{"as_of":"2026-08-13T04:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d226e8c02761b589d0efc8d96818f0ac07d19ea30e4da34b4b82e5f3fb1a2ee8","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:51:42.881629Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2505.20739/citation-record","integrity":"/paper/2505.20739/integrity","json":"/paper/2505.20739/citation-record.json","paper":"/paper/2505.20739"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:51:49.090772Z","title":null,"venue":null,"work_id":"bcfbc894-fc3c-4070-8a1a-fbd494677ffa","year":2021},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:37.585261Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:598afd90999523a2e1e57c3cf35a59d68c3deb34aa3274b35c1aba6e527ca148","observation_id":"c9b52ec4-6c29-4d1f-94bd-216843e027ec","resolution":{"observed_at":"2026-08-07T13:51:49.193613Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:48.915418Z","title":"Squeeze-and-excitation on spatial and temporal deep feature space for action recognition","venue":null,"work_id":"63de4543-8d74-4ac4-83b9-39acf1bcc1f4","year":2018},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:37.681567Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:2ebead3d3d37ec1d94a79c8f9c0d864bf3b6de356e667b8c2aa10648b80a49f2","observation_id":"4914d6e5-4a9f-428e-9b92-7e0d00990af6","resolution":{"observed_at":"2026-08-07T13:51:49.005655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.01271","last_updated":"2018-04-19T14:32:38Z","snapshot_observed_at":"2026-07-06T06:26:27.965096Z","submitted_at":"2018-03-04T00:20:29Z","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.01271","snapshot_observed_at":"2026-08-07T13:51:37.841923Z","title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling.arXiv preprint arXiv:1803.01271, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:37.841923Z"},"links":{"cited_paper":"/paper/1803.01271","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:ce46304756bd9e4bc2d5ea63eeea2b0fdf24c12859cfdfa2f06790f7f34b9c7c","observation_id":"98288a5b-497a-4f3f-8d76-43ddf45e63a6","resolution":{"observed_at":"2026-08-07T13:51:37.841923Z","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":"2026-08-07T13:51:48.719580Z","title":"Lawrence Zitnick, Kavita Bala, and Ross Girshick","venue":null,"work_id":"3b174c54-1112-42d0-8f73-53600d823ca1","year":2015},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:38.072570Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:3ff77b993b2fefc684fb292e1635681e13b761d2e8433e8553491cbd7b5e3ae8","observation_id":"e356d8ff-631a-4f36-a307-1a15fe44f84b","resolution":{"observed_at":"2026-08-07T13:51:48.830121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:48.549086Z","title":"Improving deep learning for har with shallow lstms","venue":null,"work_id":"68307184-5694-43cf-b0ab-1e6efa7230f0","year":2021},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:38.246266Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:eddfbfc27401ea2324a657de0abfa199a0acfe6a9b1813b4cc3751b24072197a","observation_id":"d582133f-4633-46e1-a5a9-38e63f1e5a49","resolution":{"observed_at":"2026-08-07T13:51:48.584410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05088","last_updated":"2024-10-15T07:48:59Z","snapshot_observed_at":"2026-07-06T15:14:21.040481Z","submitted_at":"2023-04-11T09:31:07Z","title":"WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition","version":4},"cited_work":{"arxiv_id":"2304.05088","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.05088","snapshot_observed_at":"2026-08-07T13:51:43.591514Z","title":"WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition","venue":"cs.CV","work_id":"3bd184dd-181d-4719-9efa-f0b7fa90f2c3","year":2023},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:38.436465Z"},"links":{"cited_paper":"/paper/2304.05088","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:b54627cb58623611e59ee3b4cb9f291072da9fa5dfebf47643a34eaeab1dd80a","observation_id":"12245741-cbb9-43a5-833b-5a7a73a09053","resolution":{"observed_at":"2026-08-07T13:51:43.650628Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:48.361668Z","title":"Gcnet: Non-local networks meet squeeze-excitation networks and