{"as_of":"2026-08-08T21:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:64d50eeb573490dff3d17e69535e8b0fa3bacc69540d66b44c13aff400274cd4","coverage":[{"denominator":79,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":79,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T01:03:53.455714Z","state":"measured"},{"denominator":79,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":79,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.12226/citation-record","integrity":"/paper/2506.12226/integrity","json":"/paper/2506.12226/citation-record.json","paper":"/paper/2506.12226"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.10867","last_updated":"2021-02-22T10:07:51Z","snapshot_observed_at":"2026-08-05T09:02:46.752099Z","submitted_at":"2021-02-22T10:07:51Z","title":"Linear unit-tests for invariance discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.10867","snapshot_observed_at":"2026-08-07T01:03:46.832614Z","title":"Linear unit-tests for invariance discovery.arXiv preprint arXiv:2102.10867,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:46.832614Z"},"links":{"cited_paper":"/paper/2102.10867","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:c769d227224a84e8d961a3668f7316531f7d8cf201be5dac3b5fdcb5eedf0c76","observation_id":"e96e318e-dfd0-44cb-a48d-5eb663686d09","resolution":{"observed_at":"2026-08-07T01:03:46.832614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-07T01:03:46.902604Z","title":"J., Kiros, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:46.902604Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:0b2e8b8a293f107bf59412cd09c26bdae91015badd8a94c3f01f8afcd858ebfa","observation_id":"80d84918-c1fc-4bac-9837-4a9228305473","resolution":{"observed_at":"2026-08-07T01:03:46.902604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.10653","last_updated":"2022-02-03T15:26:42Z","snapshot_observed_at":"2026-07-06T09:40:31.292082Z","submitted_at":"2020-07-21T08:18:06Z","title":"Accounting for Unobserved Confounding in Domain Generalization","version":6},"cited_work":{"arxiv_id":"2007.10653","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.10653","snapshot_observed_at":"2026-08-07T01:03:59.862973Z","title":"Accounting for Unobserved Confounding in Domain Generalization","venue":"stat.ML","work_id":"e3bce090-0754-4225-9c04-29cea84f35d7","year":2020},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.139393Z"},"links":{"cited_paper":"/paper/2007.10653","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:1a384e5d5f22fc034299423d3305593b291bfb1ec8c4a2d3674ae2a589d3178b","observation_id":"9eeb4047-847b-4fcb-9428-b1d2ab5a22b3","resolution":{"observed_at":"2026-08-07T01:03:59.940035Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12712","last_updated":"2023-04-13T20:41:31Z","snapshot_observed_at":"2026-08-03T04:49:15.195814Z","submitted_at":"2023-03-22T16:51:28Z","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.12712","snapshot_observed_at":"2026-08-07T01:03:47.340464Z","title":"T., Li, Y., Lundberg, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.340464Z"},"links":{"cited_paper":"/paper/2303.12712","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:e7264af8e6df0ebb453a7cad75db6bb655183653566a3c0efdf50d7e1511f851","observation_id":"9bddc9aa-ab94-4739-be3a-49453897db03","resolution":{"observed_at":"2026-08-07T01:03:47.340464Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:01.654434Z","title":"Estimating generalization under distribution shifts via domain-invariant representations","venue":null,"work_id":"d503102f-3970-4fdd-a3bc-0bac194a6ebf","year":1984},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.686939Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:bb09ebe1dcc7d6584034d469a350b7b9a2fa624ed6e0fcc037175df3d0650071","observation_id":"c49056e7-6915-4bd4-a044-1884a09e3a6d","resolution":{"observed_at":"2026-08-07T01:04:01.739300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04949","last_updated":"2023-10-29T03:03:32Z","snapshot_observed_at":"2026-07-06T15:40:04.846330Z","submitted_at":"2023-06-08T05:44:06Z","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04949","snapshot_observed_at":"2026-08-07T01:03:47.920840Z","title":"Robust learning with progressive data expansion against spurious correlation.arXiv preprint, arXiv:2306.04949,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.920840Z"},"links":{"cited_paper":"/paper/2306.04949","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:6d8f5cfcd0ca32575b482ed70250a38a9ac53be6d78112d975c2926642ffb052","observation_id":"b65a68f7-f281-48e2-8fe6-a99058788185","resolution":{"observed_at":"2026-08-07T01:03:47.920840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.13982","last_updated":"2022-08-10T18:58:19Z","snapshot_observed_at":"2026-08-08T18:23:36.569943Z","submitted_at":"2020-07-28T04:16:27Z","title":"Distributionally Robust Losses for Latent Covariate Mixtures","version":2},"cited_work":{"arxiv_id":"2007.13982","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.13982","snapshot_observed_at":"2026-08-07T01:03:59.599274Z","title":"Distributionally