{"as_of":"2026-08-06T22:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:33efc94ed3aec30484cc247054f82a6218f1ed517d5c84cb4800eb70cae0152a","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-25T19:41:47.309669Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+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/1906.08654/citation-record","integrity":"/paper/1906.08654/integrity","json":"/paper/1906.08654/citation-record.json","paper":"/paper/1906.08654"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1811.04918","last_updated":"2020-06-01T17:11:51Z","snapshot_observed_at":"2026-07-06T07:14:13.912107Z","submitted_at":"2018-11-12T18:57:02Z","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","version":6},"cited_work":{"arxiv_id":"1811.04918","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1811.04918","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learnin g and generalization in overparam- eterized neural networks, going beyond two layers","venue":null,"work_id":"bad7a144-1b48-4a6d-aff6-9de2bba63e62","year":2018},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1811.04918","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:74ccb06f5d249cc6e43c84fa24607d9fda166ff4deac5b0d4fe1b6e2df422367","observation_id":"b8b94b1a-2399-4bbf-b2b8-d60b81b73834","resolution":{"observed_at":"2026-05-25T19:46:10.524339Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.03962","last_updated":"2019-06-17T06:39:04Z","snapshot_observed_at":"2026-07-06T07:13:43.676370Z","submitted_at":"2018-11-09T15:16:13Z","title":"A Convergence Theory for Deep Learning via Over-Parameterization","version":5},"cited_work":{"arxiv_id":"1811.03962","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.03962","snapshot_observed_at":"2026-07-01T21:36:15.093108Z","title":"A Convergence Theory for Deep Learning via Over-Parameterization","venue":"cs.LG","work_id":"bd8bc890-8fe4-4f45-b6a5-e4757aea9b00","year":2018},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1811.03962","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:896a33bbbc9a98d6a824b96ee89455387813aff8bd3dccff69e3bde6b56c04ac","observation_id":"4b55879c-9299-47e0-b390-ab15d01bd879","resolution":{"observed_at":"2026-05-25T19:46:10.499539Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08584","last_updated":"2019-05-27T04:22:57Z","snapshot_observed_at":"2026-08-01T13:55:48.495792Z","submitted_at":"2019-01-24T18:58:16Z","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","version":2},"cited_work":{"arxiv_id":"1901.08584","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.08584","snapshot_observed_at":"2026-07-04T10:19:47.792371Z","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","venue":"cs.LG","work_id":"3012c49d-e8f7-4778-ba52-a1df6ff6bdaa","year":2019},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1901.08584","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:6b9033493e0a566fd6da42964ecce60d478229a996ec77076f1924dc1b05aa8c","observation_id":"0cafec1a-4a76-4191-8fb9-8a1cd0f0c1d9","resolution":{"observed_at":"2026-05-25T19:46:10.511051Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Rank-r decision trees are a subclass of r-dec ision lists","venue":null,"work_id":"309dd78a-5ccf-42d0-ae98-f8fd9351b793","year":1992},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:be0c5cb4752ff652589156ab1e66feb95af666daa95d304493492e9762823112","observation_id":"6ef7d665-d658-4af8-88d0-ea6246f622ea","resolution":{"observed_at":"2026-05-25T19:47:08.335220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Weakly learning dnf and characterizing statistical query learning using fourier analysis","venue":null,"work_id":"5688fdce-34a6-430f-8c97-584e15fc8221","year":1994},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:026422c84589d1da60b31d7b90b71ced6c18751c6b1f3c060e38a87ff38d0f7c","observation_id":"52ca0074-c4b1-485d-b13c-16e660d49f42","resolution":{"observed_at":"2026-05-25T19:47:08.311384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Noise-tolera nt learning, the parity problem, and the statistical query