{"as_of":"2026-08-12T19:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:724523893411a4ade6efd09a841e806a71c37ae1d633f6f9d65eda7e57f6c479","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":"2026-08-11T10:56:33.229857Z","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":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.15983/citation-record","integrity":"/paper/2412.15983/integrity","json":"/paper/2412.15983/citation-record.json","paper":"/paper/2412.15983"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:32.977808Z","title":"Finding structure in time,","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:32.977808Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:5c9d442bcb56be1adee26bc69570f7a726464d10934f7e0fff86fe69eb5b7bcd","observation_id":"cf1d8ca2-a7d0-4c6e-9e6c-46f6eae935de","resolution":{"observed_at":"2026-08-11T10:56:32.977808Z","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":"2026-08-11T10:56:34.359080Z","title":"Neural networks and physical systems with emergent collective computational abilities,","venue":null,"work_id":"fdcb50d3-0c78-4212-87d3-86cc328f9dd9","year":1982},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:32.984370Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:104b41338a141e58088031824d49963feffe0e30a2261eba89a89b1d52c55ce1","observation_id":"2f692704-9494-430f-9f04-bef00a510ae1","resolution":{"observed_at":"2026-08-11T10:56:34.366844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-07-06T03:45:28.546418Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-11T10:56:32.991870Z","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:32.991870Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:12caff325dfbb9d0d3a2fb0713b802783f1c1e89a4f8c64cf843f6d3d9ea414c","observation_id":"c372dae3-2c0c-4c24-aa6c-3c00ffc97242","resolution":{"observed_at":"2026-08-11T10:56:32.991870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00396","last_updated":"2022-08-05T17:54:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-10-31T03:32:18Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.00396","snapshot_observed_at":"2026-08-11T10:56:32.997889Z","title":"Efficiently modeling long sequences with structured state spaces,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:32.997889Z"},"links":{"cited_paper":"/paper/2111.00396","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:2ad61a43603c33e679d70750465e3c5eebf00a798df1f6816d519218967f8585","observation_id":"7510738f-745e-4d7a-acec-793b96b3703f","resolution":{"observed_at":"2026-08-11T10:56:32.997889Z","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":"2026-08-11T10:56:33.005956Z","title":"Resurrecting recurrent neural networks for long sequences,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.005956Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:cfeb6b42340af3a9200630e32f955a8ff3b942bee5704f1808be234876a71566","observation_id":"6ea6b151-2d96-44c7-8652-f65050171065","resolution":{"observed_at":"2026-08-11T10:56:33.005956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.04933","last_updated":"2023-03-03T18:35:28Z","snapshot_observed_at":"2026-07-06T13:40:19.948018Z","submitted_at":"2022-08-09T17:57:43Z","title":"Simplified State Space Layers for Sequence Modeling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.04933","snapshot_observed_at":"2026-08-11T10:56:33.013099Z","title":"Simplified state space layers for sequence modeling,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.013099Z"},"links":{"cited_paper":"/paper/2208.04933","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:fb150b9226b06de3c0fe02194de9ebcfa727c4e8dc42dc9f24ddc2d1699ab479","observation_id":"81117a0f-1d85-43c5-9506-c3f39b54c99d","resolution":{"observed_at":"2026-08-11T10:56:33.013099Z","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":"2026-08-11T10:56:34.322572Z","title":"Surrogate gradient learning in spiking neural