Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:0adf800b35d7420ca5488d68551de4ff0eea74465bca68162f129a1acab3b24e","observation_id":"08032ef1-47cf-4b4b-a3b7-65a337618998","resolution":{"observed_at":"2026-08-11T17:46:47.244447Z","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":"2026-08-11T17:46:47.689810Z","title":"Ib-gan: Disentangled rep- resentation learning with information bottleneck generative adversarial networks,","venue":null,"work_id":"51612ff1-8899-43ba-9bbf-ce9e38baf4f4","year":2021},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.249791Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:32b377c4490b8482ac5cd954be02c9aa73fd33fa508814138c68a4f0cff57b14","observation_id":"5729423d-c513-4cb6-a4f6-e8ba6da628fc","resolution":{"observed_at":"2026-08-11T17:46:47.698217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03599","last_updated":"2018-04-10T15:48:18Z","snapshot_observed_at":"2026-08-14T19:27:23.675013Z","submitted_at":"2018-04-10T15:48:18Z","title":"Understanding disentangling in $\\beta$-VAE","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03599","snapshot_observed_at":"2026-08-11T17:46:47.255899Z","title":"Understanding disentangling in β-vae,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.255899Z"},"links":{"cited_paper":"/paper/1804.03599","citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:993aba540b534d26efaa311a68c02840f946914e888f8deb658531b54808b743","observation_id":"bdb6e2f4-6cdf-4bf7-acbe-69690bc337fe","resolution":{"observed_at":"2026-08-11T17:46:47.255899Z","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":"2026-08-11T17:46:47.662313Z","title":"Disen- tanglement via latent quantization,","venue":null,"work_id":"d9eae468-84e9-4247-b605-b600aa064e9c","year":2024},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.262254Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:99eef28da389054ba35b254eb1306f2cb218b7d5fef8c2d648dbe7e61bb47311","observation_id":"3979add3-642e-4f16-b8ef-fa476e764bfa","resolution":{"observed_at":"2026-08-11T17:46:47.672024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.07384","last_updated":"2021-12-20T17:53:43Z","snapshot_observed_at":"2026-08-16T10:03:07.055074Z","submitted_at":"2020-10-14T20:06:28Z","title":"Human-interpretable model explainability on high-dimensional data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.07384","snapshot_observed_at":"2026-08-11T17:46:47.268737Z","title":"Human- interpretable model explainability on high-dimensional data,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.268737Z"},"links":{"cited_paper":"/paper/2010.07384","citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:166819f5457c11f0ac40246fc4cff6339fb708710d43cc4c5db97d37c200f247","observation_id":"d7be270d-18d7-4613-a663-bcccdcd708f2","resolution":{"observed_at":"2026-08-11T17:46:47.268737Z","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":"2026-08-11T17:46:47.639774Z","title":"A disentangling invertible interpretation network for explaining latent representations,","venue":null,"work_id":"86ff4679-e991-4ee6-99fb-fd2d5704630a","year":2020},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.274982Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:dd3ee24aee3168077748b7a4d9a48b83f496c5b5c55faf135f0ad7548d6ee9a3","observation_id":"e1ce65d8-9e97-4514-82af-a57fa3b023c8","resolution":{"observed_at":"2026-08-11T17:46:47.647332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.02968","last_updated":"2021-06-23T12:28:10Z","snapshot_observed_at":"2026-08-13T19:28:22.602398Z","submitted_at":"2021-05-05T12:28:34Z","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.02968","snapshot_observed_at":"2026-08-11T17:46:47.281169Z","title":"This looks like that... does it? shortcomings of latent space prototype interpretability in deep networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.281169Z"},"links":{"cited_paper":"/paper/2105.02968","citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:c0abd38044edb85167df5c101ea7c763633e6cafbaac9cff80826ca4550bc1e8","observation_id":"18fea037-a06b-4636-8faf-bc9c4f101364","resolution":{"observed_at":"2026-08-11T17:46:47.281169Z","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":"2026-08-11T17:46:47.287389Z","title":"A survey on