{"as_of":"2026-08-22T10:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a9ef3257abe8fa02b7217a1a359a6a9544b951d923a75df177a4415b1e19f432","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T05:11:03.062848Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/1909.01994/citation-record","integrity":"/paper/1909.01994/integrity","json":"/paper/1909.01994/citation-record.json","paper":"/paper/1909.01994"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:11:02.825192Z","title":"Goodfellow, Y","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.825192Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:c8ad9cd17d9792577d91f9d5b7c1723835d48c93efc0ecc162997c26d19c3587","observation_id":"d92b27da-c96f-4c63-9426-a7f996178b2f","resolution":{"observed_at":"2026-08-14T05:11:02.825192Z","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":"2026-08-14T05:11:03.864341Z","title":null,"venue":null,"work_id":"836914c4-a704-47af-8c11-0da52f24a519","year":2019},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.830442Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:b29a5c56e8b8a1f958507e25d959ef9b2e7f73425c6a56183d129ebc43a32f7b","observation_id":"4dcbd533-1d18-44fc-bd8c-9a7e83752806","resolution":{"observed_at":"2026-08-14T05:11:03.868621Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.851660Z","title":"Hastie, R","venue":null,"work_id":"03b2691b-79d7-4799-87be-f90e016b34fb","year":2009},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.835189Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:68e5a7c3a279774cd4022c561854fc0a1f3498809cc6dfeec1462e0872ad07de","observation_id":"8045ec2a-be1f-41df-b7cb-a7c2c958bd7d","resolution":{"observed_at":"2026-08-14T05:11:03.855713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.838319Z","title":"Robbins and S","venue":null,"work_id":"d56a31cc-7e32-4ded-9454-b99236048eb0","year":1951},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.840325Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:9a88a35da717b7055562e0172c1f4be5600ee9cfd732202cc67550f1dea28644","observation_id":"684dde69-7420-4a1b-8c24-0dbe73f69100","resolution":{"observed_at":"2026-08-14T05:11:03.842739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.824981Z","title":null,"venue":null,"work_id":"89384b05-2d4c-47b9-81cc-ae76f5879f7f","year":2010},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.844054Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:ad792c9f961d72f3add8f2e47ac6df594072b8d2cb2f2094a4ffced5e6bcc099","observation_id":"7c9a6b84-9dc8-4662-a80a-8e2d62cc88a3","resolution":{"observed_at":"2026-08-14T05:11:03.829473Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.812076Z","title":"Duchi, E","venue":null,"work_id":"cf8ebb83-fc5e-40f9-b5a6-b5effdc313e6","year":2011},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.847905Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:3b3d858b732ce3627fc3799efacc6d4f724877325b5b784189082ad32bb285ae","observation_id":"86a6d3c8-96fa-4ed2-8726-f6968bb1f143","resolution":{"observed_at":"2026-08-14T05:11:03.816418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.797984Z","title":"Recht, C","venue":null,"work_id":"00350649-2f3e-4ff2-bd2e-12a68d3ac02b","year":2011},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.852224Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:7269e3b54f7756beabe65b55e6284cba1b14592e4cda8bca247a3e7d559bb1b5","observation_id":"cacb97d8-62f5-4411-a140-4b2dffabeee4","resolution":{"observed_at":"2026-08-14T05:11:03.802719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.784060Z","title":"Adhikari, O","venue":null,"work_id":"cfcd6f8e-839d-491d-a6bd-d4eb915917bd","year":2017},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.855818Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:8f939b07cd8e60abffec7ca7c676c7389ab7148ff2be824cf1cbd6785a013965","observation_id":"9c86b0e0-faf9-457d-83ec-924ff7132ab4","resolution":{"observed_at":"2026-08-14T05:11:03.789091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.770338Z","title":null,"venue":