Robust Losses for Latent Covariate Mixtures","venue":"cs.LG","work_id":"9355e89b-d769-43dd-8dc0-cebd633bf919","year":2020},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.060897Z"},"links":{"cited_paper":"/paper/2007.13982","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:d8631af3749f049db92b31cee87f373443014046f4c9f509e8c580e8dcf17928","observation_id":"06238774-ea0c-42b1-a1cb-0ba46abb2e15","resolution":{"observed_at":"2026-08-07T01:03:59.637885Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00982","last_updated":"2022-12-28T04:57:24Z","snapshot_observed_at":"2026-08-07T16:00:11.035143Z","submitted_at":"2020-03-02T15:58:46Z","title":"Benchmarking Graph Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.00982","snapshot_observed_at":"2026-08-07T01:03:48.165338Z","title":"P ., Joshi, C","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.165338Z"},"links":{"cited_paper":"/paper/2003.00982","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:5a728503cc683242dab19afdbc327423f3b2afac5c0edbd8fd9510dde6ca536d","observation_id":"1dcb9df6-1ee0-416c-a7b3-4014997c411e","resolution":{"observed_at":"2026-08-07T01:03:48.165338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.10652","last_updated":"2022-09-21T20:49:26Z","snapshot_observed_at":"2026-07-06T13:54:56.779166Z","submitted_at":"2022-09-21T20:49:26Z","title":"Toy Models of Superposition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.10652","snapshot_observed_at":"2026-08-07T01:03:48.254653Z","title":"Toy models of superposition.arXiv preprint arXiv:2209.10652,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.254653Z"},"links":{"cited_paper":"/paper/2209.10652","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:7ef679cec3883f8686f006565fb1af97c938734b7142d19ac4206bcfcd3ac0b9","observation_id":"fbe903a6-0550-4ae3-9d97-eaed212941ad","resolution":{"observed_at":"2026-08-07T01:03:48.254653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.01313","last_updated":"2025-01-14T01:28:03Z","snapshot_observed_at":"2026-07-06T14:47:48.494911Z","submitted_at":"2023-02-02T18:39:30Z","title":"Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.01313","snapshot_observed_at":"2026-08-07T01:03:48.348331Z","title":"Double equivariance for inductive link prediction for both new nodes and new relation types.arXiv preprint, arXiv:2302.01313,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.348331Z"},"links":{"cited_paper":"/paper/2302.01313","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:6f668ec79ab8b9484b3dc6c2292d93215322a137207d828e414f38926fd85845","observation_id":"b0153e60-1f3c-4c60-9529-4deca9bf8eb8","resolution":{"observed_at":"2026-08-07T01:03:48.348331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.07640","last_updated":"2018-05-31T17:56:14Z","snapshot_observed_at":"2026-07-06T06:29:20.394058Z","submitted_at":"2018-03-20T20:32:07Z","title":"AllenNLP: A Deep Semantic Natural Language Processing Platform","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.07640","snapshot_observed_at":"2026-08-07T01:03:48.453496Z","title":"F., Peters, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.453496Z"},"links":{"cited_paper":"/paper/1803.07640","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:56d90e6932ac9fe4d4bb17043b0fbaa82d75e0631347b30e845353a54f6f7bcc","observation_id":"11dc3e8c-9d7d-4c97-a351-f4b42945b4fd","resolution":{"observed_at":"2026-08-07T01:03:48.453496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.01103","last_updated":"2023-10-31T18:40:49Z","snapshot_observed_at":"2026-07-06T15:36:52.977284Z","submitted_at":"2023-06-01T19:33:30Z","title":"Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization","version":3},"cited_work":{"arxiv_id":"2306.01103","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.01103","snapshot_observed_at":"2026-08-07T01:03:59.396821Z","title":"Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization","venue":"cs.LG","work_id":"57f40750-13ff-4198-b0e6-176a129a767e","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.567748Z"},"links":{"cited_paper":"/paper/2306.01103","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:4e27502ae90224b459a9f1791a507920fc37975fc71636b9d07b59eda23ce32e","observation_id":"62d00e3a-652f-43d0-831c-584f9d537328","resolution":{"observed_at":"2026-08-07T01:03:59.466653Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.01391","last_updated":"2024-07-23T06:43:57Z","snapshot_observed_at":"2026-08-06T12:45:32.736837Z","submitted_at":"2023-04-03T21:42:42Z","title":"Counterfactual Learning on Graphs: A Survey","version":3},"cited_work":{"arxiv_id":"2304.01391","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.01391","snapshot_observed_at":"2026-08-07T01:03:59.264007Z","title":"Counterfactual Learning on Graphs: A