{"as_of":"2026-08-19T21:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e82fdb47a742c2e79df6a1decf515f9787329989b742614c01007ddd9007620","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T15:09:51.394202Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2501.14495/citation-record","integrity":"/paper/2501.14495/integrity","json":"/paper/2501.14495/citation-record.json","paper":"/paper/2501.14495"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.944414Z","title":"Gate-shift networks for video action recognition,","venue":null,"work_id":"51c32fbc-b36d-4c16-9836-a2db89764bb5","year":2020},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.232404Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:f5ecb2dce3e8ca1d025f101e94588528ea6878fa7266fe3777a01f2d07f1a2cf","observation_id":"2ca037a5-1500-45ef-9aed-2ca235052243","resolution":{"observed_at":"2026-08-10T15:09:51.949050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.930404Z","title":"Temporal segment networks for action recognition in videos,","venue":null,"work_id":"c8b36f0a-368d-438c-ac14-db452084e635","year":2019},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.237873Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:c93d04b24b98c1df9161ac03c0b65b677c7d40f1d6dfb7500757a950f6b4f3fe","observation_id":"6092e0c4-2714-4d63-a900-dd0c0ddde7bd","resolution":{"observed_at":"2026-08-10T15:09:51.935050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.917329Z","title":"Gating re- visited: Deep multi-layer RNNs that can be trained,","venue":null,"work_id":"be8f43d5-e9d2-4197-8c3d-c48035bb5b49","year":2021},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.242220Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:6dd3f56f14be462a5d914f726c39ce6da5cf8299e36ed2a380062f45770e136e","observation_id":"47aee195-8840-4af5-835b-84114611235c","resolution":{"observed_at":"2026-08-10T15:09:51.921763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.903230Z","title":"Quo vadis, action recognition? a new model and the Kinetics dataset,","venue":null,"work_id":"fada5ee8-239e-4769-af79-dd6824090fd2","year":2017},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.245958Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:500ad86dcef4c619eacbe3b3895f1942b2b0903676eab49d4ce160f2ccf3e09c","observation_id":"9fba6a1f-1b10-4cd6-b4f5-17b6caa4bc06","resolution":{"observed_at":"2026-08-10T15:09:51.908306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.08675","last_updated":"2016-09-27T21:21:49Z","snapshot_observed_at":"2026-08-14T21:37:52.670253Z","submitted_at":"2016-09-27T21:21:49Z","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.08675","snapshot_observed_at":"2026-08-10T15:09:51.250002Z","title":"YouTube-8M: A large-scale video clas- sification benchmark,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.250002Z"},"links":{"cited_paper":"/paper/1609.08675","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:a11c7475595f3df138bc16b7cb59cc15d23f9e82980a74b70e1f2b8d02f13a40","observation_id":"f9d9e131-83bf-4270-8ea4-36ec8531a0af","resolution":{"observed_at":"2026-08-10T15:09:51.250002Z","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":"2026-08-10T15:09:51.889195Z","title":"The Jester dataset: A large-scale video dataset of human gestures,","venue":null,"work_id":"de044657-b683-4a0b-ab37-5aff168989f3","year":2019},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.254546Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:dfd84340f944b733d8ec2d8048e81ee7c761f370d7e56dbaeccfcb29f15e3e24","observation_id":"86935754-81bd-47be-8313-6e1c03528122","resolution":{"observed_at":"2026-08-10T15:09:51.893783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.876127Z","title":"Can spatiotemporal 3D cnns retrace the history of 2D cnns and imagenet?","venue":null,"work_id":"ebd8ebe2-4f36-4659-b447-e3d93d33f3a8","year":2018},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.258819Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:ea970eb2d0570833f965ab4a9c988746f6713ee3bff66609b7a342bf63c39620","observation_id":"00f51229-d641-4e57-9d97-450badba8c39","resolution":{"observed_at":"2026-08-10T15:09:51.880135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.863924Z","title":"Long Short-Term