null,"work_id":"00b8d0d3-e0e5-4977-a70b-a2ca7f82e589","year":2011},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.859374Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:4896fa2302a7191a70a01448f6e25ba3e5f965273f8c717eb4063100ada6fb4f","observation_id":"890fce02-eb17-4ed2-8c30-0ae9871ff427","resolution":{"observed_at":"2026-08-14T05:11:03.775047Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.757803Z","title":null,"venue":null,"work_id":"bff5af04-0281-448c-98e9-695c445d3043","year":2019},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.862933Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:6502e36dd85b76d2f630afade1ee91c49fe251fabb471782e7b6fd103810ef06","observation_id":"d59276ef-2154-41a2-b811-cc55865fea13","resolution":{"observed_at":"2026-08-14T05:11:03.761808Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.743856Z","title":null,"venue":null,"work_id":"f3663717-86a2-41c5-a89d-2c4f31652001","year":2017},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.866517Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:4f29ab012d961d1b8d704b7035920669ad86c9b3163e2b6013d40b098d39e88f","observation_id":"733aa9a5-6311-4c0a-b55e-a4471b114d10","resolution":{"observed_at":"2026-08-14T05:11:03.749150Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.730189Z","title":null,"venue":null,"work_id":"f30068eb-6a58-4334-9189-53a706a30bd7","year":2010},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.870348Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:e8013dc3f77e181f3e8d9a87c364c39497d08e80f074a7e646d6743c7cb60baa","observation_id":"80310657-82f7-4031-8012-ade6606bb06c","resolution":{"observed_at":"2026-08-14T05:11:03.734433Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.716490Z","title":"Martens and I","venue":null,"work_id":"e6a026e9-b151-4d1d-8508-9f816081ebde","year":2011},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.875252Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:4c85750a82ad847e8b8c23585578451f8bd4d68a107d426fdfd716fcd2e4c3b7","observation_id":"c99aac95-4398-43d9-8d5f-b7a17e91ca4a","resolution":{"observed_at":"2026-08-14T05:11:03.721592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.703076Z","title":"Martens and I","venue":null,"work_id":"7194e155-dcbd-4857-8843-7c934e0daa01","year":2012},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.879540Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:bc4cd5dac3315a039bdaf15274f298614051efca5c3d08e7a58f4a78a6699ea5","observation_id":"4d2280ba-3913-43b5-a466-c8e731e87e32","resolution":{"observed_at":"2026-08-14T05:11:03.707468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.690540Z","title":"Bollapragada, R","venue":null,"work_id":"0d7036e1-3a5b-4d65-958d-b6be7e3fe1e4","year":2016},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.884366Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:705390ad9676a340693a0aef1e49e8eac3118b8bfcb03071760ae2ef6dd9d5e8","observation_id":"84f3ba8a-9d57-4cdb-a4ff-d11ac15aed50","resolution":{"observed_at":"2026-08-14T05:11:03.694524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.5701","last_updated":"2012-12-22T15:46:49Z","snapshot_observed_at":"2026-08-19T05:19:50.480481Z","submitted_at":"2012-12-22T15:46:49Z","title":"ADADELTA: An Adaptive Learning Rate Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.5701","snapshot_observed_at":"2026-08-14T05:11:02.888355Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.888355Z"},"links":{"cited_paper":"/paper/1212.5701","citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:c3bc9d9dc4038750645c53ecbb2d4e094b9e9a08a82c6cea8f10ecf378584e6d","observation_id":"5e302f0d-a4da-4365-be40-fd7c9edfb68c","resolution":{"observed_at":"2026-08-14T05:11:02.888355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-14T05:11:02.892837Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.892837Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:5ad9887e41d08a2146813f140087d9d9e93322d31238e553aded8b83909706f4","observation_id":"9b636777-0a3f-437b-90eb-c56c5f20d7e5","resolution":{"observed_at":"2026-08-14T05:11:02.892837Z","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":"2026-08-14T05:11:03.677250Z","title":"Nocedal