networks,","venue":null,"work_id":"fe1264fa-e4e1-4e54-9a51-1c63d14e2e8f","year":2019},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.022380Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:947783d490ae52e4c57c5d981034618a33b9b51e9351d81d4bb7d6e464bd31be","observation_id":"24e8fd1d-7d59-4341-aa25-18f6b08e3be8","resolution":{"observed_at":"2026-08-11T10:56:34.328630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.030401Z","title":"Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.030401Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:5dc5bc4f4adec7dd2ee4ffea102971f5485284f8dd313c32c01717063d6ce034","observation_id":"2f7eeb7a-b92b-44d3-8b66-37f55da03682","resolution":{"observed_at":"2026-08-11T10:56:33.030401Z","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":"2026-08-11T10:56:33.036790Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.036790Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:367f1a19362b07f7a8202abacf3d5c4501011150cfbca83bfd1b402d0b300583","observation_id":"4ff349b7-59e5-46d5-868a-77b1bba50254","resolution":{"observed_at":"2026-08-11T10:56:33.036790Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-11T10:56:33.043639Z","title":"Roberta: A robustly optimized bert pretraining approach,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.043639Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:e3f362dae3d8d819474d1a8348ef85d0eef3a2498802f55389a2bee508789a91","observation_id":"64762a6c-af2e-4a5b-9076-530d574d281e","resolution":{"observed_at":"2026-08-11T10:56:33.043639Z","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":"2026-08-11T10:56:33.050097Z","title":"Language mod- els are few-shot learners,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.050097Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:d58a8c98d0db528e8e62f3de29932e14e09e078fbe0984354579961783c17111","observation_id":"adacdd0d-a2ce-4581-82b1-df7b13834a66","resolution":{"observed_at":"2026-08-11T10:56:33.050097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.10094","last_updated":"2021-07-27T00:20:03Z","snapshot_observed_at":"2026-08-05T05:54:57.605467Z","submitted_at":"2021-02-19T18:51:10Z","title":"Formal Language Theory Meets Modern NLP","version":3},"cited_work":{"arxiv_id":"2102.10094","doi":null,"metadata_source":"pith","pith_arxiv_id":"2102.10094","snapshot_observed_at":"2026-08-11T10:56:33.616275Z","title":"Formal Language Theory Meets Modern NLP","venue":"cs.CL","work_id":"6eb8eb58-a52f-492c-9e45-57b3291017f9","year":2021},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.057477Z"},"links":{"cited_paper":"/paper/2102.10094","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:e9567ea1058a23441d3ae0f10bb211800803ec560ce5c68506db6f5354cbf50a","observation_id":"dd226dcc-4d70-4010-a9d8-95583c6e2db7","resolution":{"observed_at":"2026-08-11T10:56:33.624107Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.064442Z","title":"Stuffed mamba: State collapse and state capacity of rnn-based long-context modeling,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.064442Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:1b4517e16ee9555914b3bb74e1cf4b52b9883fb4607e2e555d842c6196167b03","observation_id":"aadd0903-465a-4048-9426-f3772f7e6259","resolution":{"observed_at":"2026-08-11T10:56:33.064442Z","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":"2026-08-11T10:56:34.228691Z","title":"Computational capabilities of neural networks,","venue":null,"work_id":"9d7de9e1-7422-4c1a-956d-6464b9ed76bc","year":1995},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.070732Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:856dbb73d400edcca96496a9a0b56e83de83276e7e100ad01c98ab95567e8d20","observation_id":"89b2164a-648e-4326-be04-174a314cb38f","resolution":{"observed_at":"2026-08-11T10:56:34.240423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:34.186661Z","title":"Neural networks with recurrent operations for processing arbitrary-length sequences,","venue":null,"work_id":"f390dd65-3484-4e80-989b-ba56b2931432","year":2021},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.079142Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:faa87c1a508261160b9d3d9e77d7bf8320cd81d3b59f14a9a90fe05699e2d211","observation_id":"1ac2e087-e486-444c-b3a3-4a21c602d62a","resolution":{"observed_at":"2026-08-11T10:56:34.195371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1610.10099","last_updated":"2017-03-15T18:09:51Z","snapshot_observed_at":"2026-07-06T05:16:51.224466Z","submitted_at":"2016-10-31T19:56:39Z","title":"Neural Machine Translation in Linear Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.10099","snapshot_observed_at":"2026-08-11T10:56:33.084928Z","title":"Neural machine translation in linear