Memory,","venue":null,"work_id":"0ce14748-c6e9-4e77-8788-03874e12f7a9","year":1997},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.262486Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:c621339025785bca43b28d5c55b0ee24f2294afc733671d660c30b0f17bc106d","observation_id":"7550150f-18f5-4bf2-9186-f4b03af9179c","resolution":{"observed_at":"2026-08-10T15:09:51.867521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.849779Z","title":"Resource efficient 3D convolutional neural networks,","venue":null,"work_id":"1171cba4-3eb7-43a7-948d-dfa974714f80","year":2019},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.266377Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:6c640db0086a965fb80bf068d8ec41da926668fa385029f73073c910b7d9111f","observation_id":"e6c4b65c-aedb-44fd-9b1b-16859b7b97e4","resolution":{"observed_at":"2026-08-10T15:09:51.854627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.06961","last_updated":"2021-06-30T01:25:26Z","snapshot_observed_at":"2026-08-11T14:41:13.233440Z","submitted_at":"2019-10-15T17:55:37Z","title":"Tiny Video Networks","version":3},"cited_work":{"arxiv_id":"1910.06961","doi":null,"metadata_source":"pith","pith_arxiv_id":"1910.06961","snapshot_observed_at":"2026-08-10T15:09:51.539856Z","title":"Tiny Video Networks","venue":"cs.CV","work_id":"a40494ef-6ec0-424c-8e96-5c0794771db8","year":2019},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.270553Z"},"links":{"cited_paper":"/paper/1910.06961","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:9ad762cb0e94253593547267f9b6a39bc6658f1cb5400c72edc9338e7b739837","observation_id":"a7389c92-47e4-4571-90d7-d92faec0326c","resolution":{"observed_at":"2026-08-10T15:09:51.544096Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.834691Z","title":"3D CNN acceleration on FPGA using hardware-aware pruning,","venue":null,"work_id":"01f5c12a-8581-4fde-aef2-c0a0c2323a3c","year":2020},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.274876Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:a0eec1fe3aebbf41bb515774186bd119326dd641747c4fb1b1c7347ed9665514","observation_id":"f27d7d0e-8fb7-4331-bf07-aa274929b348","resolution":{"observed_at":"2026-08-10T15:09:51.839041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.819968Z","title":"Quantized neural networks: Training neural networks with low preci- sion weights and activations,","venue":null,"work_id":"14b57e12-8797-43af-91f1-0141c67126a6","year":2017},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.278810Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:308b2e9d5f9df7f612545c7155f6e2a281f8c37f559557e6a3d7a1be489213cb","observation_id":"f0c3d5d7-b110-41e4-95a1-1feea8bc848d","resolution":{"observed_at":"2026-08-10T15:09:51.824683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.805946Z","title":"Bi- narized neural networks,","venue":null,"work_id":"bdf9e48c-8fa7-42db-baf3-c7b4124f59cf","year":2016},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.282976Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:32604ca6e86b9074744c846358983e39bce7b2a8253114d0dd24fdaff46afab6","observation_id":"fef8cbf6-68b1-4b07-9f7f-abf75a3c8ced","resolution":{"observed_at":"2026-08-10T15:09:51.810332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.791813Z","title":"Learned step size quantization,","venue":null,"work_id":"95af6f3d-5859-4241-87d4-5a6a977d4de2","year":2020},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.287062Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:c2fd6c4d5210dd6863d6e479d51b0b8505071f66551879e7b1e0a7afef6cc29e","observation_id":"ec4ec736-1861-4154-96c5-e923d17a77a5","resolution":{"observed_at":"2026-08-10T15:09:51.796276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07065","last_updated":"2017-02-26T14:13:25Z","snapshot_observed_at":"2026-08-14T21:29:18.829674Z","submitted_at":"2016-11-21T21:24:45Z","title":"Recurrent Neural Networks With Limited Numerical Precision","version":2},"cited_work":{"arxiv_id":"1611.07065","doi":null,"metadata_source":"pith","pith_arxiv_id":"1611.07065","snapshot_observed_at":"2026-08-10T15:09:51.519498Z","title":"Recurrent Neural Networks With Limited Numerical