{"as_of":"2026-08-21T03:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bf62b3342e3549ba5dd4ac7743a25a9d2ddd4b467c14d6d12ceb0f7abc28d130","coverage":[{"denominator":204,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:47:10.336941Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2504.14751/citation-record","integrity":"/paper/2504.14751/integrity","json":"/paper/2504.14751/citation-record.json","paper":"/paper/2504.14751"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:09.972637Z","title":"Systematic generalisation with group invariant predictions","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.972637Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:c3bddfa342b73d7eaf505aff3e7686accee0ef6d6a6f063b9c76a0ffb990d24e","observation_id":"8c55c465-1532-49cb-a2b2-9a04e344fa11","resolution":{"observed_at":"2026-08-16T11:47:09.972637Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.16412","last_updated":"2022-08-19T17:20:03Z","snapshot_observed_at":"2026-08-16T19:09:13.862719Z","submitted_at":"2020-10-30T17:55:30Z","title":"Empirical or Invariant Risk Minimization? A Sample Complexity Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.16412","snapshot_observed_at":"2026-08-16T11:47:09.976149Z","title":"Empirical or invariant risk minimization? a sample complexity perspective","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.976149Z"},"links":{"cited_paper":"/paper/2010.16412","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:8541d41248fb4080d12e1b866d20989d920f294bf48c688c53903de15fabcca6","observation_id":"1383e2a0-775a-43d8-b367-e8425ad8fce3","resolution":{"observed_at":"2026-08-16T11:47:09.976149Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12973","last_updated":"2024-01-30T18:59:34Z","snapshot_observed_at":"2026-08-18T18:41:48.541535Z","submitted_at":"2024-01-23T18:59:21Z","title":"In-Context Language Learning: Architectures and Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12973","snapshot_observed_at":"2026-08-16T11:47:09.979859Z","title":"In-context language learning: Arhitectures and algorithms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.979859Z"},"links":{"cited_paper":"/paper/2401.12973","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:372bd929c9012711143852945dd2db8a88abd47926a9b189bdde86774ef388c5","observation_id":"d2af58b7-62bf-4c46-a175-b2cf1ae92b26","resolution":{"observed_at":"2026-08-16T11:47:09.979859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.05337","last_updated":"2023-06-07T09:50:21Z","snapshot_observed_at":"2026-08-17T03:33:18.941499Z","submitted_at":"2022-10-11T11:00:04Z","title":"SGD with Large Step Sizes Learns Sparse Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.05337","snapshot_observed_at":"2026-08-16T11:47:09.983206Z","title":"Sgd with large step sizes learns sparse features","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.983206Z"},"links":{"cited_paper":"/paper/2210.05337","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:3904e48e27acbba974ef1b66ad17491d0e0dafcc00c426cd52e345b2b535cc39","observation_id":"067a2e78-80a2-4059-bd3d-b882536bdec6","resolution":{"observed_at":"2026-08-16T11:47:09.983206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:09.987166Z","title":"Sgd with large step sizes learns sparse features","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.987166Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:332b99ad7b32ca1f7bfdf6cc2d757ee401fcf0492228542852a07be041bf560a","observation_id":"e032eedf-fa87-4ca7-b9a5-e02d7c90bac0","resolution":{"observed_at":"2026-08-16T11:47:09.987166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02893","last_updated":"2020-03-27T19:07:58Z","snapshot_observed_at":"2026-08-16T03:32:37.688772Z","submitted_at":"2019-07-05T15:26:26Z","title":"Invariant Risk Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02893","snapshot_observed_at":"2026-08-16T11:47:09.990737Z","title":"Invariant risk minimization","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.990737Z"},"links":{"cited_paper":"/paper/1907.02893","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:d010db922ac650cb88394ea76fa2de7ed7ce590a153846e60bf8fbd3b7cdce68","observation_id":"7be1d68d-4016-4676-8ddd-93b5a544e236","resolution":{"observed_at":"2026-08-16T11:47:09.990737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:09.995245Z","title":"Invariant risk minimization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.995245Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:15a1f3a8709929e9f07273d094f29c9933a600204c78abd14545b52ff6d1af33","observation_id":"a2fb3ba9-99fa-4d39-bf30-792e77743133","resolution":{"observed_at":"2026-08-16T11:47:09.995245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:09.998740Z","title":"Ensemble of averages: Improving model selection and boosting performance in domain generalization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:09.998740Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:555ee5b94b8f0ed2be5d765dcf459b5e64822af33eb249d1affddb6f00cd4200","observation_id":"397c8b26-94c3-4128-8e92-37063c5fa270","resolution":{"observed_at":"2026-08-16T11:47:09.998740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06470","last_updated":"2021-07-18T16:17:28Z","snapshot_observed_at":"2026-08-13T16:19:22.490042Z","submitted_at":"2020-02-15T23:28:19Z","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06470","snapshot_observed_at":"2026-08-16T11:47:10.002535Z","title":"Pitfalls of in-domain uncertainty estimation and ensembling in deep learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.002535Z"},"links":{"cited_paper":"/paper/2002.06470","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:debfb6a18cfb8c67da776ca690e519e4b0a8525549ee00e49b2481d0344a2f98","observation_id":"25b8ff43-8f56-4c36-9d7d-517d7b149e34","resolution":{"observed_at":"2026-08-16T11:47:10.002535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.006801Z","title":"Locally weighted learning","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.006801Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:35a3fd189a10a9a2d62ed301893ce8b577480783c6696df16486d362a6d38f9b","observation_id":"626759ca-900e-4d1d-bfff-91585fdfb6be","resolution":{"observed_at":"2026-08-16T11:47:10.006801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.010377Z","title":"Multiple