model","venue":null,"work_id":"d39ffe00-7a57-4730-99c7-f6914eaf79f8","year":2003},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:f451cce3717f1aec31454c50412ce55ba12bbccd182c02b75f9b69791b58e6c9","observation_id":"df6fdcad-c9bd-495a-a264-2663893e45c3","resolution":{"observed_at":"2026-05-25T19:47:08.305293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10174","last_updated":"2017-10-27T14:42:09Z","snapshot_observed_at":"2026-07-06T06:06:26.276752Z","submitted_at":"2017-10-27T14:42:09Z","title":"SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data","version":1},"cited_work":{"arxiv_id":"1710.10174","doi":null,"metadata_source":"pith","pith_arxiv_id":"1710.10174","snapshot_observed_at":"2026-07-04T09:59:45.286269Z","title":"SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data","venue":"cs.LG","work_id":"bc839d89-da08-45c6-b61a-ab92b42d308f","year":2017},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1710.10174","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:d4249cff8660b535e1bfbe9173bce3697179ba6683a854667c1a9d8619b46814","observation_id":"fd65e0bd-7e58-4025-b00d-769b11c64702","resolution":{"observed_at":"2026-05-25T19:46:10.517807Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"On the proper learnin g of axis-parallel concepts","venue":null,"work_id":"474dd07b-b49b-421b-836d-66b92de3ce5c","year":2003},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:168cfaea3db848f0329cdf18f54acf8724a6c510d700e1d4805c85fcf971326b","observation_id":"44df274c-b8f9-4b29-956f-ec7dffa7c0e5","resolution":{"observed_at":"2026-05-25T19:47:08.330539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"On using extended sta tistical queries to avoid member- ship queries","venue":null,"work_id":"502e8c88-0163-4e6c-a0e3-e055483d30ca","year":2002},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:e475d9801cb9e4e67cbb9bdcd1dfd137340b2e33682dcfda25c463e157f2fdb3","observation_id":"551c350b-dd83-4b69-aef4-c3cc2e9c6635","resolution":{"observed_at":"2026-05-25T19:47:08.316389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Learning dnf from random walks","venue":null,"work_id":"110f25cb-4334-4f01-8d60-6f7df80f8704","year":2005},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:2799cf6e85bac8b7496c0062167705d459d9e2deee8e344ba5de666b94cb340b","observation_id":"0933d055-f77a-4603-ae4d-78d20f54a30d","resolution":{"observed_at":"2026-05-25T19:47:08.325898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.06521","last_updated":"2019-02-19T17:43:48Z","snapshot_observed_at":"2026-07-06T06:28:49.951458Z","submitted_at":"2018-03-17T15:26:04Z","title":"Beyond the Low-Degree Algorithm: Mixtures of Subcubes and Their Applications","version":2},"cited_work":{"arxiv_id":"1803.06521","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.06521","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Beyond the Low-Degree Algorithm: Mixtures of Subcubes and Their Applications","venue":"cs.LG","work_id":"9b7a70c1-e913-4574-96e1-8d0e88b4a13a","year":2018},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1803.06521","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:5fb36fe49db458e397db80a7b6bb84889e3f32e840b1998d806d0f519d12c671","observation_id":"090a1293-39be-49a6-95cb-7b051bfaec69","resolution":{"observed_at":"2026-05-25T19:46:10.505495Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Sgd learns the conjugate kernel class of t he network","venue":null,"work_id":"28b178f5-dd6e-49b6-ac8f-fb7635ded751","year":2017},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:3bbdff7e9f60b1216cf060a92216536d10ff8e6e12835547752b906fba729b07","observation_id":"e6689616-ba50-4f5a-b6aa-4f2f106ccfd4","resolution":{"observed_at":"2026-05-25T19:47:08.297050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02054","last_updated":"2019-02-05T01:59:59Z","snapshot_observed_at":"2026-07-06T07:05:59.910542Z","submitted_at":"2018-10-04T04:47:47Z","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","version":2},"cited_work":{"arxiv_id":"1810.02054","doi":null,"metadata_source":"pith","pith_arxiv_id":"1810.02054","snapshot_observed_at":"2026-07-10T08:56:58.947053Z","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","venue":"cs.LG","work_id":"f8869a2d-5e6f-4ab3-8826-04c3b0855136","year":2018},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1810.02054","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:d6afae9e2fbdf90f91ad2eac7d44191a220176e3b7836527fe56e4b1259caaa5","observation_id":"507705b1-a834-4a09-b5f9-84563c5a3d50","resolution":{"observed_at":"2026-05-25T19:46:10.530447Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Learning