Precision","venue":"cs.NE","work_id":"6a56b02a-d441-4a93-9b5a-db09c1701e4b","year":2016},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.290998Z"},"links":{"cited_paper":"/paper/1611.07065","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:b293c48866fbed61bf857a8d38bd7489b1a7ad3a9f2d7224fa5bbdc21553dc3b","observation_id":"4499f90c-d8db-426a-8d7f-7de0164dee8a","resolution":{"observed_at":"2026-08-10T15:09:51.524754Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.777963Z","title":"Effective quantization approaches for recurrent neural networks,","venue":null,"work_id":"cf563703-dd86-409b-b1fa-0e9d14584a0d","year":2018},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.296299Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:1ff7501b9888d9e0c049333459654159a694fe94809c9fdb42dfda4d3d890714","observation_id":"7975a117-0000-47cd-a5ee-cd20cbfd0074","resolution":{"observed_at":"2026-08-10T15:09:51.782315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.300790Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.300790Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:20284505109d8fa2315f881f89405f2b93393bcdba1febeea2960b64fd01940d","observation_id":"9cf9cbc8-5079-4932-b688-00c3cf0695ff","resolution":{"observed_at":"2026-08-10T15:09:51.300790Z","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":"2026-08-10T15:09:51.755718Z","title":"Residual attention network for image classification,","venue":null,"work_id":"13a073cb-8d75-4c32-ac83-a209694c5635","year":2017},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.305949Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:8875b621c18a83ae7e78be525f31c2a985c048d5d2b454b1dd01044ba232abcd","observation_id":"196bdfde-fc79-4ffa-b69d-7430f7a71548","resolution":{"observed_at":"2026-08-10T15:09:51.759941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.743327Z","title":"Squeeze-and-excitation networks,","venue":null,"work_id":"131bd237-e1f2-4479-80a9-191f03453bfd","year":2011},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.309964Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:b1aaf72d0b7f304ecb52fdc49b5f7e8d571b394ebd4ffc74d575a5aba80c3019","observation_id":"8f8879bd-87c9-4b1a-9808-cb18d85e32f3","resolution":{"observed_at":"2026-08-10T15:09:51.746969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.730171Z","title":"Learning spatio-temporal features with 3D residual networks for action recognition,","venue":null,"work_id":"7b1407cb-8dd5-4940-a562-bd5149111e75","year":2017},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.314201Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:fec8cfaa0d097b6ad96610465fec75beffdd7803b6eb9ae0b12efb3d1f68deae","observation_id":"0f81dbfd-5614-4068-b8ed-865135e8571c","resolution":{"observed_at":"2026-08-10T15:09:51.734723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.01696","last_updated":"2021-09-03T18:27:52Z","snapshot_observed_at":"2026-08-16T17:58:56.890506Z","submitted_at":"2021-09-03T18:27:52Z","title":"Revisiting 3D ResNets for Video Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.01696","snapshot_observed_at":"2026-08-10T15:09:51.318493Z","title":"Revisiting 3D resnets for video recognition,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.318493Z"},"links":{"cited_paper":"/paper/2109.01696","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:d5ad46cefbb1591ead65fe4c1f4ef209ecf82ec76ecb425c6a30aa7dd37b502e","observation_id":"916bca99-8d99-4275-9ac7-b26a12bff0a4","resolution":{"observed_at":"2026-08-10T15:09:51.318493Z","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":"2026-08-10T15:09:51.717111Z","title":"Spatio- temporal attention networks for action recognition and detection,","venue":null,"work_id":"0d80af9a-9293-4b4f-81bf-0fd0ee052740","year":2020},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.322874Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:981e0917c0b9b6172e99c59d40a1f8bc2e28df9a7bef51120d2ee459530d36f4","observation_id":"1b6d1c31-29c4-424a-9c36-a1414ed2286d","resolution":{"observed_at":"2026-08-10T15:09:51.721576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.703263Z","title":"A closer look at spatiotemporal convolutions for action recognition,","venue":null,"work_id":"615af4e0-43cf-4c37-b85b-7368b6e9b433","year":2018},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.326950Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:968a704cbdc908578b0a1cbb60704e6c1e91283899059e8f2dc06ec931e377d1","observation_id":"964ab87e-ef2a-48d6-9f08-0c3a720fa043","resolution":{"observed_at":"2026-08-10T15:09:51.707847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.690084Z","title":"Rethinking