kernel learning, conic duality, and the smo algorithm","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.010377Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:cb33a3f355c190e5bec1e6ffb7d0ce812ab7c23c9b6d95f4375dfd06858c1fbf","observation_id":"123e7841-5239-4287-bd5c-5e26c271db79","resolution":{"observed_at":"2026-08-16T11:47:10.010377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.014065Z","title":"Meta-learned invariant risk minimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.014065Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:6719b6c4ec89390fbd528bd163fb8fb9f75bf6937b160d899a1e83f32e07342d","observation_id":"4c13700f-3dce-4983-894a-9768cd8fee0c","resolution":{"observed_at":"2026-08-16T11:47:10.014065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.017655Z","title":"Neural machine translation by jointly learning to align and translate","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.017655Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:d60cb0282fcd3920bbcad71b21071c07c6ecbf58af475892150717210c9d86e6","observation_id":"57d88539-c9d4-4106-a66e-3d8e813d9e4a","resolution":{"observed_at":"2026-08-16T11:47:10.017655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.020980Z","title":"From detection of individual metastases to classification of lymph node status at the patient level: the camelyon17 challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.020980Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:b2a1d268e6f770518021236c6e3b2f333a8a911291a8e437ff8b16bdbf0920e0","observation_id":"7275b6c1-9c08-4cb9-af71-8b706897f50d","resolution":{"observed_at":"2026-08-16T11:47:10.020980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.024996Z","title":"Predict then interpolate: A simple algorithm to learn stable classifiers, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.024996Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:570bd01cecd9cb7688e058a7f0a4f7304b6f0ac8b681b3cc8d53468eac3259f7","observation_id":"45dc0572-0bda-4f31-93b0-9c3c2ca20e77","resolution":{"observed_at":"2026-08-16T11:47:10.024996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.04906","last_updated":"2022-01-28T12:23:37Z","snapshot_observed_at":"2026-08-21T02:04:15.452338Z","submitted_at":"2021-05-11T09:53:21Z","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.04906","snapshot_observed_at":"2026-08-16T11:47:10.028677Z","title":"Vicreg: Variance-invariance-covariance regularization for self-supervised learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.028677Z"},"links":{"cited_paper":"/paper/2105.04906","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:c7ff0732e343ab37f00f16a6acaddab061f9dec4307e55cb0c97a1fb910d5e7a","observation_id":"3c492b19-89c5-4947-8d39-f42c2e0927d8","resolution":{"observed_at":"2026-08-16T11:47:10.028677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.032355Z","title":"o ppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, G \\","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.032355Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:15f79730710af1c4ef4e3f0d2f9611a4a55abdbbf9a75f6d5bc2beab058167de","observation_id":"b67590c3-bf9c-4a39-aaf6-45001ad1a40a","resolution":{"observed_at":"2026-08-16T11:47:10.032355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.035328Z","title":"Recognition in terra incognita","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.035328Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:e12ed11f99ef28f1742a6bfe0580176c634bf0393ac76352d691a268aa212d1a","observation_id":"e1ad00ba-5312-482b-b60a-9e9aabae1aa3","resolution":{"observed_at":"2026-08-16T11:47:10.035328Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05150","last_updated":"2020-12-02T17:52:35Z","snapshot_observed_at":"2026-07-31T17:17:17.205582Z","submitted_at":"2020-04-10T17:54:09Z","title":"Longformer: The Long-Document Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.05150","snapshot_observed_at":"2026-08-16T11:47:10.038452Z","title":"Longformer: The long-document transformer","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.038452Z"},"links":{"cited_paper":"/paper/2004.05150","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:56e7ebb453e412e5e3a3cb6eedad4d2b33ada0e6de98aae7fed7ddd1e4efef90","observation_id":"abc388f9-d5a7-415b-aa55-e722cdd03d5c","resolution":{"observed_at":"2026-08-16T11:47:10.038452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.041894Z","title":"Robust Optimization, volume 28 of Princeton Series in Applied Mathematics","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.041894Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:68cf0da61e01f2ab27e5ffd415f4aa0168ebd724fab1771caf00ab25b614db42","observation_id":"d8885d0c-ce80-4462-a73f-e1813d49c7f5","resolution":{"observed_at":"2026-08-16T11:47:10.041894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.045755Z","title":"Deep learning of representations: Looking forward","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.045755Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:aa886e486ca7214b60a7e73177b3c3cf212ad436ae034503df8bda2a4c5473a6","observation_id":"7035859b-14bb-4da6-9cae-0d47083917f2","resolution":{"observed_at":"2026-08-16T11:47:10.045755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.049309Z","title":"Deep learning of representations: Looking forward","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.049309Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:3b9256a084b51c3dae164d33d226c6966c9a84ce13682a2d469997fab6fedf8a","observation_id":"b200b2b8-3080-4abc-8c12-52e6e52db6ce","resolution":{"observed_at":"2026-08-16T11:47:10.049309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.10912","last_updated":"2019-02-04T19:58:56Z","snapshot_observed_at":"2026-08-14T17:23:35.494755Z","submitted_at":"2019-01-30T15:47:12Z","title":"A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.10912","snapshot_observed_at":"2026-08-16T11:47:10.057358Z","title":"A meta-transfer objective for learning to disentangle causal mechanisms","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.057358Z"},"links":{"cited_paper":"/paper/1901.10912","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:aff9b4348faa2a99f9815e67011bdee8f47dcf5ec24b4c2df8a18a4890a5bef9","observation_id":"a98954da-c9cb-40ef-8f18-134bb5117768","resolution":{"observed_at":"2026-08-16T11:47:10.057358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.061353Z","title":"Backgammon