Survey","venue":"cs.LG","work_id":"abf78dbc-4bc7-4bca-93d6-fab6a2df8dc5","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.648664Z"},"links":{"cited_paper":"/paper/2304.01391","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:4f4aa1f991774cb7382d3e365d2182726925bfd28c293695a4cc12051ec5ea6c","observation_id":"213a0488-c6ff-44bc-9e8e-e143307f917f","resolution":{"observed_at":"2026-08-07T01:03:59.324741Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.04406","last_updated":"2021-02-20T07:28:12Z","snapshot_observed_at":"2026-07-06T10:12:54.188337Z","submitted_at":"2020-11-09T13:16:02Z","title":"A Survey of Label-noise Representation Learning: Past, Present and Future","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.04406","snapshot_observed_at":"2026-08-07T01:03:48.747120Z","title":"SIGUA: Forgetting may make learning with noisy labels more robust","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.747120Z"},"links":{"cited_paper":"/paper/2011.04406","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:4aeb93ccbb858f4ffa0335a76262cdc2d4e1ab69789ebcae5d1e2bf318cf4980","observation_id":"3149f253-0478-41a0-bf42-a16697179114","resolution":{"observed_at":"2026-08-07T01:03:48.747120Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:01.302770Z","title":"Does distributionally robust supervised learning give robust classifiers? InInternational Conference on Machine Learning, pp","venue":null,"work_id":"14834e16-ed7a-44df-9600-1ff2f240a323","year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.846095Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:23072ad546a2dadc613ead37729bacaf3c41f13743293e7e33b607a3508a2d28","observation_id":"b7ba944d-4da9-4d76-85d6-8be89b4c90fc","resolution":{"observed_at":"2026-08-07T01:04:01.406903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.13926","last_updated":"2025-06-06T15:58:22Z","snapshot_observed_at":"2026-07-06T15:46:13.880066Z","submitted_at":"2023-06-24T10:21:11Z","title":"Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons","version":3},"cited_work":{"arxiv_id":"2306.13926","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.13926","snapshot_observed_at":"2026-08-07T01:03:59.108631Z","title":"Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons","venue":"cs.LG","work_id":"197dc8d0-e140-4a39-b06d-a21a604bad4f","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.931563Z"},"links":{"cited_paper":"/paper/2306.13926","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:2c785c9b81417782fa3efeea62bef26fe3365bf1d454f28b5eab27695b86dd18","observation_id":"8cdcd182-f1fe-48ef-a022-94c93d52ef6d","resolution":{"observed_at":"2026-08-07T01:03:59.190733Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:01.133381Z","title":"and Wallace, B","venue":null,"work_id":"bef2f808-918d-4025-99d4-33be1e31e0b4","year":2019},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.019481Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:17a4afcdc848f10d4e006ff89092aedf281d244f285b45b6184bad9ff385788f","observation_id":"0c9c0bad-7b22-4459-9c39-33d9b4003c75","resolution":{"observed_at":"2026-08-07T01:04:01.230145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.09637","last_updated":"2022-01-24T12:32:48Z","snapshot_observed_at":"2026-07-06T12:30:38.345126Z","submitted_at":"2022-01-24T12:32:48Z","title":"DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.09637","snapshot_observed_at":"2026-08-07T01:03:49.097262Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.097262Z"},"links":{"cited_paper":"/paper/2201.09637","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:9f48c79e030fe896a2b26569bf40e6303a4c0165b02860ce26f5ec0d98a22aab","observation_id":"8b0b2a5a-7e87-493f-8d1f-fce515f76282","resolution":{"observed_at":"2026-08-07T01:03:49.097262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03561","last_updated":"2023-02-26T06:03:39Z","snapshot_observed_at":"2026-07-06T14:01:55.812123Z","submitted_at":"2022-10-07T13:51:59Z","title":"Empowering Graph Representation Learning with Test-Time Graph Transformation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03561","snapshot_observed_at":"2026-08-07T01:03:49.169290Z","title":"Empowering graph representation learning with test-time graph transformation.arXiv preprint, arXiv:2210.03561,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.169290Z"},"links":{"cited_paper":"/paper/2210.03561","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:23674e9a09af33e671754ae3d047a601125654eaffad521ca98702bcf0ed7f89","observation_id":"39e1288a-bce6-4d6f-9cdd-1307c3caea8e","resolution":{"observed_at":"2026-08-07T01:03:49.169290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.12514","last_updated":"2024-11-28T02:55:56Z","snapshot_observed_at":"2026-07-06T10:07:57.849143Z","submitted_at":"2020-10-23T16:32:28Z","title":"No Free Lunch for Approximate