spatio- temporal feature learning: Speed-accuracy trade-offs in video classifica- tion,","venue":null,"work_id":"17179e65-020f-425f-ae40-c4316711fdf9","year":2018},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.331303Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:b207d1807e479a84a6ed25ff689ece4ad8d92d736c0af24376fe1b70fdeda878","observation_id":"a85fce89-8fbe-44a1-b6b8-612e3146178f","resolution":{"observed_at":"2026-08-10T15:09:51.694430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.676499Z","title":"Learning spatio-temporal representation with pseudo-3D residual networks,","venue":null,"work_id":"907a32f3-7c7a-437d-9ef2-5abc6626b749","year":2017},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.335342Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:7c529da40fbb45de5cfa60bcb4db122ed4bb9db502244c34a1cde390cc0f90be","observation_id":"bf0c568c-786b-4bc3-9b25-0b30cf2ce30b","resolution":{"observed_at":"2026-08-10T15:09:51.680973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.661273Z","title":"TSM: Temporal shift module for efficient video understanding,","venue":null,"work_id":"228fa337-308c-426a-aff9-bd30c99daea2","year":2019},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.340165Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:c9d26a734d81d6845fa23dff998f3f743235253627d26ea2755cfd777360bef8","observation_id":"d0089e38-2a0f-4384-a544-717c7879084f","resolution":{"observed_at":"2026-08-10T15:09:51.667074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.646716Z","title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices,","venue":null,"work_id":"e32e8677-a856-43dc-a310-07977eca18c8","year":2018},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.354008Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:7736eecf7aa078a25243ab87d8457b31515e8f1cf25427544500737d11d88464","observation_id":"10f45ddf-8f33-4ef0-b9d5-cff9ceebbf19","resolution":{"observed_at":"2026-08-10T15:09:51.651054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.631950Z","title":"Dynamic network quantization for efficient video inference,","venue":null,"work_id":"e815bb77-7147-4c4d-a371-11414662b78e","year":2021},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.358143Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:70f2f5281b82a3020085a25758586892cc9af8f70cc7e66c65c1f37fec3ffb74","observation_id":"add81909-b74b-4b97-b550-76dc3d73e825","resolution":{"observed_at":"2026-08-10T15:09:51.636268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.618239Z","title":"Efficient binary 3D convo- lutional neural network and hardware accelerator,","venue":null,"work_id":"8228eeae-b934-4d48-9c7c-2a3746efb073","year":2022},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.361926Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:65ae9b30cb575fab4d2d456bf7ea09fbf285c6b7a2addfea8031772ba42866ce","observation_id":"b163ce48-badc-486e-b18e-b488930ecc63","resolution":{"observed_at":"2026-08-10T15:09:51.622665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.12074","last_updated":"2021-08-27T00:59:52Z","snapshot_observed_at":"2026-08-16T18:00:38.773155Z","submitted_at":"2021-08-27T00:59:52Z","title":"4-bit Quantization of LSTM-based Speech Recognition Models","version":1},"cited_work":{"arxiv_id":"2108.12074","doi":null,"metadata_source":"pith","pith_arxiv_id":"2108.12074","snapshot_observed_at":"2026-08-10T15:09:51.470274Z","title":"4-bit Quantization of LSTM-based Speech Recognition Models","venue":"cs.CL","work_id":"84d22efc-02e8-4867-8651-dd1695732f32","year":2021},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.365508Z"},"links":{"cited_paper":"/paper/2108.12074","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:428bda43a4cffad150f10290a61b3040f0d4a29c263eea42260ab08149556a41","observation_id":"b4301e80-485b-4b9e-8048-c9c1dadd7bf8","resolution":{"observed_at":"2026-08-10T15:09:51.476984Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.604392Z","title":"HitNet: Hybrid ternary recurrent neural