deci sion trees from random examples","venue":null,"work_id":"ecf0a8c5-a872-4463-aa0d-c313482df053","year":1989},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:33678758041f7491e027ee14b6f5fa0e80cc814d7700d5ca7f21280b74cb3291","observation_id":"507fc251-3184-4b88-b5e5-e22c632bc64d","resolution":{"observed_at":"2026-05-25T19:47:08.320699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"New results for learning noisy parities and halfspaces","venue":null,"work_id":"3440b534-8d19-48ce-8252-f0806a9f815b","year":2006},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:7507c03641050d4c077460434ba61ed8f4ca9ef951395db7bd68fc941f85b5e2","observation_id":"5646b298-5994-466c-947d-783271740b16","resolution":{"observed_at":"2026-05-25T19:47:08.300933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"On agnos- tic learning of parities, monomials, and halfspaces","venue":null,"work_id":"6da047bc-6aa0-46f0-a3a9-3beec8a87570","year":2009},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:a0a3ad6d5e1e6cc9bec332ee6648dd519cb3b89461fa123f3b241e693088996d","observation_id":"ac1b1bc6-9e03-41a8-ae27-113cbf874040","resolution":{"observed_at":"2026-05-25T19:47:08.367770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Decision trees: More the oretical justification for practical algorithms","venue":null,"work_id":"892b0093-4fc3-4c37-85eb-42a9552aad47","year":2004},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:cd844a9d5ee3f61d6728883bf7b8e1b784054e69e3081d30d64e54379e82b37c","observation_id":"c4c32737-34c7-4001-9fc2-deb5a92be012","resolution":{"observed_at":"2026-05-25T19:47:08.360104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.00764","last_updated":"2018-01-20T03:49:23Z","snapshot_observed_at":"2026-08-03T19:33:48.460543Z","submitted_at":"2017-06-02T17:25:58Z","title":"Hyperparameter Optimization: A Spectral Approach","version":4},"cited_work":{"arxiv_id":"1706.00764","doi":null,"metadata_source":"pith","pith_arxiv_id":"1706.00764","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hyperparameter Optimization: A Spectral Approach","venue":"cs.LG","work_id":"7af8c06a-1571-4aeb-87f8-0a3649910d4d","year":2017},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1706.00764","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:96c01dca149011fea432ca2566041f58828da2e3f1db11bed781bd7b443ceeef","observation_id":"7f4747ad-f2ae-450c-ad3b-cfcb8c3b7265","resolution":{"observed_at":"2026-05-25T19:46:10.459811Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Learning random log-depth decision trees under the uniform distribution","venue":null,"work_id":"785a818e-3ffe-4d7a-b67c-1c82a7c70280","year":2003},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:6255bd94edb027b6850d92d78d951e19eabfe9b91ac19a7087311c62ba80e367","observation_id":"11ef6297-fa51-40b9-a159-9f0349ef7388","resolution":{"observed_at":"2026-05-25T19:47:08.348229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"0812.0933","last_updated":"2008-12-04T13:34:26Z","snapshot_observed_at":"2026-07-06T01:46:51.846123Z","submitted_at":"2008-12-04T13:34:26Z","title":"Decision trees are PAC-learnable from most product distributions: a smoothed analysis","version":1},"cited_work":{"arxiv_id":"0812.0933","doi":null,"metadata_source":"pith","pith_arxiv_id":"0812.0933","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Decision trees are PAC-learnable from most product distributions: a smoothed