neural network interpretability,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.287389Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:16869e71b3180d551b0b53e3e4bc92fc99d8902622123f22afcb40e680e09f46","observation_id":"80a712d9-0975-447c-8bfe-01d01325fe25","resolution":{"observed_at":"2026-08-11T17:46:47.287389Z","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":"2026-08-11T17:46:47.602200Z","title":"Explaining deep neural networks and beyond: A review of methods and applications,","venue":null,"work_id":"fded2f09-e664-4f31-b2b8-21f03e1291b2","year":2021},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.293296Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:408205efa258640456f269571d916bd34b283d7e80d7f9751ca2c9992b3a2c91","observation_id":"3e7f6bfb-38e8-4c88-9ee7-aad1dfaec153","resolution":{"observed_at":"2026-08-11T17:46:47.608935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.578549Z","title":"Interpretable deep learning: Interpretation, interpretability, trustworthi- ness, and beyond,","venue":null,"work_id":"9fc39f60-b9be-4656-8157-017d8437e2e3","year":2022},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.299043Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:0b41348fde8ec95542dbf701e04e15ce89c74345b914739a1cc95bd2ef05b619","observation_id":"14735d58-ac10-42a7-b90f-72e19f113e77","resolution":{"observed_at":"2026-08-11T17:46:47.584850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:46:47.304348Z","title":"Liii. on lines and planes of closest fit to systems of points in space,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.304348Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:75c638ab3ba375aca4ea991cc6baad427f2c22ad8fe9a4e38b557b719f214474","observation_id":"bf50746b-ee6f-4a91-a836-d6a4e056a2ba","resolution":{"observed_at":"2026-08-11T17:46:47.304348Z","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":"2026-08-11T17:46:47.310410Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.310410Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:3484c691c905bdb105626cb3f35fb0b33840b8c35acf24dae413d17f7678af04","observation_id":"b962cd76-87bb-4cae-9908-8b5c1667ec76","resolution":{"observed_at":"2026-08-11T17:46:47.310410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.03426","last_updated":"2020-09-18T01:56:41Z","snapshot_observed_at":"2026-08-02T15:32:07.466568Z","submitted_at":"2018-02-09T19:39:33Z","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.03426","snapshot_observed_at":"2026-08-11T17:46:47.316159Z","title":"Umap: Uniform manifold approximation and projection for dimension reduction,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.316159Z"},"links":{"cited_paper":"/paper/1802.03426","citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:ba72ec722d4a724de21c1614e4c08794c7e1c79477d7f6627e21eb890f327a00","observation_id":"5bea378d-45f9-4582-81b3-af6472b8d51c","resolution":{"observed_at":"2026-08-11T17:46:47.316159Z","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":"2026-08-11T17:46:47.322299Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.322299Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:31a1bedb4eeff6993d4b687dc3e70e75cb8c3af07ca6f2fc6f32007f17b26e31","observation_id":"dd0d147f-78d6-4bb5-aad9-a3a8ed198f4f","resolution":{"observed_at":"2026-08-11T17:46:47.322299Z","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":"2026-08-11T17:46:47.327709Z","title":"Introducing a new benchmarked dataset for activity monitoring,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T17:46:47.327709Z"},"links":{"citing_paper":"/paper/2412.08507"},"observation_digest":"sha256:136e369fd695c4af20153e7e837098017df4efa5fce033220b098913be2ae102","observation_id":"b22e0dee-7579-44f2-a4a5-2466cf761fb2","resolution":{"observed_at":"2026-08-11T17:46:47.327709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.08507","last_updated":"2024-12-11T16:18:26Z","latest_version":1,"primary_category":"cs.HC","snapshot_observed_at":"2026-08-15T00:53:47.732924Z","submitted_at":"2024-12-11T16:18:26Z","title":"Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":1,"verified_fuzzy":15},"total_outbound_references":32},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 1 inbound Pith citation observation for arXiv:2412.08507."}