time,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.084928Z"},"links":{"cited_paper":"/paper/1610.10099","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:6b415252831ea43bae8231c63eec55ea83b0102717371c5d3c73e0cef258c97c","observation_id":"1078581d-6a1f-4fca-a502-338a05d026eb","resolution":{"observed_at":"2026-08-11T10:56:33.084928Z","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":"2026-08-11T10:56:34.159598Z","title":"Attentive decision-making and dynamic resetting of continual running srnns for end-to-end streaming keyword spotting,","venue":null,"work_id":"fb536d4f-248e-49a2-8039-88424382f570","year":2022},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.092307Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:4c672605d695f71492df4ad64705b8db61ed0e72d012f71cc59af602ee50652d","observation_id":"12b2e025-4163-45d1-8a45-edd7b6f83236","resolution":{"observed_at":"2026-08-11T10:56:34.165449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.04006","last_updated":"2020-11-08T15:53:56Z","snapshot_observed_at":"2026-08-09T15:12:21.086848Z","submitted_at":"2020-11-08T15:53:56Z","title":"Long Range Arena: A Benchmark for Efficient Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.04006","snapshot_observed_at":"2026-08-11T10:56:33.099122Z","title":"Long range arena: A benchmark for efficient transformers,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.099122Z"},"links":{"cited_paper":"/paper/2011.04006","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:c4da4ac26b0193c7c1b3f7e5931426ef857cdc6411a798f8ae707fa28d6db225","observation_id":"7314ab5c-18eb-4138-a9f1-853d61ca8dea","resolution":{"observed_at":"2026-08-11T10:56:33.099122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.12147","last_updated":"2021-12-23T18:53:38Z","snapshot_observed_at":"2026-08-11T21:02:33.039857Z","submitted_at":"2021-12-22T18:59:21Z","title":"Generative Models of Brain Dynamics -- A review","version":2},"cited_work":{"arxiv_id":"2112.12147","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.12147","snapshot_observed_at":"2026-08-11T10:56:33.414438Z","title":"Generative Models of Brain Dynamics -- A review","venue":"q-bio.NC","work_id":"855f5003-3280-4254-84fb-f7781a84c5b6","year":2021},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.105935Z"},"links":{"cited_paper":"/paper/2112.12147","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:8353f42a837453cf049da6890678ae8ed7db802f1885e610ba650c3b6cddcb18","observation_id":"1c1e7050-a793-405f-a9d9-caf828476441","resolution":{"observed_at":"2026-08-11T10:56:33.420120Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:34.135566Z","title":"Reservoir memory machines as neural computers,","venue":null,"work_id":"2e004900-99ed-4492-80ae-fd0905d5d377","year":2021},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.112326Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:bc2cf1689079e3d834968fff0e943c31092c4978ae2b1ca775361154cc71906f","observation_id":"738385ee-a6dd-410b-a370-b3fa0a77c169","resolution":{"observed_at":"2026-08-11T10:56:34.143590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.08387","last_updated":"2020-10-20T13:15:59Z","snapshot_observed_at":"2026-08-07T22:29:44.795145Z","submitted_at":"2020-06-15T13:20:13Z","title":"Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech","version":2},"cited_work":{"arxiv_id":"2006.08387","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.08387","snapshot_observed_at":"2026-08-11T10:56:33.375127Z","title":"Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech","venue":"cs.CL","work_id":"7cea944d-c0f6-48a1-95b0-434329a0506f","year":2020},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.117857Z"},"links":{"cited_paper":"/paper/2006.08387","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:75bc59161ce46cf91b76c4b3c64a506c7b80c97fa4df3e1c04644fa3af87052b","observation_id":"5a193ce3-404c-4f55-b0aa-4d73ec60678b","resolution":{"observed_at":"2026-08-11T10:56:33.386640Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:34.105942Z","title":"Efficient modeling of long sequences with structured state spaces,","venue":null,"work_id":"04fc3bc2-b5ac-42fd-9c45-2ffc2734e1dc","year":2022},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.124762Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:ca5016c872ed1baf3abb002b17689a35ec5bfec1860d234fb0247cb61b74d0cd","observation_id":"ed35c084-3564-45e3-ae0c-ae8b444d9c09","resolution":{"observed_at":"2026-08-11T10:56:34.117992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13948","last_updated":"2024-10-27T08:32:11Z","snapshot_observed_at":"2026-08-10T04:32:31.633232Z","submitted_at":"2023-05-23T11:17:45Z","title":"Decoupled