{"as_of":"2026-08-11T09:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b2f47f243729ff7f15a07c6e6c054e94cd97c57a62862ccc0c254948fe16efc1","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T10:42:07.888794Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2502.00047/citation-record","integrity":"/paper/2502.00047/integrity","json":"/paper/2502.00047/citation-record.json","paper":"/paper/2502.00047"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.09477","last_updated":"2024-06-13T09:53:24Z","snapshot_observed_at":"2026-08-09T15:13:24.019781Z","submitted_at":"2024-06-13T09:53:24Z","title":"Q-S5: Towards Quantized State Space Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09477","snapshot_observed_at":"2026-08-10T10:42:07.698480Z","title":"Abreu, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.698480Z"},"links":{"cited_paper":"/paper/2406.09477","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:3144fa7ea19921b3a4c9339836d3d4d80ac5bdac0e9b3724253adae54bee603c","observation_id":"2a55578b-ad79-4193-9923-95b977a10d89","resolution":{"observed_at":"2026-08-10T10:42:07.698480Z","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":"2026-08-10T10:42:08.364908Z","title":null,"venue":null,"work_id":"44e163d7-9b77-4fd9-9d01-2d05cb27e29f","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.833235Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:bb0883103d46dfd50e938f5d014a14a708dac12c5c91cecad57f69e585b75295","observation_id":"a003981a-9f31-4bdb-8b30-946a2b1242b0","resolution":{"observed_at":"2026-08-10T10:42:08.370770Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.383890Z","title":null,"venue":null,"work_id":"26d7d449-26f1-4f05-ae08-f1345e1ae126","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.828368Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:e1d300fdd79de690251f670092d721e5a88d25ec2c0ff843d783f706f9a7ecc1","observation_id":"d858835e-3102-4bb2-894a-ab0c491768f1","resolution":{"observed_at":"2026-08-10T10:42:08.391797Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.431721Z","title":"Experiments where done on a NVIDIA GeForce RTX 3080 GPU","venue":null,"work_id":"6dc1b89e-69f9-4e3d-ad89-35ce5011e122","year":2018},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.816475Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:338e73435c4fead5ab5aaa49b8a9e9dbdc832e301e4b54024d3f3de0028b3c6d","observation_id":"697116fb-2189-40c0-a632-1b6bfc3fb3da","resolution":{"observed_at":"2026-08-10T10:42:08.438076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04012","last_updated":"2024-06-10T11:40:40Z","snapshot_observed_at":"2026-08-11T03:37:52.826059Z","submitted_at":"2024-02-05T09:59:57Z","title":"Quantized Approximately Orthogonal Recurrent Neural Networks","version":2},"cited_work":{"arxiv_id":"2402.04012","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.04012","snapshot_observed_at":"2026-08-10T10:42:08.038970Z","title":"Quantized Approximately Orthogonal Recurrent Neural Networks","venue":"cs.NE","work_id":"a4738ea3-5446-4d12-aa03-45d19d15a043","year":2024},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.741645Z"},"links":{"cited_paper":"/paper/2402.04012","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:f7ff80816776ef0a3eac6df3fe50dd19648e35c9372b9afe754964ccd4592a5e","observation_id":"76b03f77-ca72-43f8-83d9-7bc3903219c7","resolution":{"observed_at":"2026-08-10T10:42:08.047788Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.411345Z","title":"The experiments were conducted using the IMDB dataset, with similar trends observed across the other benchmarks, supporting the consistency of these conclusions","venue":null,"work_id":"295ee0a0-9c78-4d4b-ad42-d006a95ca8de","year":2010},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.823060Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:a37fd2ced7701ccdbf0c305ebaaaadaf06af8a597d61abc9d1b2e7217638c151","observation_id":"87ed2efb-221f-4f1d-b8ca-c21668801034","resolution":{"observed_at":"2026-08-10T10:42:08.418143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.235712Z","title":"This is because HadamRNN better memorize than