analysis","venue":"cs.LG","work_id":"a7015c97-d117-4939-9837-2bdff937e0fe","year":2008},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/0812.0933","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:2e0b89d7f10b2f0819e37570461aa8bf3b2ffdb3010f724b6d33609fb86a69ae","observation_id":"74f0ff1c-5d3a-4998-8727-872fe0b2f03c","resolution":{"observed_at":"2026-05-25T19:46:10.479801Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Boosting theory towards practice: Rec ent developments in decision tree induction and the weak learning framework","venue":null,"work_id":"3e4267ba-50fc-4933-860c-559a1817f7df","year":1996},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:5ef0af6f0d642c0d516e0c57e6e6447a62735597d1648905bc05e5477689d419","observation_id":"df1bd29f-1785-49f9-934a-e5f7e1d9a601","resolution":{"observed_at":"2026-05-25T19:47:08.339793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"On the boosting abil ity of top–down decision tree learn- ing algorithms","venue":null,"work_id":"50c0deaf-66e0-4cda-bc50-1257462223ed","year":1999},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:ec4b5cf5940c1de08497515343305ea6b5eda701c6d555a29a2b54341f275d37","observation_id":"a43360c0-74de-4979-9863-2a3fabf0c96f","resolution":{"observed_at":"2026-05-25T19:47:08.381507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Learning decisio n trees using the fourier spectrum","venue":null,"work_id":"0b2cba4b-30b2-4527-beaa-39bbed9ca43a","year":1993},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:4ab7f4ec77760779f5ee86e38a1646e40f4a2a2c2fb76d71ff6464f27e7976af","observation_id":"cd02752f-6e27-4956-8dbc-d78c7ce590a1","resolution":{"observed_at":"2026-05-25T19:47:08.376112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-07-06T07:33:52.991927Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:6399a783b30f44d087c4c63d87ece2fb9f81cc9730b9303a1736adcd7db41353","observation_id":"594230e1-80ae-49d6-b302-f918a27c482b","resolution":{"observed_at":"2026-05-25T19:46:10.453628Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.04326","last_updated":"2020-02-21T04:48:07Z","snapshot_observed_at":"2026-07-06T07:44:48.972610Z","submitted_at":"2019-04-08T19:43:09Z","title":"A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics","version":2},"cited_work":{"arxiv_id":"1904.04326","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1904.04326","snapshot_observed_at":"2026-07-04T14:49:54.852173Z","title":"A comparative analysis of the opti mization and generalization prop- erty of two-layer neural network and random feature models u nder gradient descent dynamics","venue":null,"work_id":"d1f131de-7269-4368-ba6e-79d40b77927c","year":1904},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1904.04326","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:0efc14c8896baba3a56ac89bdb482f6ead90b458d9c055c9e665bfd902446c76","observation_id":"393b31fb-dcfb-4168-b006-3d3e92fc1cc3","resolution":{"observed_at":"2026-05-25T19:46:10.467554Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Learning monotone decision trees in polynomial time","venue":null,"work_id":"e7ab8551-69c9-40fd-8ff4-90a4cdbc4ca2","year":2007},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:c694f7c5d13e5316380b881346d41b049caef5ed97e953f8712b7be4c8a50ed6","observation_id":"1081f446-24fd-4850-a4bf-239520346a4c","resolution":{"observed_at":"2026-05-25T19:47:08.344001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.10004","last_updated":"2018-12-25T01:10:28Z","snapshot_observed_at":"2026-08-03T12:13:37.956525Z","submitted_at":"2018-12-25T01:10:28Z","title":"Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?","version":1},"cited_work":{"arxiv_id":"1812.10004","doi":null,"metadata_source":"pith","pith_arxiv_id":"1812.10004","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?","venue":"cs.LG","work_id":"1103d0a0-9bcb-4af8-a737-de264caef521","year":2018},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1812.10004","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:e22c5d473d7f84f5fa794d305e4601b4b94ab9ed3d7dfe363faa149ccbfe1e99","observation_id":"8727ee5b-263c-4b13-bce0-4f3c795d3377","resolution":{