and S","venue":null,"work_id":"96111990-0e2e-4fdd-9296-5ddf8756b915","year":2006},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.896941Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:51f89c607f0d1dfd6b08cb081a12f6fb9b3371c3f1ee4c77fc17e5c1d31e2573","observation_id":"381c52ae-e7c4-41fe-b5ea-3be26f5dee70","resolution":{"observed_at":"2026-08-14T05:11:03.681287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.02396","last_updated":"2019-05-22T15:37:04Z","snapshot_observed_at":"2026-08-14T20:26:15.167930Z","submitted_at":"2017-10-06T13:22:59Z","title":"A Dense Initialization for Limited-Memory Quasi-Newton Methods","version":5},"cited_work":{"arxiv_id":"1710.02396","doi":null,"metadata_source":"pith","pith_arxiv_id":"1710.02396","snapshot_observed_at":"2026-08-14T05:11:03.132634Z","title":"A Dense Initialization for Limited-Memory Quasi-Newton Methods","venue":"math.OC","work_id":"d674f5f1-57bf-4376-8bff-9545f69765fb","year":2017},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.901198Z"},"links":{"cited_paper":"/paper/1710.02396","citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:fff2ba7bb89b59315eae64a3850ce848252d218d46319c930b81e283d93d59b0","observation_id":"ca8e2811-50bf-4b88-b039-06a2a5142f9b","resolution":{"observed_at":"2026-08-14T05:11:03.137165Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.663682Z","title":"Brust, J","venue":null,"work_id":"d1b57c39-a426-4ca4-a394-c64701c78289","year":2017},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.905900Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:78a6ab2a957f5397633a95d90030ede120d90e3425acc7f7a11ba1a748490031","observation_id":"2ec47884-279e-41e5-aecf-e99cb4439c5a","resolution":{"observed_at":"2026-08-14T05:11:03.668176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.650366Z","title":null,"venue":null,"work_id":"dfdae4e0-dcee-4145-9f95-18decfc4393f","year":1970},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.910137Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:22de77381879774cb18f7472a6df499fb32cc29c80fa27ed51e10caba434e5a8","observation_id":"e6132d73-2a8e-496e-bf93-d35b49c82758","resolution":{"observed_at":"2026-08-14T05:11:03.654792Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.636822Z","title":"Fletcher","venue":null,"work_id":"8d51d8d9-aced-4a5e-8ca6-8901bdeac71c","year":1970},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.914335Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:52ac91c9da37d93a77f42d7d50bfaf58ede763a019c9c4b6816c33d89e36e27d","observation_id":"d11625a2-ab12-4a6b-a6b5-4adc2cb41f5d","resolution":{"observed_at":"2026-08-14T05:11:03.641200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.621254Z","title":"Goldfarb","venue":null,"work_id":"f666fee1-b7d0-450f-bd27-23403a0d990c","year":1970},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.918686Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:c070ab1992caacb3123ea6079745c5a0953ea2c4a535754fce45c1c1101be37d","observation_id":"52bbf9b3-4a85-4337-bfc8-371dceace5fa","resolution":{"observed_at":"2026-08-14T05:11:03.626587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.607682Z","title":null,"venue":null,"work_id":"be359579-d352-445d-9c85-b6f43bacade4","year":1970},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.922676Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:86f07f2f748b7ea7d52de7b476a6c2b19d584d534a26c2a46a3aaf60839d453f","observation_id":"4c57789f-0f16-4a1f-befc-113641173225","resolution":{"observed_at":"2026-08-14T05:11:03.612074Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.592309Z","title":null,"venue":null,"work_id":"8018f335-2f2f-4eb8-92d3-40976214407d","year":2011},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.926935Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:58d18c976751eecb4300326d3fcf2d467fa1dfaf3677d4e547f1d57811fe8c35","observation_id":"94ab