Kullback-Leibler Divergence Loss","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13948","snapshot_observed_at":"2026-08-11T10:56:33.130738Z","title":"Decou- pled kullback-leibler divergence loss,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.130738Z"},"links":{"cited_paper":"/paper/2305.13948","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:2b0f2ee3a2a696dbee8a0d5027d959e51563162209e51897109b1cde1ae5736c","observation_id":"2ccb582f-498d-42fb-9b21-25ff16cc79a1","resolution":{"observed_at":"2026-08-11T10:56:33.130738Z","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":"2026-08-11T10:56:34.074269Z","title":"On the difficulty of training re- current neural networks,","venue":null,"work_id":"6b02e343-281a-40e6-9002-036947f197e5","year":2013},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.136914Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:231fba71478081b9e01c2c2d233745871ce2e5e3c1f9777016d21a76a638a60d","observation_id":"458fd37d-fec0-47e7-9fd8-fef2bd7054c1","resolution":{"observed_at":"2026-08-11T10:56:34.087765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.142730Z","title":"Learning long-term dependencies with gradient descent is difficult,","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.142730Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:8c1fb72f2baaf78eff2173aca03e1e4531d07236ecc6616c1bbbc7963c96d52e","observation_id":"bb225191-8523-4af0-b7b0-092aea7ebcce","resolution":{"observed_at":"2026-08-11T10:56:33.142730Z","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":"2026-08-11T10:56:34.022174Z","title":"Learning to forget: Continual prediction with lstm,","venue":null,"work_id":"bd6dcfe3-68f3-4e45-b4c0-e2f28ca93f35","year":2000},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.148557Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:f2056d8a43fd7668243b62eae9144ee92d5d18e2852118c75530c4b7758bd745","observation_id":"eee8b0d8-83f5-4971-abbf-074fb53e619b","resolution":{"observed_at":"2026-08-11T10:56:34.033365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06027","last_updated":"2016-10-19T04:32:46Z","snapshot_observed_at":"2026-07-06T05:07:42.723236Z","submitted_at":"2016-08-22T01:42:45Z","title":"Surprisal-Driven Feedback in Recurrent Networks","version":4},"cited_work":{"arxiv_id":"1608.06027","doi":null,"metadata_source":"pith","pith_arxiv_id":"1608.06027","snapshot_observed_at":"2026-08-11T10:56:33.313902Z","title":"Surprisal-Driven Feedback in Recurrent Networks","venue":"cs.LG","work_id":"ba2f4eb0-8a40-423a-9ba9-14d8910e1e6b","year":2016},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.154501Z"},"links":{"cited_paper":"/paper/1608.06027","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:be2a699b23cd73c758b73288b090905315a34b8d54c3e0d5bff820ffb3a19b68","observation_id":"dbc9fc86-1a23-4db0-af02-c612a2c0d8b9","resolution":{"observed_at":"2026-08-11T10:56:33.322322Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.995718Z","title":"Reading selectively via binary input gated recurrent unit","venue":null,"work_id":"e77ae72e-6b04-4fc7-830e-66c512d53568","year":2019},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.160643Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:0be1361bf84bb07f2507b17170574968f2816ea8f12bc0accc4fc284c16700f8","observation_id":"05f94a2e-f0bb-4561-8369-c5fb31bd959c","resolution":{"observed_at":"2026-08-11T10:56:34.002682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.165580Z","title":"Long short-term memory,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.165580Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:a627d0e5a667ce80825376a285ab925410a9b8ef2c1dac9808cf4b86c057868b","observation_id":"6bea2793-207e-4d01-ac94-c5fce7622a83","resolution":{"observed_at":"2026-08-11T10:56:33.165580Z","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":"2026-08-11T10:56:33.948021Z","title":"Lyapunov-stable deep equilibrium