computer program beats world champion","venue":null,"work_id":null,"year":1980},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.061353Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:826080f14216b9a03c6c64e31ee0382b20a5ac86080dceaea3567c972f603b0c","observation_id":"2791e5ba-a554-4668-b36a-04a8b63c2cdf","resolution":{"observed_at":"2026-08-16T11:47:10.061353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.065195Z","title":"Birth of a transformer: A memory viewpoint","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.065195Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:c1614491bf1e85ebe66409f7a2fe28889ad1f3a2e9e43a330d23648211d28bc6","observation_id":"1107660b-711a-41d7-9ed5-5c49d68a34bb","resolution":{"observed_at":"2026-08-16T11:47:10.065195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.068671Z","title":"Implicit regularization for deep neural networks driven by an ornstein-uhlenbeck like process","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.068671Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:2c5635575f722bf11b38eecba7e6faf1ae2ee82b297a589fc88bd72661ca12f0","observation_id":"de84558d-0eb7-40fa-be0c-0ee4e9203522","resolution":{"observed_at":"2026-08-16T11:47:10.068671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-16T11:47:10.072498Z","title":"On the opportunities and risks of foundation models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.072498Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:9c93e5eed6f0e7a3fc1b367067d240ed37cf882d01c6545fc205cd4126c0668e","observation_id":"8594e3ba-ed31-4cfb-b993-d3f94ca38ef8","resolution":{"observed_at":"2026-08-16T11:47:10.072498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1102.1808","last_updated":"2011-02-11T05:10:57Z","snapshot_observed_at":"2026-08-20T19:06:07.330849Z","submitted_at":"2011-02-09T08:25:36Z","title":"From Machine Learning to Machine Reasoning","version":3},"cited_work":{"arxiv_id":"1102.1808","doi":null,"metadata_source":"pith","pith_arxiv_id":"1102.1808","snapshot_observed_at":"2026-08-16T11:47:11.491361Z","title":"From Machine Learning to Machine Reasoning","venue":"cs.AI","work_id":"f0b9f0e9-a106-4fad-b4d8-264fe3f8919d","year":2011},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.076329Z"},"links":{"cited_paper":"/paper/1102.1808","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:79d52a5cd1b5e2e50908e4e16631c8e937d4931e175ccaef645a250db01fe28d","observation_id":"1a9c7d02-6406-4071-859c-72d003a3e2a0","resolution":{"observed_at":"2026-08-16T11:47:11.495705Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.080193Z","title":"Local learning algorithms","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.080193Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:9f0d295db6c18dff4d29c7d6b575a1e8618d4c58931e6ddf9140b5639f684edc","observation_id":"032dc853-2940-43bd-af1b-e025ee763c8c","resolution":{"observed_at":"2026-08-16T11:47:10.080193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.083754Z","title":"Optimization methods for large-scale machine learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.083754Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:9fcd70e5e3fa0f5890a63dcd55fee259f416b270ab762ca7169ab0fc44d45374","observation_id":"e25a60af-e097-4d4e-82a3-67d43de351f3","resolution":{"observed_at":"2026-08-16T11:47:10.083754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.087114Z","title":"AI for open world, https://leon.bottou.org/feuilleton/turing","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.087114Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:1ba7d326b3efdc08f41115acd663eea9e32c4b9336d228b7499a28d2e585f5e5","observation_id":"e38449c0-4cbd-4235-86df-efd031620685","resolution":{"observed_at":"2026-08-16T11:47:10.087114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.090270Z","title":"Approximate matching: Definition and terminology","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.090270Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:c5ac3ac4450cea11ddb025248ff43710b730af6e9d14a19373a2ea9ff120b84d","observation_id":"7ab444fd-6488-4048-be1f-21981b5a16e2","resolution":{"observed_at":"2026-08-16T11:47:10.090270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.093741Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.093741Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:19e66f4946c647db55740547c7105413eb6e209e31a4387a594b17de47de0630","observation_id":"a539606a-4572-4c38-8a32-b9a79e0219f7","resolution":{"observed_at":"2026-08-16T11:47:10.093741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.097200Z","title":"Attribute bagging: improving accuracy of classifier ensembles by using random feature subsets","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.097200Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:d7e539aea6502fcbfaa0972856a9b8549002e839fc96be31496d6e9b54924e81","observation_id":"38d07d4c-f371-4826-a3b5-960bc2ded1d1","resolution":{"observed_at":"2026-08-16T11:47:10.097200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.100651Z","title":"Unsupervised learning of visual features by contrasting cluster assignments","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.100651Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:e532a47fc589600a826e1bdbf2369dd9934bbab1cb088d34f3bbd6a2ce127258","observation_id":"075072f8-8464-4b5e-87ca-d72fd9d5cbb2","resolution":{"observed_at":"2026-08-16T11:47:10.100651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04807","last_updated":"2020-03-10T15:33:54Z","snapshot_observed_at":"2026-08-17T23:59:15.683084Z","submitted_at":"2020-03-10T15:33:54Z","title":"Efficient Intent Detection with Dual Sentence Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04807","snapshot_observed_at":"2026-08-16T11:47:10.104010Z","title":"Efficient intent detection with dual sentence encoders","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.104010Z"},"links":{"cited_paper":"/paper/2003.04807","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:a72c2ebf7a48ae6075cb31b14111138efb1249c270caf83c2bf4f17056985bc9","observation_id":"225f6b67-2e94-44dc-9e1e-a60f997a55d5","resolution":{"observed_at":"2026-08-16T11:47:10.104010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.108134Z","title":"Transformer