84a9-17f8-4e3d-ae42-ecff9a260890","resolution":{"observed_at":"2026-08-14T05:11:03.597299Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.579209Z","title":"Rafati, O","venue":null,"work_id":"c0727c10-8bc6-4487-bbc0-b71ee3aacb58","year":2018},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.930905Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:70102ce69cb44ca9f0ef5fe939cb9d4f0f52c297cc1c7983e284fb6bda1d1ca3","observation_id":"a110a1c4-8b16-450f-ba38-f3f4be05ef2b","resolution":{"observed_at":"2026-08-14T05:11:03.583438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.564815Z","title":"Burdakov, L","venue":null,"work_id":"77d20a2b-e1d9-47d7-90d9-bd8f59ba5bc6","year":2016},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.935090Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:5d1a8cbe99f9e6b8058f1125c3665a7adcd88615c1f90211c0ecf12341cf7252","observation_id":"0e67ed38-c1a0-4c1a-85bd-671abc0e9ea0","resolution":{"observed_at":"2026-08-14T05:11:03.569646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.551006Z","title":null,"venue":null,"work_id":"8391f032-f13b-40be-9b55-658d78179130","year":2018},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.939669Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:3c6ad824c064b5afc94be8bb1328e74b787dcb8c04be125ceed9eeb4f9dcf7ad","observation_id":"75dcfca3-95eb-4777-8731-b1e0cc57de92","resolution":{"observed_at":"2026-08-14T05:11:03.555052Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.536958Z","title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","venue":null,"work_id":"94110c87-c47f-4134-9de9-fdc1f2a39318","year":1996},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.944027Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:302e049cd7c6fd477b285cd9d0b4ce8e447d81950dc6249aeec5b1bd930a7c98","observation_id":"a262c5b0-c7f5-4082-88b4-07e01de73df6","resolution":{"observed_at":"2026-08-14T05:11:03.541578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.523888Z","title":"Rafati and D.C","venue":null,"work_id":"e20e98f0-fd61-47a2-bc3c-668c5bf28581","year":2015},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.948280Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:774e11e40b0b10f3e2e00d861245a4ccf8b999485676cbdf427fbf7c3da12a6e","observation_id":"fa2c2e92-007c-4677-a5f4-7fcc74e3971d","resolution":{"observed_at":"2026-08-14T05:11:03.528231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.510448Z","title":"Rafati and D.C","venue":null,"work_id":"c568c2b7-7b40-4e66-ab80-64fb5dbca35e","year":2017},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.952293Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:04c62db739d83d81f030620c41e147523387996bcf05f9c21626d52871e9b369","observation_id":"b8f829ee-6c79-496d-80bd-a11c4ba26ccd","resolution":{"observed_at":"2026-08-14T05:11:03.514916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.496829Z","title":"Rafati Heravi","venue":null,"work_id":"0f452f01-27b4-4b4d-b306-680dc864d998","year":2019},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.956466Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:e6dfdf7edfb70148ca977a4ff7093e31c7b961be314f7155a70e033287318fbe","observation_id":"2a3f56f6-d9a4-4a73-a7d9-7dbf7ea6e05f","resolution":{"observed_at":"2026-08-14T05:11:03.501113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.10096","last_updated":"2019-04-12T16:37:31Z","snapshot_observed_at":"2026-08-14T18:10:18.820038Z","submitted_at":"2018-10-23T21:24:06Z","title":"Learning Representations in Model-Free Hierarchical Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"1810.10096","doi":null,"metadata_source":"pith","pith_arxiv_id":"1810.10096","snapshot_observed_at":"2026-08-14T05:11:03.111087Z","title":"Learning Representations in Model-Free Hierarchical Reinforcement