HadamRNN-ReLU","venue":null,"work_id":"91d52587-5a2c-423a-b650-44d51aa1c2bd","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.865368Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:68084f8b220c81fedb9213f71a6c0f58022dea60880df9cdd47946a93c928187","observation_id":"38c0f8ad-0060-4851-800a-bc749c12eb0a","resolution":{"observed_at":"2026-08-10T10:42:08.241676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.192616Z","title":"This finding, along with Appendix H.1, supports our choice to learn row switches only","venue":null,"work_id":"4884d801-a2f6-4b51-9196-3a7921fef43c","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.882226Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:7983fde1ec04c97713b01cca931b247670bf8b878c6ec96a0571493bc5b183c2","observation_id":"33662c01-248d-409d-a21d-063162a461a0","resolution":{"observed_at":"2026-08-10T10:42:08.199481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.494757Z","title":null,"venue":null,"work_id":"aa47de03-6789-474c-b19b-08ec721d7f9d","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.785118Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:b770de5321bbb0b4828d2b702542a8d56fe0281a32201193211e07335d4903cf","observation_id":"431ce30d-1425-4841-a6d7-0eee7545c230","resolution":{"observed_at":"2026-08-10T10:42:08.503101Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.472184Z","title":"Zhang, Q","venue":null,"work_id":"57e92d07-14ce-4c7a-9d42-181d5141ab7a","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.791040Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:f598397b5e4ed0e3d8ef814f0b390c8660c8a50f88c0b1a2170520e720e585c3","observation_id":"fbd27977-3d57-48dd-8431-8f2f532e60b0","resolution":{"observed_at":"2026-08-10T10:42:08.478180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06160","last_updated":"2018-02-02T01:43:54Z","snapshot_observed_at":"2026-07-06T05:00:35.763958Z","submitted_at":"2016-06-20T15:02:31Z","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06160","snapshot_observed_at":"2026-08-10T10:42:07.797545Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.797545Z"},"links":{"cited_paper":"/paper/1606.06160","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:e5f3e54f3601320c5b2c977f18e60625914bbbe0299c09f9250481c55304b890","observation_id":"a6154ec1-a0b6-47ef-8e0e-52c835f3376a","resolution":{"observed_at":"2026-08-10T10:42:07.797545Z","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":"2026-08-10T10:42:08.450315Z","title":"Unitary Recurrent Neural Networks (URNNs) were introduced in Arjovsky et al","venue":null,"work_id":"4a1d6c0e-bc59-49c8-86a5-124a5b395b6e","year":2016},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.809819Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:8aed48a75c67bd07d6db1e65513debcc667d3457dd38c788b1c874d2021cf42f","observation_id":"7f328653-f278-48ee-ac92-45b0bfd71dbe","resolution":{"observed_at":"2026-08-10T10:42:08.456663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.346097Z","title":"F M ORE BENCHMARKS In Appendix F.1, we provide a comparison of HadamRNN and quantized versions of BERT on the SST-2 and QQP benchmarks from GLUE (Wang et al., 2019)","venue":null,"work_id":"2a735a8c-0640-4b01-8869-62f7987d1d99","year":2018},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.838387Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:f61c1a5089711de998c9fe8e08c9885d37289fb1651dea2bb0547e656fd76c6a","observation_id":"605c1baa-bbe6-442b-b12e-e1d8863a5d23","resolution":{"observed_at":"2026-08-10T10:42:08.351890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.305916Z","title":"(2022)) 88.7 13 400 BiBERT (Qin et al.,","venue":null,"work_id":"ace9ac81-eb84-4f84-b6a7-4c125852f975","year":2022},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.848763Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:53ab804f91080b666afcf718b031854e0d757e6d4c8ec74a05ee5478048b9e66","observation_id":"fbd96d88-dc96-4673-b0db-481f754edf1d","resolution":{"observed_at":"2026-08-10T10:42:08.313169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.278950Z","title":"This result surpasses the smallest BiBERT, despite our model being more than 130 times