flops","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.108134Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:fff35b6adc5cf5858c2063dd2d0458e9678e762ca2d34dbbe9769297b71c228a","observation_id":"7a44622a-500d-4c39-85a8-57d4835a5eca","resolution":{"observed_at":"2026-08-16T11:47:10.108134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.111435Z","title":"Swad: Domain generalization by seeking flat minima","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.111435Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:8992509b5e669b290d0265067456ab2de2ab3379a342bf74735e8c756e102b7f","observation_id":"befff649-ef90-465c-a1ba-2b931832a97b","resolution":{"observed_at":"2026-08-16T11:47:10.111435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.15595","last_updated":"2023-06-28T04:26:05Z","snapshot_observed_at":"2026-08-16T11:24:28.964729Z","submitted_at":"2023-06-27T16:26:26Z","title":"Extending Context Window of Large Language Models via Positional Interpolation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.15595","snapshot_observed_at":"2026-08-16T11:47:10.115366Z","title":"Extending context window of large language models via positional interpolation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.115366Z"},"links":{"cited_paper":"/paper/2306.15595","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:e0aaf2966e006dbde76c68d3f6241cb7c476c6c4da1876f95db1e7ba7ba7dd56","observation_id":"3740f502-4b08-4932-9215-7e316fada5b6","resolution":{"observed_at":"2026-08-16T11:47:10.115366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.119199Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.119199Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:0fc01dee9efb2b3c3cdfcae3aef2ac27687fcfdd8b6efde3012be8b4829c04f0","observation_id":"39707124-8afb-49b9-a9c4-6896b59bf5db","resolution":{"observed_at":"2026-08-16T11:47:10.119199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.04232","last_updated":"2020-01-12T16:25:06Z","snapshot_observed_at":"2026-08-17T11:54:32.566184Z","submitted_at":"2019-04-08T17:59:07Z","title":"A Closer Look at Few-shot Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.04232","snapshot_observed_at":"2026-08-16T11:47:10.122782Z","title":"A closer look at few-shot classification","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.122782Z"},"links":{"cited_paper":"/paper/1904.04232","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:915cd3af76eba0a1db0ba83eb23fc34bd00171e403dce4df68a3ab3d00d7d7bc","observation_id":"c1ba12e0-3961-4a2c-8a60-1e7a85078c1c","resolution":{"observed_at":"2026-08-16T11:47:10.122782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.10566","last_updated":"2020-11-20T18:59:33Z","snapshot_observed_at":"2026-08-16T19:04:21.921720Z","submitted_at":"2020-11-20T18:59:33Z","title":"Exploring Simple Siamese Representation Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.10566","snapshot_observed_at":"2026-08-16T11:47:10.126621Z","title":"Exploring simple siamese representation learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.126621Z"},"links":{"cited_paper":"/paper/2011.10566","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:7c44831909c1f5233b2a0971e5ac6ff0ad25b7799915b96b5b4ba750dbe13488","observation_id":"b8527151-0450-4a07-bfc7-7822da607c3e","resolution":{"observed_at":"2026-08-16T11:47:10.126621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11327","last_updated":"2023-10-29T05:20:53Z","snapshot_observed_at":"2026-08-20T21:02:37.872725Z","submitted_at":"2023-04-22T05:57:00Z","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","version":2},"cited_work":{"arxiv_id":"2304.11327","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.11327","snapshot_observed_at":"2026-08-16T11:47:11.425404Z","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","venue":"cs.LG","work_id":"8f938ef2-33a2-4674-afc9-146e01fa6b9f","year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.130469Z"},"links":{"cited_paper":"/paper/2304.11327","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:26a80543db2c6c23b43a7d1eaf303e552f3fdb3f4a0869bbe377ed2b71721f32","observation_id":"2c317b92-15d2-4be2-a83e-1ad75e2a4c2d","resolution":{"observed_at":"2026-08-16T11:47:11.430815Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16179","last_updated":"2024-12-18T17:36:36Z","snapshot_observed_at":"2026-08-16T13:07:19.528168Z","submitted_at":"2024-10-21T16:44:51Z","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.16179","snapshot_observed_at":"2026-08-16T11:47:10.134742Z","title":"Magicpig: Lsh sampling for efficient llm generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.134742Z"},"links":{"cited_paper":"/paper/2410.16179","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:e637fb81e5c8327218fa216de53a387f45c9f4174689932c3bf23bab3c7602ba","observation_id":"e8e3e687-fda5-43c4-95a2-23da63f35733","resolution":{"observed_at":"2026-08-16T11:47:10.134742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.138812Z","title":"Natural language processing (almost) from scratch","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.138812Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:c88e09cbf90a9ce217ef64d1ae3ae5e54c92df3db353c445d66355032788fd28","observation_id":"b262a39b-b257-47c9-b1b0-33b05ed4fab3","resolution":{"observed_at":"2026-08-16T11:47:10.138812Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.142405Z","title":"Independent Component Analysis, a new concept? Signal Processing , 36: 0 287--314, Apr 1994","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.142405Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:63edece426fd07c3afc68e84db73a44cb6f14088471e0e791998cac5c1c5b385","observation_id":"366b42c5-6ec5-4ac5-aa9f-eb6d05508dfc","resolution":{"observed_at":"2026-08-16T11:47:10.142405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.145836Z","title":"Environment inference for invariant learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.145836Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:394f43ef153551e6d16b74686bb0941915c7386ebd5d71954b64e416d4d9c239","observation_id":"13c697f1-2fd3-4527-b5b7-ca8bd598fc72","resolution":{"observed_at":"2026-08-16T11:47:10.145836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00547","last_updated":"2020-06-03T00:31:11Z","snapshot_observed_at":"2026-08-15T08:22:21.965425Z","submitted_at":"2020-05-01T18:00:02Z","title":"GoEmotions: A Dataset of Fine-Grained Emotions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00547","snapshot_observed_at":"2026-08-16T11:47:10.149325Z","title":"Goemotions: A dataset of fine-grained emotions","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.149325Z"},"links":{"cited_paper":"/paper/2005.00547","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:2246bfe069363685ac72bb3e72f34ee2dcc69ac7c82a82e1f94a042d4e343189","observation_id":"643e8f46-10ac-4b52-a0fd-bab1c0e670bc","resolution":{"observed_at":"2026-08-16T11:47:10.149325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.152893Z","title":"Conditional meta-learning of linear representations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.152893Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:5d07d165f2337cdcdadc24b52090e70b3d5539276ba0c12107818fc371efafb0","observation_id":"3faaa57c-f7e3-4a11-a3f5-85fc8537ac67","resolution":{"observed_at":"2026-08-16T11:47:10.152893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.157037Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.157037Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:190f512d436ff648e5fd397636d4217383bdb86b571eaf442e4462f364571dda","observation_id":"7c4e0c1d-e562-474d-a8f4-2bcc4b3868cd","resolution":{"observed_at":"2026-08-16T11:47:10.157037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.160890Z","title":"Ensemble methods in machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.160890Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:4e0f64c86ef1c4c06b42745ee1ad2368048596d60d5cf0ce0ac75b3851e63c78","observation_id":"a0226ec9-6824-4d7a-880c-48ec8e6a1335","resolution":{"observed_at":"2026-08-16T11:47:10.160890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-16T11:47:10.164534Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.164534Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:d8d3d5f617d672a8c4a43e40cb45eb04798c37729b620cb131131af5d3c51dfe","observation_id":"6d6e1a70-b860-45b9-8917-0e6541c600dc","resolution":{"observed_at":"2026-08-16T11:47:10.164534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.07759","last_updated":"2023-05-24T23:30:43Z","snapshot_observed_at":"2026-08-20T14:47:29.320021Z","submitted_at":"2023-05-12T20:56:48Z","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.07759","snapshot_observed_at":"2026-08-16T11:47:10.168226Z","title":"Tinystories: How small can language models be and still speak coherent english? arXiv preprint arXiv:2305.07759, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.168226Z"},"links":{"cited_paper":"/paper/2305.07759","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:ec6adfb5d4b4fd24a19359f0332d3c32849f810ebb2863ba5a65d4bf2b4ea7c8","observation_id":"e6e68082-e432-414a-91da-dfe578a44888","resolution":{"observed_at":"2026-08-16T11:47:10.168226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.172366Z","title":"ELIZA, https://en.wikipedia.org/wiki/ELIZA1972","venue":null,"work_id":null,"year":1972},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.172366Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:d325ef12b5ed6a540d07a34a3633aecd045b1d356188057a6a7d6e325c53ab6b","observation_id":"809eed46-8ca2-466e-becd-487ccaf6a7e5","resolution":{"observed_at":"2026-08-16T11:47:10.172366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.175757Z","title":"Head2toe: Utilizing intermediate representations for better transfer learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.175757Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:f5db61a7076c6cbaf444aa2504cbc7d78306d89448ecf9501a18385fa2ab7902","observation_id":"bc907413-4b7c-417e-a528-46496bb4094c","resolution":{"observed_at":"2026-08-16T11:47:10.175757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.179570Z","title":"Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.179570Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:5cffec1fe687325b85a7dbebbe1587685406ce0557ae15787998290a48f567cc","observation_id":"4a00df02-08f1-4311-a3b0-0f1a21323757","resolution":{"observed_at":"2026-08-16T11:47:10.179570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.183122Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.183122Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:27dccec85aa0064c9415b9ebd9898d133bb81dff3b4e12025884740c8a3623a1","observation_id":"3200431c-1dae-44f3-8f2f-d863732c5103","resolution":{"observed_at":"2026-08-16T11:47:10.183122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.02395","last_updated":"2022-08-08T17:50:53Z","snapshot_observed_at":"2026-08-17T07:28:29.562845Z","submitted_at":"2021-04-06T09:56:29Z","title":"Ensemble deep learning: A review","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.02395","snapshot_observed_at":"2026-08-16T11:47:10.186592Z","title":"Ensemble deep learning: A review","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.186592Z"},"links":{"cited_paper":"/paper/2104.02395","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:20f01d66fa1b5522e95e9c45cd43fc86436a84baacfdfd279325c2ac38ffd897","observation_id":"c376e002-3c7f-4906-95db-229bac9c5523","resolution":{"observed_at":"2026-08-16T11:47:10.186592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.190047Z","title":"Ustinova, Hana Ajakan, Pascal Germain, H","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.190047Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:001170f170ebe03749b648e63c774b128624691f8ef5235916baad2571133b97","observation_id":"0a18fb30-4e3c-41f4-8b3f-69bd74052559","resolution":{"observed_at":"2026-08-16T11:47:10.190047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.193310Z","title":"Garc\\'ia-Portugu\\'es","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.193310Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:39c419be049d49f32f991df808453bc96714f9e475874888e605dc51c8458717","observation_id":"7cda6755-d1d6-46b5-9573-3a70ce501d9e","resolution":{"observed_at":"2026-08-16T11:47:10.193310Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19737","last_updated":"2024-04-30T17:33:57Z","snapshot_observed_at":"2026-08-16T23:36:44.216328Z","submitted_at":"2024-04-30T17:33:57Z","title":"Better & Faster Large Language Models via