beyond","venue":null,"work_id":"4326e7eb-7f4f-4518-8e71-c118ab97aede","year":2019},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:38.558104Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:93864cae2d935b34374aa927d8a4853349e0f02d7f4453565f101c122550fe05","observation_id":"cda8cbe6-e82d-46b5-ba98-d16351c7fc38","resolution":{"observed_at":"2026-08-07T13:51:48.448389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:48.128123Z","title":"Fused behavior recognition model based on attention mechanism","venue":null,"work_id":"e38c2bc5-610c-40bd-a5eb-b7fa9e814438","year":2020},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:38.807896Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:8264e8473f0649170eccda3fdc9d27b0790b0167916b703a283217b01ed10fa3","observation_id":"a1475495-5541-439c-9f9d-1fb62a46482f","resolution":{"observed_at":"2026-08-07T13:51:48.263127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:47.950171Z","title":"Esenet: A human behavior recognition model based on extended squeeze-and-excitation network","venue":null,"work_id":"6fca1032-0f4c-438a-9a7c-6ac35b7b0dea","year":2020},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:38.959334Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:12838dae2b46b4a661ad97110c6193b8b5df0c136859c9ac88c1684dc37fe292","observation_id":"5b217c80-c673-4b33-9621-f654a623ef65","resolution":{"observed_at":"2026-08-07T13:51:48.003810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:47.717137Z","title":"Probabilistic forecasting with temporal convolutional neural net- work.Neurocomputing, 399:491–501, 2020","venue":null,"work_id":"781e643c-60dd-426d-a6ac-c44fc97d1be7","year":2020},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:39.187769Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:4f07b62617a4b50e81417ccf9e84f860b01c6fe9aac2b935e40829e3dfda60c2","observation_id":"d6a78900-decc-4dea-a2a0-da77165f7b57","resolution":{"observed_at":"2026-08-07T13:51:47.843723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-07-06T03:45:28.546418Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-07T13:51:39.380787Z","title":"Learning phrase representations using rnn encoder- decoder for statistical machine translation.arXiv preprint arXiv:1406.1078, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:39.380787Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:2abff0eaa0c79463c165dc1ab0c6db102133616ad5a54ad81b99c730ac45f9b6","observation_id":"19dcebf7-1d7d-4db0-b157-7a81cff5500b","resolution":{"observed_at":"2026-08-07T13:51:39.380787Z","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":"2026-08-07T13:51:47.585215Z","title":"Leveraging large language models for activity recognition in smart environments","venue":null,"work_id":"20aaeec2-cdea-4561-8378-8230dcd12b34","year":2024},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:39.574817Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:1b596ad67800c5523c80ed0a72ff0c4ede5f6089d688f4907e6e9b0bdb2ee8ea","observation_id":"2fd09f83-3673-4a28-a518-d67de4c4c00a","resolution":{"observed_at":"2026-08-07T13:51:47.631167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:39.666768Z","title":"Finding structure in time.Cognitive science, 14(2):179–211, 1990","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:39.666768Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:aaf8023d647839e803eb8bc5642c1c6a91a36f382c449fcba5184aa567b9446a","observation_id":"4d709d36-73c2-43dd-9dda-822789f6e872","resolution":{"observed_at":"2026-08-07T13:51:39.666768Z","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":"2026-08-07T13:51:47.372816Z","title":"Using k-nearest neighbours feature selection for activity recogni- tion","venue":null,"work_id":"f45018b9-6e3c-4982-b639-74dbed00d834","year":2022},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:39.739735Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:c4627d3f076af4d701bfa81b7796261f77e1e85857e53de892549e5c2e29aee5","observation_id":"861b4268-c82d-49cb-868a-610194c9fd56","resolution":{"observed_at":"2026-08-07T13:51:47.445895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:47.168417Z","title":"Deep sparse rectifier neural