smaller","venue":null,"work_id":"87f05752-73f6-4ac5-a6c4-5eccfbb99e96","year":2018},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.853724Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:2a81dd528fb45112360824de2364217b8972bbfbf896a5fa0bf1692f37f12444","observation_id":"db5e508f-b6e6-4410-a380-9bc31f5dea1f","resolution":{"observed_at":"2026-08-10T10:42:08.287556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.254609Z","title":null,"venue":null,"work_id":"28762480-461c-4b8f-aae3-8a9f804b7875","year":2018},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.858470Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:8ab6feb1c2d8515af5a161a0f7806ed118a178d774ca160f3a0ecee60e3dba89","observation_id":"ff16ec61-b480-43a9-b31c-5cbd271c1e68","resolution":{"observed_at":"2026-08-10T10:42:08.260834Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.214737Z","title":"Conversely, in the ReLU-ORNN case, the norm increases, possibly approaching0","venue":null,"work_id":"9dfc76e6-f2cc-4ff7-b60e-82c3f8c79353","year":2021},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.872648Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:b7d2329a0037f2d63f07bac18f1af6a5cfd1571ca8fa5db9fde314d11110ec1f","observation_id":"05e98e88-17b9-4ab4-95e5-55005af2fbde","resolution":{"observed_at":"2026-08-10T10:42:08.220894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.160733Z","title":"29 Published as a conference paper at ICLR 2025 Table 10: Value of𝛼𝑊 and𝛼ℎ for activation quantification across the datasets and bitwidth","venue":null,"work_id":"60d51d8b-8e1d-46c8-bdaf-618195fb1722","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.888794Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:fe14ff295e4e4aa820fad0ffda8ea06599e6131d604efe375301913a423a4fd8","observation_id":"92d3f3bd-d513-45e5-aa1b-6eb4ec399f3f","resolution":{"observed_at":"2026-08-10T10:42:08.173371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:42:08.326784Z","title":"In comparison, the smallest BiBERT model, distilled from a BERT pre-trained on a large dataset and with a network size 550 times larger, achieves85.4%","venue":null,"work_id":"09dfd8b7-b57e-40f6-9b86-5ead8c0fc278","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.843737Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:e641b2bf4391ece1158a4e67f02e010b10f0e63399841acf27fecb1f8659979f","observation_id":"490a0888-9921-4936-9c64-68c0953ab764","resolution":{"observed_at":"2026-08-10T10:42:08.333205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.10176","last_updated":"2016-11-30T14:33:08Z","snapshot_observed_at":"2026-07-06T05:20:45.882004Z","submitted_at":"2016-11-30T14:33:08Z","title":"Effective Quantization Methods for Recurrent Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.10176","snapshot_observed_at":"2026-08-10T10:42:07.748234Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":1893,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.748234Z"},"links":{"cited_paper":"/paper/1611.10176","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:6e170968e2f9753803c56b9c3d1d407a163e912e7e55d20c643ab7613665a210","observation_id":"874b4e14-6332-42d9-94af-51ab41e5d586","resolution":{"observed_at":"2026-08-10T10:42:07.748234Z","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":"2026-08-10T10:42:08.538356Z","title":"Helfrich, D","venue":null,"work_id":"a1a5e7df-df8f-4aca-88aa-1a9de19aac3a","year":1969},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":1978,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.754444Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:ea199df2ad1b51e79ed847f96afb50f489a44b5a6301cde8a64c31113ef8fa6a","observation_id":"2efec118-3030-4ceb-a565-9816cd3ce6ab","resolution":{"observed_at":"2026-08-10T10:42:08.543651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-10T10:42:07.734326Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.734326Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:e25d70f4ce53eaa74fc8b1bb85e9e6ab6901ae8f9a1bbaec2295d0d0a1131890","observation_id":"f1e7f8cd-ef51-4933-8ea8-cefa928447da","resolution":{"observed_at":"2026-08-10T10:42:07.734326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1602.02830","last_updated":"2016-03-17T14:54:25Z","snapshot_observed_at":"2026-08-10T10:55:02.784121Z","submitted_at":"2016-02-09T01:01:59Z","title":"Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.02830","snapshot_observed_at":"2026-08-10T10:42:07.728028Z","title":"Courbariaux, I","