Learning","venue":"cs.AI","work_id":"4025400e-f131-4b76-a06b-40abb94489c6","year":2018},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.961196Z"},"links":{"cited_paper":"/paper/1810.10096","citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:5b2d9fd4ff466590ea2ebd39f6d93a0287fae89261bfd76a9bd711aed3dad361","observation_id":"4bc88f45-e231-4428-bc54-6a8c02da8162","resolution":{"observed_at":"2026-08-14T05:11:03.117555Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.483458Z","title":null,"venue":null,"work_id":"efa00029-c06a-40cc-88be-794a9606ea11","year":2008},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.965411Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:e9b372a33735378b9b989df653c3597dd30cc0a81d6b356b70e459629a470357","observation_id":"b02ae9e2-32a5-426a-a7cc-e7b5c5bda50d","resolution":{"observed_at":"2026-08-14T05:11:03.487991Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.469455Z","title":null,"venue":null,"work_id":"2dad22d6-6d80-4d8e-9533-3c202a9f54df","year":1995},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.969643Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:d60c3389c2b2af6f0d73257ebadca0ee10825d7a3e71b956042b485e9503a4f2","observation_id":"6278ac0a-7276-4b27-a6e3-6e021e1a6648","resolution":{"observed_at":"2026-08-14T05:11:03.474629Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.5602","last_updated":"2013-12-19T16:00:08Z","snapshot_observed_at":"2026-08-17T17:19:33.060917Z","submitted_at":"2013-12-19T16:00:08Z","title":"Playing Atari with Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.5602","snapshot_observed_at":"2026-08-14T05:11:02.974003Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.974003Z"},"links":{"cited_paper":"/paper/1312.5602","citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:b292b3ac675dbfb614f9cf56269a36c06f815af79e19c0d51cf93ce88664c8f7","observation_id":"eb73b045-55ad-42fd-8869-017bbbef6ac4","resolution":{"observed_at":"2026-08-14T05:11:02.974003Z","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":"2026-08-14T05:11:03.456259Z","title":null,"venue":null,"work_id":"4e70d2f2-2ce4-4594-b97c-c608ca0106c3","year":2015},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.978411Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:2fa1fe0d687e3f69583292e54a43d7e364e908a114a669f083933de909bdea61","observation_id":"fd1e2ca8-a6d1-4510-aebc-e1e63d807230","resolution":{"observed_at":"2026-08-14T05:11:03.460631Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.442466Z","title":"Silver, A","venue":null,"work_id":"549c8ab7-a4ab-4c07-8cfa-d09cadef75f3","year":2016},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.982047Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:fb61c03f93cfc17c3203cd9162855af981df5be2a23e2a5e0d71a3de2d08a14d","observation_id":"46d92a55-b096-4c4c-bfa7-be4ddf044463","resolution":{"observed_at":"2026-08-14T05:11:03.447259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.429458Z","title":null,"venue":null,"work_id":"c340eb5b-c76b-4b5e-9c0a-33f66232c1d3","year":1969},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.985453Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:ecb92ff2be32e9b0e318c30a8e2868ada85eed2afd86e95174e995d67098f47a","observation_id":"e587a3f0-14a8-488c-841e-7acc6b8636f8","resolution":{"observed_at":"2026-08-14T05:11:03.433659Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.416653Z","title":null,"venue":null,"work_id":"1b6847e8-e136-4f37-9680-741b39ef7324","year":1981},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.989186Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:62c14b59e62038fea3ffaf563188daedad4ee9bf67c14645bc33f378182bf721","observation_id":"8052d863-034c-4d8a-835f-417941a473c6","resolution":{"observed_at":"2026-08-14T05:11:03.420745Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.403504Z","title":null,"venue":null,"work_id":"edb8177e-dd00-49ef-8e62-51b221f463ff","year":1983},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.993103Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:ffc01ca9a5b41d577bf371087224aa7d656b475091a2cb165328a680d668fe96","observation_id":"ef3da8e6-803d-4d63-98e1-446734ef7fb9","resolution":{"observed_at":"2026-08-14T05:11:03.407726Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.390305Z","