Multi-token Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19737","snapshot_observed_at":"2026-08-16T11:47:10.196453Z","title":"Better & faster large language models via multi-token prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.196453Z"},"links":{"cited_paper":"/paper/2404.19737","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:1fc46aa5be32f2af0fdd570c9f506bbc442abe5e433d3bcb3aeda9f8ff49a9f1","observation_id":"07e9ec92-1b70-4194-9638-d4971c115d33","resolution":{"observed_at":"2026-08-16T11:47:10.196453Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.199833Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.199833Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:cddf6678e7532b7ff1fb798131c4db1ac19f4f9f5225a60656629190b7acadae","observation_id":"30b97307-38ca-465a-a83c-3a0a4a7eadf4","resolution":{"observed_at":"2026-08-16T11:47:10.199833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.203248Z","title":"No one representation to rule them all: Overlapping features of training methods","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.203248Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:5177c542832b8f24460c76bef25441bc20bd7eb4fa4eac19de6c61876aff3205","observation_id":"dc23e2ef-8a31-49e0-9dae-528fd97ec5f2","resolution":{"observed_at":"2026-08-16T11:47:10.203248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02677","last_updated":"2018-04-30T21:53:41Z","snapshot_observed_at":"2026-08-09T05:23:26.365677Z","submitted_at":"2017-06-08T16:51:53Z","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02677","snapshot_observed_at":"2026-08-16T11:47:10.206479Z","title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.206479Z"},"links":{"cited_paper":"/paper/1706.02677","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:64fb8c71a14a03c724a064a0b0f489d979cd76ce945d308ca8249a58fb0c0971","observation_id":"58a17c7a-24d2-45b2-a959-ee55bc0a5001","resolution":{"observed_at":"2026-08-16T11:47:10.206479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08360","last_updated":"2022-02-22T18:15:21Z","snapshot_observed_at":"2026-08-16T17:20:43.611977Z","submitted_at":"2022-02-16T22:26:47Z","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08360","snapshot_observed_at":"2026-08-16T11:47:10.210290Z","title":"Vision models are more robust and fair when pretrained on uncurated images without supervision","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.210290Z"},"links":{"cited_paper":"/paper/2202.08360","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:6fc471f171a94f35206dbb81ffaa27fdf786023906c78af18e2b4a9a56adc47f","observation_id":"a98e7582-f17e-47db-b17f-af0c711433ec","resolution":{"observed_at":"2026-08-16T11:47:10.210290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.213908Z","title":"The fast Gauss transform","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.213908Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:be75ccf6041fbbc93b24acb3dabbd571c49d0b2e932e611f0157c889f3d552b4","observation_id":"5913aa5d-c967-43f9-ad65-12958d9dae98","resolution":{"observed_at":"2026-08-16T11:47:10.213908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-08-17T20:47:46.242385Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-16T11:47:10.221392Z","title":"Mamba: Linear-time sequence modeling with selective state spaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.221392Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:9ee4ef026cc05c7b5e11ae9b2bf7fa4c626f1fab9493a4b8aef12c56d8632c1e","observation_id":"3d998dcc-fe3a-4ef2-9a24-18a4c452a46e","resolution":{"observed_at":"2026-08-16T11:47:10.221392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.01434","last_updated":"2020-07-02T23:08:07Z","snapshot_observed_at":"2026-08-20T08:37:09.156079Z","submitted_at":"2020-07-02T23:08:07Z","title":"In Search of Lost Domain Generalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.01434","snapshot_observed_at":"2026-08-16T11:47:10.224852Z","title":"In search of lost domain generalization","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.224852Z"},"links":{"cited_paper":"/paper/2007.01434","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:6fec4ae0b2bd2e1c97bf0cb84f1e544d4d780f3fd769e1c6d681efefdaedae8b","observation_id":"e2002943-8c81-4551-9934-a0391a441905","resolution":{"observed_at":"2026-08-16T11:47:10.224852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.228689Z","title":"In search of lost domain generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.228689Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:1e2302e6b51e221213ef2c41586c420a6e3f7c061e36b9ecf35c791926220579","observation_id":"103e4dac-496d-4f10-86bf-baebb097ac5e","resolution":{"observed_at":"2026-08-16T11:47:10.228689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-16T11:47:10.232218Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.232218Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:b755546f602920dc08caa513be781db8707749067a65d45e7c2c41ab7504e9ab","observation_id":"20886e17-b886-4e5b-a636-95e0f190a31b","resolution":{"observed_at":"2026-08-16T11:47:10.232218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19470","last_updated":"2024-11-11T02:27:54Z","snapshot_observed_at":"2026-08-19T06:50:57.472059Z","submitted_at":"2024-06-27T18:21:32Z","title":"Changing Answer Order Can Decrease MMLU Accuracy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.19470","snapshot_observed_at":"2026-08-16T11:47:10.236247Z","title":"Changing Answer Order Can Decrease MMLU Accuracy , June 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.236247Z"},"links":{"cited_paper":"/paper/2406.19470","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:5eaea6c3b00e6636711f388a19e1f1ed49944dab12c767d68686ea9a2d8fc413","observation_id":"47fa2e3d-bb28-4f45-9bf6-ea4d6accbee8","resolution":{"observed_at":"2026-08-16T11:47:10.236247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.240295Z","title":"Structural risk minimization for character recognition","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.240295Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:820b4dc9a41b903317ff8cce711e603092e2afdf851c79e33feb7c59e0febb18","observation_id":"63f07ac3-39f7-4c8d-b71b-ea55cb08d4f8","resolution":{"observed_at":"2026-08-16T11:47:10.240295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.243782Z","title":"Mathematical Structures of