"observed_at":"2026-05-25T19:46:10.493693Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.04674","last_updated":"2019-02-12T23:42:45Z","snapshot_observed_at":"2026-07-06T07:32:43.361003Z","submitted_at":"2019-02-12T23:42:45Z","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","version":1},"cited_work":{"arxiv_id":"1902.04674","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.04674","snapshot_observed_at":"2026-07-03T00:47:30.925923Z","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","venue":"cs.LG","work_id":"df274e2f-df93-41f4-a941-e6d765f7f1ea","year":2019},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1902.04674","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:40ea10ec7db244b708509fb654bee69257e4c799711712d425381a5a194ae851","observation_id":"fb16fe27-e7b2-4461-bb61-9f288190f651","resolution":{"observed_at":"2026-05-25T19:46:10.487440Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-07-07T07:23:27.290505Z","title":"Ross Quinlan","venue":null,"work_id":"fa91ce70-ae49-485b-9f5c-d2642fc437ef","year":1986},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:8d4d4b6875124c11fecf5582ae0ccd8333a85ad4f7c20a0427fc14a8d50c30f7","observation_id":"4cd1ceb6-f815-4ce8-8550-bbdb8ab888b6","resolution":{"observed_at":"2026-05-25T19:47:08.355837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Learning decision lists","venue":null,"work_id":"445d4703-a81e-4899-bddc-eb3c4a3f5c63","year":1987},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:1052093ef46c55d862429ba8dc3b8bbb02413c7b02e7d73998ee0773b6fd1de1","observation_id":"c44c4c14-a8cc-472b-b825-3540172b0cb9","resolution":{"observed_at":"2026-05-25T19:47:08.363900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Understanding machine learning: From theory to algorithms","venue":null,"work_id":"5a02992a-1a2d-48bf-8e25-772b23158b0e","year":2014},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:4962d3ae79b94492f5602cce34ad1df0e40757ed5e9a7b694e6dd3f32cdca340","observation_id":"c9e3c00c-bd33-4a73-9ce7-084fed329540","resolution":{"observed_at":"2026-05-25T19:47:08.371854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Failures of gradient-based deep learning","venue":null,"work_id":"8e04e397-04f3-4bb4-bb31-e57a39d3c276","year":2017},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:8f3d907cdb90adf9deb00e07d005e9b5901bf4f4cc5cbd13f067aa910bf07bc3","observation_id":"e517468b-1eae-40ca-b7dd-4d83e9fa88b5","resolution":{"observed_at":"2026-05-25T19:47:08.385699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-05T21:23:00.469572Z","title":"Smoothed analysi s of algorithms: Why the simplex algorithm usually takes polynomial time","venue":null,"work_id":"cc7b6dc9-6317-49bb-8e29-cbdb4ebbe987","year":2004},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:28ca1848afed9b7d88d16199638e0a3f5d263f1b1522f59f2e7b0997d34471e2","observation_id":"85c3ecc2-15b4-4025-af32-b174c8de58c2","resolution":{"observed_at":"2026-05-25T19:47:08.351954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.03131","last_updated":"2017-03-03T04:38:29Z","snapshot_observed_at":"2026-07-06T05:18:04.201552Z","submitted_at":"2016-11-09T23:19:21Z","title":"Diverse Neural Network Learns True Target Functions","version":3},"cited_work":{"arxiv_id":"1611.03131","doi":null,"metadata_source":"pith","pith_arxiv_id":"1611.03131","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Diverse Neural Network Learns True Target Functions","venue":"cs.LG","work_id":"b7513c3e-27ee-40e5-8045-0a87b4d7a98a","year":2016},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1611.03131","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:109ff3c0789243bd44b7ef2219168fb70736f752ee4d9fd073ee6305d73a841d","observation_id":"ac63bc3b-f7d8-42be-9770-ef7b6f2e13d7","resolution":{"observed_at":"2026-05-25T19:46:10.474440Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T08:01:41.630447Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":13,"verified_fuzzy":21},"total_outbound_references":34},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:1906.08654."}