title":null,"venue":null,"work_id":"3bd6c47a-0e8f-4f48-8f48-8c2a336c812b","year":2000},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:02.996831Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:6860bfe9fee95f43c6c42a0ba22496bcb0f8606a7286716aa210377046499f53","observation_id":"e51e347c-b1d0-4401-a0ab-d89ad7375f1e","resolution":{"observed_at":"2026-08-14T05:11:03.394697Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.377101Z","title":null,"venue":null,"work_id":"1c0213cd-741a-44ae-9418-e252dac1246a","year":1989},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.000492Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:1da27e13fe6bdfb2feaeef29be208cf671989d7ce57c2eb15db70b2c90827ef2","observation_id":"d1b9dbb3-6327-44de-a87e-881a8bc4b5de","resolution":{"observed_at":"2026-08-14T05:11:03.381540Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.364250Z","title":"Rafati and R","venue":null,"work_id":"da95f9d8-a850-4ffb-aa32-31abe1a2350e","year":2018},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.004486Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:3a32df45c708327ba2a96102f453043096e04e1478bdd42ebcbc48a10ac46542","observation_id":"1fccd193-f370-4569-a839-9d8d55839b03","resolution":{"observed_at":"2026-08-14T05:11:03.368562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.351254Z","title":null,"venue":null,"work_id":"13b90c1a-490b-49c9-ac4c-f7d6b0e2ab3e","year":1994},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.008553Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:36516a9d2d1774d70fa7e3ad6347ba58d718257176d56717f3ed607d02d51f98","observation_id":"01448191-529a-457e-a552-3754c09f309f","resolution":{"observed_at":"2026-08-14T05:11:03.355465Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.338255Z","title":"Lecun, L","venue":null,"work_id":"387828fa-418b-43a1-9742-79cf6124b48e","year":1998},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.012647Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:0e4468961dd0063691791913d331ee279fac8073ca2a34923bd3e0bd1c41b312","observation_id":"b2b2a07f-abf4-440d-b42f-e0177181a830","resolution":{"observed_at":"2026-08-14T05:11:03.342533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.324193Z","title":"LeCun and Others","venue":null,"work_id":"353be02f-848d-47df-abf8-a83fc6b5258a","year":2015},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.016678Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:a18ac7062d682a2eebcbb06873960a9abe7471d2b281de6dad1158cf0bd62bfe","observation_id":"1487c9a0-7b76-43a3-b96d-1fd853071183","resolution":{"observed_at":"2026-08-14T05:11:03.328245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.310990Z","title":"The MNIST database of handwritten digits","venue":null,"work_id":"5438c18d-ad07-4b27-ab3c-718aa3de6def","year":1998},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.020748Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:defc5be9cad7cccc79328d321e34cc7e44c758808d8970be45f42f67977bca40","observation_id":"3fe9c0cf-8e26-42c3-9afc-fc7fe4fb00aa","resolution":{"observed_at":"2026-08-14T05:11:03.315460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.297476Z","title":null,"venue":null,"work_id":"c9ece1e4-5b8b-42e0-9d93-10fe458bc04c","year":1998},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.024854Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:9ee6797bc82f60c5ad326357acf6d569396b70a2432b5e08e12455868e47bd0a","observation_id":"33f5ca77-bc06-4a55-8e08-a1b1e616c433","resolution":{"observed_at":"2026-08-14T05:11:03.301850Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.283583Z","title":null,"venue":null,"work_id":"ec518a7d-bbc2-4ee0-99f7-89ac8ea54ddd","year":2016},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.029173Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:e73738fee0e6bdd95a10d9df4d54185c3b02f510f220976113aeb783b85fdf68","observation_id":"2677408e-0946-43f3-9f41-20c599d57ea9","resolution":{"observed_at":"2026-08-14T05:11:03.287835Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.