Language","venue":null,"work_id":null,"year":1968},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.243782Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:0688f50fa2da6064cf285c1b977a6e99a252a081dcf2ab3a2fa586703b57a8d4","observation_id":"447eebc0-a65e-42f5-998e-532389be6ba8","resolution":{"observed_at":"2026-08-16T11:47:10.243782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.247499Z","title":"The elements of statistical learning, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.247499Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:38ef65e64a090d4a0aef04e56676b8a4e6dc8bce69d74990c52dcaaaacbbf350","observation_id":"a07b8725-6ca6-4bfa-9902-ecbbbb08945b","resolution":{"observed_at":"2026-08-16T11:47:10.247499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.251157Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.251157Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:c35379385112147c59c4005e30d220e97ce9692d69d0caae3ebbb0e6d4fb8ce5","observation_id":"0d41842d-74c4-4770-835c-9c1c2797860e","resolution":{"observed_at":"2026-08-16T11:47:10.251157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.254665Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.254665Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:c398ee0a701ada09079b4eb0dd7951e915054716bc4c61bb90c7450229a65545","observation_id":"8225b85d-b494-4120-8eee-178b7d7ac294","resolution":{"observed_at":"2026-08-16T11:47:10.254665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.258671Z","title":"Multicalibration: Calibration for the ( C omputationally-identifiable) masses","venue":null,"work_id":null,"year":1939},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.258671Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:f7b8394609123561541bf4c29a5d053e9d30e15e9041a07b04b20ce6451a32a1","observation_id":"87f8334a-9f5e-47a7-a05b-7e356b2c9349","resolution":{"observed_at":"2026-08-16T11:47:10.258671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.02230","last_updated":"2018-12-05T21:21:09Z","snapshot_observed_at":"2026-08-15T03:54:20.493152Z","submitted_at":"2018-12-05T21:21:09Z","title":"Towards a Definition of Disentangled Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.02230","snapshot_observed_at":"2026-08-16T11:47:10.262227Z","title":"Towards a definition of disentangled representations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.262227Z"},"links":{"cited_paper":"/paper/1812.02230","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:1a269588d5e4fccdf7a7e6675889794dda38ede7d5ac7c53d5972c1129c0bad5","observation_id":"9d2eb625-cbe0-4e48-8873-6e3703a0d89b","resolution":{"observed_at":"2026-08-16T11:47:10.262227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-16T11:47:10.265992Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.265992Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:511678f6cb3eaaaf567161ebd09c2cb6e852e7d2f200211f9e5943e0ab86091c","observation_id":"ab146f31-3009-4376-80af-fb80954a354a","resolution":{"observed_at":"2026-08-16T11:47:10.265992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06654","last_updated":"2024-08-06T21:48:58Z","snapshot_observed_at":"2026-08-18T14:33:16.365411Z","submitted_at":"2024-04-09T23:41:27Z","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06654","snapshot_observed_at":"2026-08-16T11:47:10.269703Z","title":"Ruler: What's the real context size of your long-context language models? arXiv preprint arXiv:2404.06654, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.269703Z"},"links":{"cited_paper":"/paper/2404.06654","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:68c4e70b664d243628e3c45e5a540b13e93639ac13a15bf795e07ee64577d2e0","observation_id":"a801923a-f773-43f3-8935-52c50d52c2be","resolution":{"observed_at":"2026-08-16T11:47:10.269703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.273303Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.273303Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:4ed9a152913f4b8d16dcd3adfafae77b3fe588a640e01eea8d690627f5952d32","observation_id":"0751997f-a2b3-4c4d-9340-c89cd3e4c20d","resolution":{"observed_at":"2026-08-16T11:47:10.273303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.276703Z","title":"Xing, and Dong Huang","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.276703Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:51b24241e5cad53c0f3bf5bf54921fd60aa052cad4530100de2f14d362dfbd7b","observation_id":"d885973c-be2a-4649-9ef2-24bc3af40f05","resolution":{"observed_at":"2026-08-16T11:47:10.276703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.280195Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.280195Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:d7d579daf60d9e8f2eb2ebaf49f98e9a3b71da8f8472f381d9d15aa273dcaeab","observation_id":"7fa5452e-3988-4b00-84b0-d8456a5462b6","resolution":{"observed_at":"2026-08-16T11:47:10.280195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.283520Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.283520Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:9c475eedbe37f465d244e1f772a6fc0c2ad9a5e394bb9b31aaae6eaeaaa9518b","observation_id":"b2d81e43-512d-45a5-b11d-1e371e6300bb","resolution":{"observed_at":"2026-08-16T11:47:10.283520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.287193Z","title":"Adaptive mixtures of local experts","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.287193Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:fb91787a0d5a57955cb95e54bf2aed1096fcca99820cc6ff61c8fbbee61013df","observation_id":"c6dadebe-4484-4df3-89ab-50833c3041fe","resolution":{"observed_at":"2026-08-16T11:47:10.287193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.290821Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.290821Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:7b705391e34e774c22c64b9b99f6fc6b97e61bb60821be9279740398d32734db","observation_id":"9573743f-022a-48ac-9039-ea8ae31160c5","resolution":{"observed_at":"2026-08-16T11:47:10.290821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.294303Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.294303Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:9e72f78c77cb319b44d5b6caa125d189433d46e33d1c037e19c6a529f9763fe0","observation_id":"aad48532-4933-488a-9132-b30a55577391","resolution":{"observed_at":"2026-08-16T11:47:10.294303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.09348","last_updated":"2022-04-23T16:44:20Z","snapshot_observed_at":"2026-08-16T17:48:26.312603Z","submitted_at":"2021-10-18T14:22:19Z","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.09348","snapshot_observed_at":"2026-08-16T11:47:10.298183Z","title":"Understanding