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.728028Z"},"links":{"cited_paper":"/paper/1602.02830","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:b9f1d7204a9923b3c9449ef0b78e8674b06b102c60df3afe12198e328035e464","observation_id":"99945597-c8c2-404a-8623-1cb9ae615a30","resolution":{"observed_at":"2026-08-10T10:42:07.728028Z","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":"2026-08-10T10:42:08.516751Z","title":null,"venue":null,"work_id":"df3679ae-8d8e-4ba9-8add-40a4ce7a925c","year":2025},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.759778Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:600a9a4b9e522e203ec69191ef4054b6197fbfb4fbab667e0579e8e3c3a3fea6","observation_id":"3b11ee7e-fc09-4f73-8575-ab97b55af089","resolution":{"observed_at":"2026-08-10T10:42:08.523570Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1510.03009","last_updated":"2016-02-26T05:24:30Z","snapshot_observed_at":"2026-07-06T04:32:42.614338Z","submitted_at":"2015-10-11T04:32:39Z","title":"Neural Networks with Few Multiplications","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.03009","snapshot_observed_at":"2026-08-10T10:42:07.765280Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.765280Z"},"links":{"cited_paper":"/paper/1510.03009","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:9bb62372a99ce141927beea680934cad509e7f21e7cea2c388b2ba25fab1fb27","observation_id":"64b08c3a-af58-45ea-8a7d-d61474f870f7","resolution":{"observed_at":"2026-08-10T10:42:07.765280Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-08-11T05:54:56.124984Z","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":"2026-08-10T10:42:07.721102Z","title":"Bengio, N","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.721102Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:75e7bf76e7685e07074ca9dbaea5bc42d65dd0bc959da9905842dc7cb398bc92","observation_id":"a30a1905-4703-4a14-a87d-d5eeee28ca9d","resolution":{"observed_at":"2026-08-10T10:42:07.721102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.17888","last_updated":"2023-05-29T05:22:11Z","snapshot_observed_at":"2026-08-07T18:58:35.737110Z","submitted_at":"2023-05-29T05:22:11Z","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.17888","snapshot_observed_at":"2026-08-10T10:42:07.771646Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.771646Z"},"links":{"cited_paper":"/paper/2305.17888","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:d73f4d2ae1081f3ece963de96cd204596e60a40fde780834bd726d98408bf16c","observation_id":"a52df254-b171-450b-9fe9-a2d359a9b27b","resolution":{"observed_at":"2026-08-10T10:42:07.771646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06902","last_updated":"2017-02-26T14:01:40Z","snapshot_observed_at":"2026-07-06T05:08:01.620233Z","submitted_at":"2016-08-24T17:15:29Z","title":"Recurrent Neural Networks With Limited Numerical Precision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06902","snapshot_observed_at":"2026-08-10T10:42:07.779606Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.779606Z"},"links":{"cited_paper":"/paper/1608.06902","citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:21562ad2af1ddebd4fb74497e2d59bf1817189c90d76824266c9bee20f66941e","observation_id":"97321f2d-cdc4-4546-a510-53aeee7af956","resolution":{"observed_at":"2026-08-10T10:42:07.779606Z","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":"2026-08-10T10:42:08.558082Z","title":null,"venue":null,"work_id":"5a0403dc-e9b6-4e71-bf8f-15094b5ad79f","year":2018},"citing_paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","version":4},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T10:42:07.713915Z"},"links":{"citing_paper":"/paper/2502.00047"},"observation_digest":"sha256:59cfc7759ed5bcfc980fa22e0e4c9ae17863a4f128e5b6291c8f18773d6b7054","observation_id":"79de15a4-635e-4045-b0b0-6ff2f9c14337","resolution":{"observed_at":"2026-08-10T10:42:08.564883Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.00047","last_updated":"2025-05-06T09:45:34Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T10:32:40.909089Z","submitted_at":"2025-01-28T09:16:28Z","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":1,"verified_fuzzy":13},"total_outbound_references":29},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2502.00047."}