network,","venue":null,"work_id":"b5ce9b1d-4757-4caa-9486-8a89d8f8ba7a","year":2018},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.369251Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:15ca17003d71568b354da6f9f58ddcee21b51871cc34ca012ba5906fb0ffddca","observation_id":"56018f21-000e-49de-b861-2750ec62626c","resolution":{"observed_at":"2026-08-10T15:09:51.609044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:09:51.590428Z","title":"DC-LSTM: Deep com- pressed LSTM with low bit-width and structured matrices,","venue":null,"work_id":"ecc873f9-d75e-4d7d-8546-832f7c922a92","year":2020},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.373036Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:9f3ae2476b07cb1ba8cbb19074cba63b01924f5dbe4ed7f918c52ced0f7febaf","observation_id":"b15e8992-9218-44a3-878c-c310f6e484ad","resolution":{"observed_at":"2026-08-10T15:09:51.594877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-08-14T04:51:04.817737Z","submitted_at":"2013-08-15T15:19:34Z","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.3432","snapshot_observed_at":"2026-08-10T15:09:51.376723Z","title":"Estimating or propagat- ing gradients through stochastic neurons for conditional computation,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.376723Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:8c6b63fc2a8cd9f05229b7270e80b627e72274051e7373eb88a8ff4914bc75e3","observation_id":"ab4f281f-b5cb-4c9a-88f1-958af78b041c","resolution":{"observed_at":"2026-08-10T15:09:51.376723Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T15:09:51.380925Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.380925Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:2aa4ffdadd6e11dcf03af1ae860fdde4843d0da04d9f8f57b8a5ef69f6bb3c82","observation_id":"012f4215-4c95-4bd7-a1f5-c780828a97dd","resolution":{"observed_at":"2026-08-10T15:09:51.380925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1605.04711","last_updated":"2022-11-20T14:21:55Z","snapshot_observed_at":"2026-08-14T21:57:14.951937Z","submitted_at":"2016-05-16T10:21:25Z","title":"Ternary Weight Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.04711","snapshot_observed_at":"2026-08-10T15:09:51.386022Z","title":"Ternary weight networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.386022Z"},"links":{"cited_paper":"/paper/1605.04711","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:767de86abc77778ff384c06aef558ad3952ac06ff49d81c2ff30903b299e65d5","observation_id":"1c82684e-8196-4fac-af12-57e983e43e56","resolution":{"observed_at":"2026-08-10T15:09:51.386022Z","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":"2026-08-10T15:09:51.390229Z","title":"Adam: A method for stochastic optimiza- tion,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.390229Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:7530eb39512c513e43fccff0d1f58dbef16d3721072b5f85ad760cfcd396b27f","observation_id":"cfada1e4-b3fb-434c-a958-e43f64d1d033","resolution":{"observed_at":"2026-08-10T15:09:51.390229Z","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":"2026-08-10T15:09:51.567245Z","title":"Differentiable joint pruning and quantization for hardware efficiency,","venue":null,"work_id":"5b2b4a89-f416-4860-b958-21a8a4b2bd37","year":2020},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.394202Z"},"links":{"citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:831edc914b4d7d7727884bc797478f6eb3d3b4742179b39cd8e0d24d0d98aae5","observation_id":"a536b5aa-b984-486e-b62f-aea495c507c9","resolution":{"observed_at":"2026-08-10T15:09:51.571654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-10T15:09:51.349736Z","title":"Available: http://arxiv.org/abs/1704.04861","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T15:09:51.349736Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2501.14495"},"observation_digest":"sha256:6d912cfe22e4f0600f4fd0f71c10cdab14f1b83f18ce01e6147d401ba5bc059b","observation_id":"faeebf88-a1d1-49b8-a7b4-17e2b9b7ca20","resolution":{"observed_at":"2026-08-10T15:09:51.349736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.14495","last_updated":"2025-01-24T13:51:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T22:12:07.926214Z","submitted_at":"2025-01-24T13:51:47Z","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":3,"verified_fuzzy":27},"total_outbound_references":38},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2501.14495."}