networks","venue":null,"work_id":"41f091e8-4297-4978-986c-ae87e74936bd","year":2011},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:39.806675Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:14969cc42ce7f832aedf97abbaaa11c459982b60c8c85e745fc0d38f1b3f75d3","observation_id":"f0a1a847-4077-4421-906e-285bed68110b","resolution":{"observed_at":"2026-08-07T13:51:47.257604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:39.892385Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:39.892385Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:7df72e0f9caa6972616e51bcaa97e5a6df34b7f21161ae85562812d581da7d6d","observation_id":"b6cc7d7c-9a1c-4684-aba0-662ad50653ce","resolution":{"observed_at":"2026-08-07T13:51:39.892385Z","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":"2026-08-07T13:51:40.107566Z","title":"Long short-term memory.Neural Computation MIT-Press, 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.107566Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:fa8bfdbf3eda0d71be6562843e6af76510978676abcd6300ac6fbea64050b1e1","observation_id":"ed43a992-28c9-4efc-aba3-187e82b9e483","resolution":{"observed_at":"2026-08-07T13:51:40.107566Z","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":"2026-08-07T13:51:47.007280Z","title":null,"venue":null,"work_id":"565d2fc2-71ab-4b42-8acf-a289c71b185d","year":2024},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.170191Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:d684fda66f02b19d449e9a611cc3581eafd8f704d3c6e7a13f8d36c5b0c3df38","observation_id":"6288b6b0-1e65-4307-80ea-bff8549b60e0","resolution":{"observed_at":"2026-08-07T13:51:47.056929Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:46.844448Z","title":"Ta-da!- improving activity recognition using temporal adapters and data augmentation","venue":null,"work_id":"15123737-ad67-49d4-87cc-9cda1bf40ca9","year":2024},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.244946Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:eff6bfcc3f490c6de1d36c4dae6c1b038dc56845beb252fe88dd6d9689152cc2","observation_id":"5eb05e41-d8e6-4f9d-b9b2-32d47e92a755","resolution":{"observed_at":"2026-08-07T13:51:46.918101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:40.355436Z","title":"Squeeze-and-excitation networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.355436Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:e28752014f941f87ea6383c8cfe93a03b0c3914fd2f1ad15d11acf49e645ebfa","observation_id":"77e8b582-3b4e-47ce-8cc6-6fa0430c3c31","resolution":{"observed_at":"2026-08-07T13:51:40.355436Z","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":"2026-08-07T13:51:46.677834Z","title":null,"venue":null,"work_id":"d28bd251-cda4-4099-ba52-d513767f525a","year":2022},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.471459Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:e0ddee6e67aca321db85a9a6884220a21d12451609e6ceb05409d2fa976c896c","observation_id":"13a34fc8-9193-4ffe-b32b-36d608adff58","resolution":{"observed_at":"2026-08-07T13:51:46.734864Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-08-12T21:01:12.961874Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-07T13:51:40.552677Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift.arXiv preprint arXiv:1502.03167, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.552677Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:b3461d6d58b569429b3daafe14b298ca3b20d281ec646802f4c1d25f3f8b1198","observation_id":"71c0ef80-a17d-4c2a-86eb-fb49cee027aa","resolution":{"observed_at":"2026-08-07T13:51:40.552677Z","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":"2026-08-07T13:51:46.506293Z","title":"Spatial transformer networks, 2016","venue":null,"work_id":"753088c0-1d5f-47ec-90c9-7e70eac0c7b7","year":2016},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.620800Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:9d2b4911e978e6bf1155a88178a05a694115e5af7bf8a8a0bdc5730ca486e3d5","observation_id":"3d102497-a234-4f1e-a87f-1aaabc7ee8e5","resolution":{"observed_at":"2026-08-07T13:51:46.584553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:46.272040Z","title":"En- hancing aerial human action recognition through gan-boosted resnext architecture with squeeze-and-excitation