MCMC","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.12514","snapshot_observed_at":"2026-08-07T01:03:49.255250Z","title":"E., Pillai, N","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.255250Z"},"links":{"cited_paper":"/paper/2010.12514","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:88561729b00f082deb485edb78247e3ed09512f531a3be4542b337a7595029ec","observation_id":"e1f2cea6-404c-4e3c-ba6e-6cabddc3f100","resolution":{"observed_at":"2026-08-07T01:03:49.255250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07308","last_updated":"2016-11-21T11:37:17Z","snapshot_observed_at":"2026-08-06T06:17:37.090691Z","submitted_at":"2016-11-21T11:37:17Z","title":"Variational Graph Auto-Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07308","snapshot_observed_at":"2026-08-07T01:03:49.360192Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.360192Z"},"links":{"cited_paper":"/paper/1611.07308","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:5fc010a43c050aecbb6e0903799f087cb692d2360aa86a7e70abe4d52c995229","observation_id":"a19420aa-2313-4247-888a-4ba57f68cce1","resolution":{"observed_at":"2026-08-07T01:03:49.360192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02937","last_updated":"2023-06-30T22:51:42Z","snapshot_observed_at":"2026-07-06T12:57:32.819460Z","submitted_at":"2022-04-06T16:55:41Z","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02937","snapshot_observed_at":"2026-08-07T01:03:49.459304Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.459304Z"},"links":{"cited_paper":"/paper/2204.02937","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:3abd3ecf9d037b4ad52f7a766d245a0e36613066ca8b50a4dec01767cd27d37b","observation_id":"23084aa8-cc08-4ac3-870c-40ca2241d5f6","resolution":{"observed_at":"2026-08-07T01:03:49.459304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06390","last_updated":"2021-10-12T22:56:16Z","snapshot_observed_at":"2026-07-06T11:57:13.694881Z","submitted_at":"2021-10-12T22:56:16Z","title":"Learning ground states of quantum Hamiltonians with graph networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06390","snapshot_observed_at":"2026-08-07T01:03:49.549537Z","title":"W., and Clark, B","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.549537Z"},"links":{"cited_paper":"/paper/2110.06390","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:748cab00d63d00a529e9577ae48e8b476b06111ce82840cbec2891baa217af71","observation_id":"f611837d-fc14-4fc0-803d-0c3f6cda3891","resolution":{"observed_at":"2026-08-07T01:03:49.549537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.09891","last_updated":"2022-03-29T07:06:47Z","snapshot_observed_at":"2026-07-06T10:05:59.736442Z","submitted_at":"2020-10-19T21:51:47Z","title":"Robust Optimization as Data Augmentation for Large-scale Graphs","version":3},"cited_work":{"arxiv_id":"2010.09891","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.09891","snapshot_observed_at":"2026-08-07T01:03:58.850729Z","title":"Robust Optimization as Data Augmentation for Large-scale Graphs","venue":"cs.LG","work_id":"1ba1bb2a-3eef-48a9-b095-a4263553fdaf","year":2020},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.673048Z"},"links":{"cited_paper":"/paper/2010.09891","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:3f72d6c7b78ca085a6c7d7a65f3f2f4ca2ec6da9042eb0b1218158b1ac0ef99a","observation_id":"87faa61f-fcad-477d-8de7-37411e14ec3f","resolution":{"observed_at":"2026-08-07T01:03:58.969026Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.01883","last_updated":"2021-11-25T08:04:44Z","snapshot_observed_at":"2026-07-06T09:44:39.047831Z","submitted_at":"2020-08-04T23:57:11Z","title":"When is invariance useful in an Out-of-Distribution Generalization problem ?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.01883","snapshot_observed_at":"2026-08-07T01:03:49.770778Z","title":"and Yamaguchi, S","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.770778Z"},"links":{"cited_paper":"/paper/2008.01883","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:359e89c9b1b7ce2c4d86e0301d4ca6cf8a354fcda08d18c350917e06d216301b","observation_id":"a1cdd133-e67a-490a-ba55-29bc7c516a08","resolution":{"observed_at":"2026-08-07T01:03:49.770778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08076","last_updated":"2024-06-05T01:41:31Z","snapshot_observed_at":"2026-07-06T15:42:14.659345Z","submitted_at":"2023-06-13T18:46:28Z","title":"Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization","version":2},"cited_work":{"arxiv_id":"2306.08076","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.08076","snapshot_observed_at":"2026-08-07T01:03:58.188418Z","title":"Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization","venue":"cs.LG","work_id":"9715604d-40a1-4ae3-b6d1-da6b16c216ea","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.956461Z"},"links":{"cited_paper":"/paper/2306.08076","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:8c47cec24264a5f5a301d06b31d3956d2d431c2dd65423cab881b1ce0b3506b4","observation_id":"de922963-b48a-4a88-9ce7-855c490607ad","resolution":{"observed_at":"2026-08-07T01:03:58.336631Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17230","last_updated":"2024-07-14T08:02:49Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T13:29:22Z","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