269438Z","title":null,"venue":null,"work_id":"dcd46d04-e92e-48b6-b807-8eaf4827aa9a","year":2016},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.033265Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:be4a72defdbcb0dcb7e0776f5776259b4b18edcb0beab3f7b3cd71cc433bf119","observation_id":"989270b6-a87f-4081-be3d-39c71e2c06f1","resolution":{"observed_at":"2026-08-14T05:11:03.274329Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.255872Z","title":"Nesterov","venue":null,"work_id":"a3a5923e-d5cc-4ec3-bcd6-9d4d7dc1ba7c","year":2013},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.037637Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:e6098b35db3f4fb421c5725b9ffbccd3438ad5488226afe1d86ba6f559a533a4","observation_id":"d99ee6f9-8848-4402-8973-11089ca8b59b","resolution":{"observed_at":"2026-08-14T05:11:03.260339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.241722Z","title":"Jaakkola, M","venue":null,"work_id":"1df33d1d-6dae-4e23-800b-d11e1845c940","year":1994},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.041869Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:747e9eb8cc6e5a0ff8ca71fe2b83734aacb937f2c1f9e45ca424ce5736dc2bb9","observation_id":"befda12b-512e-4b63-b360-8c264cc5415c","resolution":{"observed_at":"2026-08-14T05:11:03.246212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.227656Z","title":"Brockman, V","venue":null,"work_id":"29536ca0-cbde-4a18-af30-47f7f21d824f","year":2016},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.046146Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:5f99620ce5273b966bc89f4470694d56ecc51c24d994cb4c54e4e5bd9eed9d5d","observation_id":"3653b917-9f6c-4f6e-a6ef-ec636b2a6216","resolution":{"observed_at":"2026-08-14T05:11:03.231845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.214187Z","title":null,"venue":null,"work_id":"15fc65b2-22be-474d-b90e-57858cabae2d","year":2013},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.050399Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:7f8014d9142c8598c7f65ead8dc654bb7e1e3676e4f0277ec3cde368e3f5889b","observation_id":"e2940a5a-9b7d-4ce5-841c-f18d7063f6c5","resolution":{"observed_at":"2026-08-14T05:11:03.218615Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.200256Z","title":null,"venue":null,"work_id":"e8ec8b54-d7fe-4c64-b91a-2cdff3e1e3ee","year":2012},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.054375Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:8f8397c58ce65d33ff1b1e64305f4d64bc19314e71ca37e5f7af5a8aa146b49b","observation_id":"b7a6d3c5-a52d-4446-8229-cd98ebf1e7f4","resolution":{"observed_at":"2026-08-14T05:11:03.205322Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.187136Z","title":"Hausknecht, J","venue":null,"work_id":"b03597f6-78e2-4f89-88fa-63beb7863330","year":2014},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.058524Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:0025f169f55ec4f53f8ff3e4fbdef2bec0d152bb5ed3212319425760b9840dd7","observation_id":"121236cb-0c18-468f-a48c-2825fabcf41d","resolution":{"observed_at":"2026-08-14T05:11:03.191235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T05:11:03.173485Z","title":"Schulman, S","venue":null,"work_id":"0e3622ed-fefe-41a8-b024-e5b27dfe7187","year":2015},"citing_paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T05:11:03.062848Z"},"links":{"citing_paper":"/paper/1909.01994"},"observation_digest":"sha256:82d5cf5d4a1bee013e4a1898f977b71dc1c93cfee6cd48724f3d2a6f49b7148c","observation_id":"a0795f04-b0f9-4fb7-906b-279d05f1387b","resolution":{"observed_at":"2026-08-14T05:11:03.177873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1909.01994","last_updated":"2019-09-04T15:52:08Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T21:00:11.736883Z","submitted_at":"2019-09-04T15:52:08Z","title":"Quasi-Newton Optimization Methods For Deep Learning Applications"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":2,"verified_fuzzy":28},"total_outbound_references":58},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:1909.01994."}