network","venue":null,"work_id":"5f221d0f-8cc4-4ad2-b013-d3f5d384946b","year":2023},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.703272Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:677605cbe6835d44e960e919ec8e937bdbb9d2b42f3d8a2e582d9727cbf45b8c","observation_id":"193558b0-3ce9-4716-970a-065d1c731e82","resolution":{"observed_at":"2026-08-07T13:51:46.369257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.04451","last_updated":"2020-02-18T16:01:18Z","snapshot_observed_at":"2026-07-06T08:50:12.690900Z","submitted_at":"2020-01-13T18:38:28Z","title":"Reformer: The Efficient Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.04451","snapshot_observed_at":"2026-08-07T13:51:40.848443Z","title":"Reformer: The efficient transformer.arXiv preprint arXiv:2001.04451, 2020","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.848443Z"},"links":{"cited_paper":"/paper/2001.04451","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:d2bafa2b4843036eea03da9ccc66e59b4e1c913f9595726e58b38575200730f3","observation_id":"e11e5a75-e4b6-4fd9-8904-584d988ac358","resolution":{"observed_at":"2026-08-07T13:51:40.848443Z","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":"2026-08-07T13:51:46.074495Z","title":"Hmdb: a large video database for human motion recognition","venue":null,"work_id":"e322d602-2a54-4e9b-8a3c-cdce068bbca2","year":2011},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:40.962025Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:7789bfad1b64b173417ae4f247f46956de3ed1e2dd88f559623a4b1f1b6a1884","observation_id":"7b8bba13-b893-4b1e-af39-cc0679a405a8","resolution":{"observed_at":"2026-08-07T13:51:46.171135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:41.056590Z","title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.056590Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:9009276d4b71acdbcade63bfc17fe111a826cb58473ecd0fc432352221f0ba7d","observation_id":"93eda4e9-baa8-4765-8d64-d70939f5efe7","resolution":{"observed_at":"2026-08-07T13:51:41.056590Z","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":"2026-08-07T13:51:45.906823Z","title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting.International Journal of Forecasting, 37(4):1748–1764, 2021","venue":null,"work_id":"f24cd30a-20cf-4c91-9dee-a84c3dfe4add","year":2021},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.149280Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:54210b100497e4e387217df999fa82683502463bc3d4f3182f93f3abd9e32f93","observation_id":"efcd9b7b-da8e-4b45-889e-f9b0c1bc354a","resolution":{"observed_at":"2026-08-07T13:51:45.955334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:45.728654Z","title":"End-to-end temporal action detection with 1b parame- ters across 1000 frames","venue":null,"work_id":"c786532f-2771-4e73-8412-848c872ec5ae","year":2024},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.264350Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:b5646b5546cdf541fcc60aab5aca30558e72021c03ff22727af89f0cb82839a3","observation_id":"38d8d521-affd-4ebe-b705-06086beaa605","resolution":{"observed_at":"2026-08-07T13:51:45.807827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-07T13:51:41.349401Z","title":"Decoupled weight decay reg- ularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.349401Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:d0f0903fc8516090ae0043e528b8b53aa2188138ce625cc44b3afdc0a5388048","observation_id":"17081f52-384b-41e5-a77a-23e980cd18bb","resolution":{"observed_at":"2026-08-07T13:51:41.349401Z","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":"2026-08-07T13:51:45.606928Z","title":"Stacked hourglass networks for human pose estimation, 2016","venue":null,"work_id":"928d7b5c-457c-4f48-b49d-653eaa266acc","year":2016},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.443574Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:609e78a9909a19c75b5434eb2f76a67995219e6342f2281a5495dfb1880cea67","observation_id":"633b0292-5f3f-4d8d-84e0-12877efce950","resolution":{"observed_at":"2026-08-07T13:51:45.667052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:45.463058Z","title":"Recognition of endotracheal suctioning activities: A feature extraction and ensemble