","version":2},"cited_work":{"arxiv_id":"2309.17230","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.17230","snapshot_observed_at":"2026-08-07T01:03:57.922805Z","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","venue":"cs.LG","work_id":"cdfce60b-7bb7-4435-a0b1-d89a95f25cfa","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.050508Z"},"links":{"cited_paper":"/paper/2309.17230","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:44a571d40d4bdad977181ba997b532b0da2b2a42727ce20d6c139896a87227d6","observation_id":"6d2f5151-84d7-480d-9bb1-bac74c918a94","resolution":{"observed_at":"2026-08-07T01:03:58.044151Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02886","last_updated":"2022-09-26T15:54:42Z","snapshot_observed_at":"2026-08-08T13:52:24.129211Z","submitted_at":"2022-06-06T20:23:30Z","title":"Graph Rationalization with Environment-based Augmentations","version":2},"cited_work":{"arxiv_id":"2206.02886","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.02886","snapshot_observed_at":"2026-08-07T01:03:57.519090Z","title":"Graph Rationalization with Environment-based Augmentations","venue":"cs.LG","work_id":"b978bfb6-76d3-40f2-bd21-e2ad4782e884","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.160097Z"},"links":{"cited_paper":"/paper/2206.02886","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:e2ea7b9b5d05afab0efd2bcb70c5b4b635865acc4ed167877b6045471f4eaf6a","observation_id":"2ae3c64f-6276-446e-a7f5-c3c30184b33e","resolution":{"observed_at":"2026-08-07T01:03:57.750646Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.11525","last_updated":"2023-08-22T09:55:34Z","snapshot_observed_at":"2026-07-06T10:36:11.192146Z","submitted_at":"2021-01-27T16:31:33Z","title":"Calibrating and Improving Graph Contrastive Learning","version":2},"cited_work":{"arxiv_id":"2101.11525","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.11525","snapshot_observed_at":"2026-08-07T01:03:57.111815Z","title":"Calibrating and Improving Graph Contrastive Learning","venue":"cs.LG","work_id":"1f4c8a0a-6279-4710-95a0-fa2c83c6924f","year":2021},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.281604Z"},"links":{"cited_paper":"/paper/2101.11525","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:82d7f1f34c0a685520ffe500c5028d3a5c92ad68007396483c49c19d79f77bc7","observation_id":"27d89c61-b303-47b3-af72-a371854ca3bb","resolution":{"observed_at":"2026-08-07T01:03:57.308190Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.00692","last_updated":"2023-03-18T08:23:33Z","snapshot_observed_at":"2026-08-04T08:54:34.448626Z","submitted_at":"2022-11-01T18:33:20Z","title":"Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.00692","snapshot_observed_at":"2026-08-07T01:03:50.379033Z","title":"Towards better out-of-distribution generalization of neural algorithmic reasoning tasks.arXiv preprint arXiv:2211.00692,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.379033Z"},"links":{"cited_paper":"/paper/2211.00692","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:8447d823074adc48b666b0c6630821380283368c2cc3220cfe208365bef1f24f","observation_id":"cec823bc-10ca-4c48-b2e1-7c9692c36f10","resolution":{"observed_at":"2026-08-07T01:03:50.379033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:00.940301Z","title":"Fisher discriminant analysis with kernels","venue":null,"work_id":"a1e5cf4c-5ff2-40f6-ba6e-8e4f2467dedc","year":1999},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.445626Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:f2cbb11fb62358d4331ac9915b1322348c6df9101d3fdcc474c43a0186b9e1fc","observation_id":"62b7524c-90bf-4b5f-bc10-dda8b18a872c","resolution":{"observed_at":"2026-08-07T01:04:01.021687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01875","last_updated":"2023-10-21T12:37:05Z","snapshot_observed_at":"2026-07-06T16:26:58.234941Z","submitted_at":"2023-10-03T08:25:32Z","title":"Towards Stable Backdoor Purification through Feature Shift Tuning","version":3},"cited_work":{"arxiv_id":"2310.01875","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.01875","snapshot_observed_at":"2026-08-07T01:03:56.769904Z","title":"Towards Stable Backdoor Purification through Feature Shift Tuning","venue":"cs.LG","work_id":"3cc08ddb-2644-4ca9-ab1f-d21ecdea1fac","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.530470Z"},"links":{"cited_paper":"/paper/2310.01875","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:67e543c8d118ec2486120a1e232d520489f8a2d32b29e2f5b2a2f8b9bbc245b2","observation_id":"dd4329e6-2133-4b63-84a1-750606982889","resolution":{"observed_at":"2026-08-07T01:03:56.932673Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.08663","last_updated":"2020-07-16T21:46:33Z","snapshot_observed_at":"2026-08-06T13:06:20.395369Z","submitted_at":"2020-07-16T21:46:33Z","title":"TUDataset: A collection of benchmark datasets for learning with graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.08663","snapshot_observed_at":"2026-08-07T01:03:50.622071Z","title":"M., Bause, F., Kersting, K., Mutzel, P ., and Neumann, M","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.622071Z"},"links":{"cited_paper":"/paper/2007.08663","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:4eea861e01355c0441a6478fb9fe4a36442b394d378910ecc981bf4534cd176d","observation_id":"228bb813-c4a9-48b1-9ab6-23a6e18f7ed1","resolution":{"observed_at":"2026-08-07T01:03:50.622071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.09992","last_updated":"2023-07-13T09:15:03Z","snapshot_observed_at":"2026-07-06T12:20:15.645829Z","submitted_at":"2021-12-18T20:14:11Z","title":"Weisfeiler and Leman go Machine Learning: The Story so far","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09992","snapshot_observed_at":"2026-08-07T01:03:50.701999Z","title":"M., Grohe, M., Fey, M., and Borgwardt, K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.701999Z"},"links":{"cited_paper":"/paper/2112.09992","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:4432e5d128ac76d0a48a719612bd0886a2869c8a66c75d654c0cdc50a362018c","observation_id":"c3820e35-dca9-46a9-89bf-ed869ef6327a","resolution":{"observed_at":"2026-08-07T01:03:50.701999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.08583","last_updated":"2023-06-05T22:23:52Z","snapshot_observed_at":"2026-08-04T20:55:50.432525Z","submitted_at":"2022-11-15T23:56:30Z","title":"Empirical Study on Optimizer Selection for Out-of-Distribution Generalization","version":3},"cited_work":{"arxiv_id":"2211.08583","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.08583","snapshot_observed_at":"2026-08-07T01:03:56.481735Z","title":"Empirical Study on Optimizer Selection for Out-of-Distribution Generalization","venue":"cs.LG","work_id":"626f646f-7ba9-4d6d-961b-494e221c9e8d","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.773569Z"},"links":{"cited_paper":"/paper/2211.08583","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:d5cb78e42e609db2123ad7f10d14be3aafa9a9316bdde2ab00adec1d7ad15768","observation_id":"26ebb3b8-e808-40d8-b4bd-0bccebe8cbfa","resolution":{"observed_at":"2026-08-07T01:03:56.566775Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:00.729283Z","title":"M., Nicolicioiu, A","venue":null,"work_id":"00d6228b-20b9-43af-82b2-96fa9aaa96a6","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.877177Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:2e187a241912b769c7b1713e2ecdd2b2467c72bb88fbdebac3746a809b147b24","observation_id":"eaf224cc-f90f-4bfa-94f1-73ef07ed33c0","resolution":{"observed_at":"2026-08-07T01:04:00.831420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16748","last_updated":"2024-07-19T17:08:00Z","snapshot_observed_at":"2026-07-06T16:25:09.382064Z","submitted_at":"2023-09-28T17:55:45Z","title":"Discovering environments with XRM","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16748","snapshot_observed_at":"2026-08-07T01:03:50.958984Z","title":"Discovering environments with XRM.arXiv preprint, arXiv:2309.16748,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:50.958984Z"},"links":{"cited_paper":"/paper/2309.16748","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:f96ba2571ff857a92f110a073479993c66cbd7919d83890132c7681db4cb2edf","observation_id":"27eda112-3e30-413a-bc6a-aa187db173f2","resolution":{"observed_at":"2026-08-07T01:03:50.958984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.02934","last_updated":"2022-06-01T14:37:01Z","snapshot_observed_at":"2026-08-07T03:22:07.581982Z","submitted_at":"2021-09-07T08:36:09Z","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.02934","snapshot_observed_at":"2026-08-07T01:03:51.013431Z","title":"Fishr: Invariant gradient variances for out-of- distribution generalization.arXiv preprint arXiv:2109.02934,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.013431Z"},"links":{"cited_paper":"/paper/2109.02934","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:1b2ec13b1aed6ca669c759995e809cebcbf6161f64c3180155a071019fab2f54","observation_id":"1fb1eec0-cf34-4e92-906b-84e8cae14b6a","resolution":{"observed_at":"2026-08-07T01:03:51.013431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10445","last_updated":"2023-08-09T14:02:55Z","snapshot_observed_at":"2026-07-06T14:33:03.656499Z","submitted_at":"2022-12-20T17:21:46Z","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","version":3},"cited_work":{"arxiv_id":"2212.10445","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.10445","snapshot_observed_at":"2026-08-07T01:03:56.163250Z","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","venue":"cs.LG","work_id":"587a6985-a8f6-49ef-b9f5-2adacb158862","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.103479Z"},"links":{"cited_paper":"/paper/2212.10445","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:68de49f8b19710a1f5b0e889f5748daaeeb137964ec3fd4b76d71f38f2bc4f68","observation_id":"36a913a0-a2b1-4c34-b4b3-0115bc67060d","resolution":{"observed_at":"2026-08-07T01:03:56.324158Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.06856","last