models,","venue":null,"work_id":"46657662-e2ca-4e6d-aeec-e82208b6fd1b","year":2024},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.170700Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:257e33825aae2d2e8fab65026c3cd049d553c66bee41afeaa10e05b4979589e7","observation_id":"00c63eb2-e5b6-40d1-bda7-f2e38ac42d74","resolution":{"observed_at":"2026-08-11T10:56:33.958564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-07-06T06:32:32.083176Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-11T10:56:33.175994Z","title":"Speech commands: A dataset for limited-vocabulary speech recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.175994Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:8e1e48f89a6af9902f196521cb14db607c9b73d73af43ed8bfcab05e8f0a29e9","observation_id":"011a4617-a989-4c8d-9422-be6d36464fee","resolution":{"observed_at":"2026-08-11T10:56:33.175994Z","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":"2026-08-11T10:56:33.922096Z","title":null,"venue":null,"work_id":"8a6fca73-d05f-46c2-8231-8dd1d5c6828c","year":null},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.181803Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:b69483b38b879a5e7d5594ffe8a9a143966a0317194932d5c3f3f379cbbd7245","observation_id":"40cd730e-be5f-4d38-a753-55025c14fe8e","resolution":{"observed_at":"2026-08-11T10:56:33.929593Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.885080Z","title":"This convergence limits the network’s ability to capture new information","venue":null,"work_id":"65ea7038-7e22-4932-a2a8-99d884760c29","year":null},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.186901Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:f4a3e6ffd40bfdaad9526802831cd21ad654b70deaf9fd49d8efa7ca7868ad25","observation_id":"15acac95-c1d1-4242-963d-48373bd0a0cc","resolution":{"observed_at":"2026-08-11T10:56:33.894213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.859851Z","title":null,"venue":null,"work_id":"00e604b2-36ea-49e5-9788-f81ff23806ef","year":null},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.192229Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:c4c7f97229d8ea5a7affc287b26ee0a9d5180759c91c2d51c4de0fe6d9ef0c57","observation_id":"6f696b9c-3d36-483f-bf4d-7840899ff7ae","resolution":{"observed_at":"2026-08-11T10:56:33.865745Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.836788Z","title":null,"venue":null,"work_id":"34e6b0be-a847-461a-93fb-b8fd9bdcb54d","year":null},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.198040Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:deaf637e79dbbc2d71786c6b0913a6249e837a3a74ce71683015b08a0d787bc1","observation_id":"0d967e18-7399-4d2b-b66d-bca8ea634483","resolution":{"observed_at":"2026-08-11T10:56:33.844367Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.806632Z","title":null,"venue":null,"work_id":"04284e42-8256-464c-ac95-81f912024fb5","year":null},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.212091Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:1ccca93c91b1aa236fd9477f264362e11e28a634961402daa9b1bc38f1867764","observation_id":"e3faa840-4548-4863-8dc2-0bd921da3930","resolution":{"observed_at":"2026-08-11T10:56:33.820021Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.772209Z","title":null,"venue":null,"work_id":"d19a0e1b-512d-4f33-9d56-92a3eb877db1","year":null},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.221279Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:2db65b8a1b1f816108530a84852263e650c2674712dd7e7ef471fb1e8942687e","observation_id":"558c71d6-291b-4009-bc93-b4df036e876a","resolution":{"observed_at":"2026-08-11T10:56:33.782396Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:56:33.747328Z","title":"APPENDIX B TRAINING We implement all experiments using the AdamW optimizer with a batch size of 512 and an initial learning rate of 3e-3 across all experimental conditions","venue":null,"work_id":"9004c7bc-b8aa-4cf3-8d63-169b56935cf3","year":null},"citing_paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T10:56:33.229857Z"},"links":{"citing_paper":"/paper/2412.15983"},"observation_digest":"sha256:8256adfb859d2b8e593465bdfaaab0af418ac2dbf525e93e2cac5c77ff210bda","observation_id":"745da528-e118-4fc3-8a60-6ba2d055eb60","resolution":{"observed_at":"2026-08-11T10:56:33.754666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.15983","last_updated":"2024-12-20T15:24:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T11:28:43.812747Z","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":4,"verified_fuzzy":13},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2412.15983."}