learning approach based on pose esti- mation data","venue":null,"work_id":"510973c6-9cbc-4669-af00-e3c091dae692","year":2024},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.532895Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:e1385476570598821a1c93e5dd87e396941c6cdd64125292817f19c2ccb6d7e1","observation_id":"3e13b2b5-b672-407f-9b88-2deec43ccb92","resolution":{"observed_at":"2026-08-07T13:51:45.538567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.05941","last_updated":"2017-10-27T17:45:21Z","snapshot_observed_at":"2026-08-08T18:23:31.977872Z","submitted_at":"2017-10-16T18:05:45Z","title":"Searching for Activation Functions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.05941","snapshot_observed_at":"2026-08-07T13:51:41.650579Z","title":"Searching for activation functions.arXiv preprint arXiv:1710.05941, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.650579Z"},"links":{"cited_paper":"/paper/1710.05941","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:692280773bfb3aaa3257923cc38852117dfbc1feec757902c67ad79fd93bad93","observation_id":"f3b242db-56f8-436c-bacc-2f603616e351","resolution":{"observed_at":"2026-08-07T13:51:41.650579Z","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":"2026-08-07T13:51:45.320539Z","title":"Tridet: Temporal action detection with relative boundary modeling","venue":null,"work_id":"3473f417-2959-45b3-ae21-92d8775c900c","year":2023},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.772403Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:f4fc81ecf3139e0d987e8ccde25182ea2ce829a1b17a05b62914910bd0ec7ced","observation_id":"19ae0fd3-5024-4167-90b5-a39742fbf217","resolution":{"observed_at":"2026-08-07T13:51:45.381895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:45.101595Z","title":"Expansion- squeeze-excitation fusion network for elderly activity recognition","venue":null,"work_id":"df351a18-2a3b-43a2-af29-6d60a06ac94e","year":2022},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.851978Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:00cfc6b5527cb287607bd913288edf76561c15588e2e6814859dfe3bb694e4bf","observation_id":"0d54e853-f616-4fd3-bd1c-f6e27cdbade9","resolution":{"observed_at":"2026-08-07T13:51:45.193068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-08-12T17:34:19.526460Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-07T13:51:41.977379Z","title":"Ucf101: A dataset of 101 human actions classes from videos in the wild.arXiv preprint arXiv:1212.0402, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:41.977379Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:6a7d09d32eb512740570edb1eadcb0d0905b5095b08f6d990732ef1237928a3b","observation_id":"d80a9a2e-d550-4d91-9e61-b91896b3f64c","resolution":{"observed_at":"2026-08-07T13:51:41.977379Z","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":"2026-08-07T13:51:42.073652Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.073652Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:9e6f66fcac4d68d76c4be715e5da13c667bbef2cc0c1604a1fdb5333c6649f24","observation_id":"07013d79-6dc4-4c9b-a840-92b9b7af5f42","resolution":{"observed_at":"2026-08-07T13:51:42.073652Z","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":"2026-08-07T13:51:42.134809Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.134809Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:dbe57038df235ab3ded3bc584ae4a7cf5fb298be7828c298a4921df865674424","observation_id":"8429b800-79ad-432e-bec0-f7f3c2d1407a","resolution":{"observed_at":"2026-08-07T13:51:42.134809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.03499","last_updated":"2016-09-19T18:04:35Z","snapshot_observed_at":"2026-08-13T01:24:25.628327Z","submitted_at":"2016-09-12T17:29:40Z","title":"WaveNet: A Generative Model for Raw Audio","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.03499","snapshot_observed_at":"2026-08-07T13:51:42.248579Z","title":"Wavenet: A generative model for raw audio.arXiv preprint arXiv:1609.03499, 12, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.248579Z"},"links":{"cited_paper":"/paper/1609.03499","citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:be155ef18a1b631d88cb54059dd5da0869fedd52272c448c649961ba7aec5e92","observation_id":"976e46b6-ae17-4def-af59-9111a2c06811","resolution":{"observed_at":"2026-08-07T13:51:42.248579Z","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":"2026-08-07T13:51:44.900024Z","title":"Attention