_updated":"2022-10-28T03:58:11Z","snapshot_observed_at":"2026-08-04T06:21:08.600833Z","submitted_at":"2022-02-14T16:42:16Z","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","version":2},"cited_work":{"arxiv_id":"2202.06856","doi":null,"metadata_source":"pith","pith_arxiv_id":"2202.06856","snapshot_observed_at":"2026-08-07T01:03:55.869074Z","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","venue":"cs.LG","work_id":"fdb96b14-be68-4c84-98ef-d2d9dff9223f","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.187641Z"},"links":{"cited_paper":"/paper/2202.06856","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:7c27b4725fd19af6a82d6b9aab585a3f30173180ce0e14b3d7d2d0625867b4b4","observation_id":"f6fe9db2-ae60-4786-8ce5-ce8aaf132aed","resolution":{"observed_at":"2026-08-07T01:03:56.012455Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-07T01:03:51.294880Z","title":"Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter.arXiv preprint arXiv:1910.01108,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.294880Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:63b0339089a1813d7e33aca0529b1abdcb616513bca2f97bf23cc9ea11d38a87","observation_id":"fa9668b3-c9fb-4113-a0b0-f32a9afc4b7e","resolution":{"observed_at":"2026-08-07T01:03:51.294880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.10500","last_updated":"2019-12-23T16:20:53Z","snapshot_observed_at":"2026-08-08T17:21:20.530297Z","submitted_at":"2019-11-24T11:04:56Z","title":"Causality for Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.10500","snapshot_observed_at":"2026-08-07T01:03:51.403071Z","title":"Causality for machine learning.arXiv preprint, arXiv:1911.10500,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.403071Z"},"links":{"cited_paper":"/paper/1911.10500","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:a3fd8c8eff1f5fac5d0fc774d6d1b73e3d625f7c0228dd5930ed176058f09289","observation_id":"ae1ab6cf-6877-450a-a729-6dc2e0f02164","resolution":{"observed_at":"2026-08-07T01:03:51.403071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.10528","last_updated":"2022-10-06T07:19:01Z","snapshot_observed_at":"2026-08-04T11:36:59.184293Z","submitted_at":"2018-12-26T20:27:42Z","title":"Adversarial Attack and Defense on Graph Data: A Survey","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.10528","snapshot_observed_at":"2026-08-07T01:03:51.575455Z","title":"S., and Li, B","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.575455Z"},"links":{"cited_paper":"/paper/1812.10528","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:e82409898426a7a3100a2b93c23a4443d8ff1efbd1549a9cc851fa320e21e87a","observation_id":"c90b5d0c-6882-4769-8ae2-76ae27aefffb","resolution":{"observed_at":"2026-08-07T01:03:51.575455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:00.343302Z","title":null,"venue":null,"work_id":"abfb253e-ca36-4d67-8672-c4749d63e6a9","year":2020},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.659239Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:acb86a40487e4527114df328ad134af5a712b2db2e9998bfedb84a4e08a34b29","observation_id":"1afebdfe-c751-4188-ad5b-aa86ad4c1d2a","resolution":{"observed_at":"2026-08-07T01:04:00.441000Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.05612","last_updated":"2022-09-11T10:29:13Z","snapshot_observed_at":"2026-07-06T11:08:46.163766Z","submitted_at":"2021-05-12T12:12:24Z","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","version":3},"cited_work":{"arxiv_id":"2105.05612","doi":null,"metadata_source":"pith","pith_arxiv_id":"2105.05612","snapshot_observed_at":"2026-08-07T01:03:55.409951Z","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","venue":"cs.LG","work_id":"54d8d751-45fa-49ed-b801-0a3b0857643d","year":2021},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.961274Z"},"links":{"cited_paper":"/paper/2105.05612","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:7ca8bba44fd277c48aacd3b2892825c6ca6b90ec016b6d5bd4c3edb69b01449a","observation_id":"b3255bb6-1c76-4731-99b0-67eb58e9af56","resolution":{"observed_at":"2026-08-07T01:03:55.463141Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.00613","last_updated":"2023-05-19T07:24:53Z","snapshot_observed_at":"2026-07-06T13:48:02.215133Z","submitted_at":"2022-09-01T17:27:25Z","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","version":4},"cited_work":{"arxiv_id":"2209.00613","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.00613","snapshot_observed_at":"2026-08-07T01:03:55.253747Z","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","venue":"cs.LG","work_id":"b6315535-23fa-44ca-aeff-2fad0e3130c3","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.025250Z"},"links":{"cited_paper":"/paper/2209.00613","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:90665311a165dc32d0ea2310e9e8c9a7bcbfcc3d7b53dc3816e6c9e3751549db","observation_id":"908776b6-9fae-47e9-8ef7-fc54dc3df21d","resolution":{"observed_at":"2026-08-07T01:03:55.328800Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-07T01:03:52.174993Z","title":"Representation