dimensional collapse in contrastive self-supervised learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.298183Z"},"links":{"cited_paper":"/paper/2110.09348","citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:6e1f161602256d0a77fdc7ca8b4c1502e144e80c8d8ece64a5c76acfa486c232","observation_id":"a273bb12-0a58-4974-9ad2-4b82cc53c137","resolution":{"observed_at":"2026-08-16T11:47:10.298183Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.301417Z","title":"Inferring algorithmic patterns with stack-augmented recurrent nets","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.301417Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:26048ddd82c740280dc89c3cced1ca461adcb127b59c7a68b32b209ca97f13e4","observation_id":"82e2f1e8-5ddc-480a-8388-777b942ea4b9","resolution":{"observed_at":"2026-08-16T11:47:10.301417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.305242Z","title":"Sutherland, and Nathan Srebro","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.305242Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:99ac99ebb65e32b6fda6d0f47a69c5593f4342028849f4f5366e9edf73ba81aa","observation_id":"a571bb6f-3bf0-4ef9-8887-852fe457120b","resolution":{"observed_at":"2026-08-16T11:47:10.305242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.309380Z","title":"How to use dropout correctly on residual networks with batch normalization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.309380Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:ce4db8ac4f28a25dbf6a54a5bda7f115d5aada020842696c28d455bb9eb3788c","observation_id":"83873cf8-bca0-4589-93b2-44f978544569","resolution":{"observed_at":"2026-08-16T11:47:10.309380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.312419Z","title":"Last layer re-training is sufficient for robustness to spurious correlations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.312419Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:66c9641bad6a72a74b45239790636cb64d8fe98fd8ab2effefdfa6ae15bc8739","observation_id":"b34ed0c3-0e6e-4c8f-b3c5-e0e38129e81e","resolution":{"observed_at":"2026-08-16T11:47:10.312419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.315678Z","title":"Overcoming catastrophic forgetting in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.315678Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:583c2b3c8e8f0aa5e363e4d090bb39b7983ce71bcaab6985c71d2e0fee7a3b98","observation_id":"7b24abc9-204d-4d9b-ae60-72fa33328c2e","resolution":{"observed_at":"2026-08-16T11:47:10.315678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.318916Z","title":"Earnshaw, Imran S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.318916Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:74f01924fe79d27485af8e477f0a596722318f14760cc21236961021a2c51da2","observation_id":"439143fa-3940-4295-a9ab-433ca02dde01","resolution":{"observed_at":"2026-08-16T11:47:10.318916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.322009Z","title":"Wilds: A benchmark of in-the-wild distribution shifts","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.322009Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:a39cba443583ef78267659078017336b15207aa09d20f3f7d1cd777587a853b5","observation_id":"41730dbe-f6f9-46d4-8fa3-fa2e0318690e","resolution":{"observed_at":"2026-08-16T11:47:10.322009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.324953Z","title":"Out-of-distribution generalization with maximal invariant predictor","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.324953Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:264864b5916ecc3921240c69e34deac518e4da86e83ea53e5a9ba6f2d78a8623","observation_id":"4b5c0db6-81f3-485c-940c-62093eb7dcf4","resolution":{"observed_at":"2026-08-16T11:47:10.324953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.328113Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.328113Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:2834cddaceeba8e58bda0e98bc2d678d4f0fa74f484e44524fb47906986fdcda","observation_id":"7708360c-3d0d-45b2-b984-eb210b88e523","resolution":{"observed_at":"2026-08-16T11:47:10.328113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.331089Z","title":"A new frontier for hopfield networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.331089Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:52d01d43ecce46bdfeb6f9de92dfd23b3a57097053ad14575519c77be4597448","observation_id":"29ab079d-8f9b-4c59-9e44-03269893ae6b","resolution":{"observed_at":"2026-08-16T11:47:10.331089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.333998Z","title":"Out-of-distribution generalization via risk extrapolation (rex)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":101,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.333998Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:33d470b42ff3f579ffbc5adcec066d7e45e233784d03a412b2618270d880e4b1","observation_id":"c351138c-9f21-4e97-9ecc-b7b70543da77","resolution":{"observed_at":"2026-08-16T11:47:10.333998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:47:10.336941Z","title":"Out-of-distribution generalization via risk extrapolation (rex)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles","version":2},"reference_index":102,"source":"arxiv_source","source_observed_at":"2026-08-16T11:47:10.336941Z"},"links":{"citing_paper":"/paper/2504.14751"},"observation_digest":"sha256:a9159c938891a17d1575f18f60e8319695ee4ea817a548dc3b54dad5a1990a03","observation_id":"af4b32d2-7443-4783-951f-4a7dc803df3b","resolution":{"observed_at":"2026-08-16T11:47:10.336941Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.14751","last_updated":"2025-07-07T02:26:30Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T05:32:53.458076Z","submitted_at":"2025-04-20T22:22:00Z","title":"AI for the Open-World: the Learning Principles"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":98,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":204},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 100 of 204 outbound references and 0 inbound Pith citation observations for arXiv:2504.14751."}