is all you need.Advances in Neural Infor- mation Processing Systems, 2017","venue":null,"work_id":"0a04a498-bc08-4faf-94f1-40383c18a6e3","year":2017},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.375032Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:763f3fb76e14cc4fa032b20f61b755d9731d0c4296c3c4b339301177179ce84e","observation_id":"20ff384f-6184-4e63-a6f8-c82cb0d1831a","resolution":{"observed_at":"2026-08-07T13:51:44.984531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:44.705723Z","title":"Action-net: Mul- tipath excitation for action recognition","venue":null,"work_id":"430353b1-22e1-4cdc-9069-490e195b870c","year":2021},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.454613Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:9ed6056246196569d7134ac53a3716380b822f3a0f91160e45143a164cb3deb0","observation_id":"2e4933ac-7f47-4dae-9e95-ee7ff3d55236","resolution":{"observed_at":"2026-08-07T13:51:44.806716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:44.550226Z","title":null,"venue":null,"work_id":"d340ceba-7548-414b-bfa0-94e3cbf554fd","year":2021},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.541956Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:0cd6aa2b18cc363e0ac5d1828ebc59593b5ec88cf1234a745876517aa3125a5d","observation_id":"3739f6ee-d091-45a5-9b99-dea4a0d3d8c6","resolution":{"observed_at":"2026-08-07T13:51:44.618611Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:44.360173Z","title":"Actionformer: Local- izing moments of actions with transformers","venue":null,"work_id":"372dc759-6067-4f26-b2e8-46f56d66d1bb","year":2022},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.635315Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:fc61438fa26c0adfad11b240455ee31344b38ed4acc6a4e115b41c92651f8d4f","observation_id":"f1b72f8b-67d7-4305-86a7-34d5a9342b71","resolution":{"observed_at":"2026-08-07T13:51:44.462387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:44.137184Z","title":"Temporal squeeze-and- excitation networks for skeleton-based action recognition","venue":null,"work_id":"15abd654-4195-4fa4-8bd6-ae9c8cbee5ea","year":2023},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.716320Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:5c3a36cc4be600b9a14f8248283ee233155ad6356a9d1a2dd84b487aba52cf39","observation_id":"0ee36b17-c583-44b7-8f22-4181ea002532","resolution":{"observed_at":"2026-08-07T13:51:44.222471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T13:51:43.816741Z","title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","venue":null,"work_id":"6d550b91-085e-4764-921d-21d212f91925","year":2021},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.817200Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:23df7dab31c849a07407702fe764fa6eba342f800156ebdb44a0ff32b9699ad1","observation_id":"cb454a75-ad3e-4cf1-a46c-a45d2b0a5161","resolution":{"observed_at":"2026-08-07T13:51:43.970212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2759.6054","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:51:43.152933Z","title":"Sensor data augmentation from skeleton pose sequences for improving human activity recogni- tion","venue":null,"work_id":"981b112e-a7d8-4c9b-b859-d5c00bc2d69f","year":2024},"citing_paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:42.881629Z"},"links":{"citing_paper":"/paper/2505.20739"},"observation_digest":"sha256:48a23438c7cecf87adecc9f31b3ebfb7585c82052ce7e61a3df6b799dc5585be","observation_id":"3a430fe3-b8b2-4c91-ad0e-02059000c885","resolution":{"observed_at":"2026-08-07T13:51:43.267899Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.20739","last_updated":"2025-05-27T05:29:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T13:37:55.344812Z","submitted_at":"2025-05-27T05:29:02Z","title":"Detecting Informative Channels: ActionFormer"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":2,"verified_fuzzy":25},"total_outbound_references":46},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2505.20739."}