learning with contrastive predictive coding.arXiv preprint, arXiv:1807.03748,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.174993Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:321218545a6c4dacd64e21747a10ef19d73ec5150ecc86db05f2e847e581087a","observation_id":"3bd81502-e8fa-4776-83df-d210268cefda","resolution":{"observed_at":"2026-08-07T01:03:52.174993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.10751","last_updated":"2020-09-03T20:31:16Z","snapshot_observed_at":"2026-07-06T07:10:32.110533Z","submitted_at":"2018-10-25T07:49:09Z","title":"Attack Graph Convolutional Networks by Adding Fake Nodes","version":4},"cited_work":{"arxiv_id":"1810.10751","doi":null,"metadata_source":"pith","pith_arxiv_id":"1810.10751","snapshot_observed_at":"2026-08-07T01:03:55.060252Z","title":"Attack Graph Convolutional Networks by Adding Fake Nodes","venue":"cs.LG","work_id":"2daa7c80-31ad-4575-9802-9b659724132d","year":2018},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.263216Z"},"links":{"cited_paper":"/paper/1810.10751","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:35019659d7b41b0544d4003d5eb5770d6ac87126927dcb2e0675d79ccf294617","observation_id":"152944e2-748d-493c-8619-0a0e2da1c387","resolution":{"observed_at":"2026-08-07T01:03:55.144218Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:00.204910Z","title":"Towards out-of- distribution generalizable predictions of chemical kinetics properties","venue":null,"work_id":"6cbc3be2-21c1-491e-a034-d75f1a094433","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.360096Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:c2a01b7fdb9f6a08a5bc0fcf20cffd898e55e0054135ae994a8ed09250a20c6b","observation_id":"eb607436-e360-4385-a757-3f5e2fd9dc27","resolution":{"observed_at":"2026-08-07T01:04:00.271712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07114","last_updated":"2023-05-08T09:03:35Z","snapshot_observed_at":"2026-07-06T12:37:46.989132Z","submitted_at":"2022-02-15T00:55:16Z","title":"Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack","version":2},"cited_work":{"arxiv_id":"2202.07114","doi":null,"metadata_source":"pith","pith_arxiv_id":"2202.07114","snapshot_observed_at":"2026-08-07T01:03:54.898853Z","title":"Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack","venue":"cs.LG","work_id":"a301ba70-8459-44e6-879e-8c6b7f3a8a3d","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.446013Z"},"links":{"cited_paper":"/paper/2202.07114","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:c93ddf8c7843615cf390b11af2ddfc55d0cbcd6fb2722d5da9417d13afccd10a","observation_id":"bf899102-2853-44a2-9698-2fd1d6b73eb9","resolution":{"observed_at":"2026-08-07T01:03:54.970604Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.15902","last_updated":"2023-06-28T03:52:41Z","snapshot_observed_at":"2026-07-06T15:47:38.256580Z","submitted_at":"2023-06-28T03:52:41Z","title":"Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization","version":1},"cited_work":{"arxiv_id":"2306.15902","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.15902","snapshot_observed_at":"2026-08-07T01:03:54.720736Z","title":"Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization","venue":"cs.LG","work_id":"fd298d29-29e1-40a6-b32e-450f1592ae8d","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.547361Z"},"links":{"cited_paper":"/paper/2306.15902","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:849dc2c47dc0e8a86efbe9620f44a8ed1e86754f4130b6d28f2a0205a1838353","observation_id":"f0b71f7f-1938-4556-8371-a9ca724dab7f","resolution":{"observed_at":"2026-08-07T01:03:54.795073Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2210.11075","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:03:54.564740Z","title":"Freeze then train: Towards provable representation learning under spurious correlations and feature noise.arXiv preprint arXiv:2210.11075,","venue":null,"work_id":"f8c6ba0c-5972-443d-85eb-331822fdd5a6","year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.614892Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:792ae287a401b9177b0be40a8ac5aa24be76fb8405c3bd5cead1ae554013e762","observation_id":"3f634531-8f22-4b78-a9d6-66675d68fada","resolution":{"observed_at":"2026-08-07T01:03:54.641867Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.15445","last_updated":"2022-07-01T23:31:41Z","snapshot_observed_at":"2026-07-06T10:28:54.011729Z","submitted_at":"2020-12-31T04:34:27Z","title":"Explainability in Graph Neural Networks: A Taxonomic Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.15445","snapshot_observed_at":"2026-08-07T01:03:52.726496Z","title":"XGNN: towards model-level explanations of graph neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.726496Z"},"links":{"cited_paper":"/paper/2012.15445","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:97532ac05114a695f02c06c722ffa340fe5375638c5994b8e1ca0b889cdbbbd5","observation_id":"8c0ab7a5-4099-48fb-856a-30f8fbf31d2c","resolution":{"observed_at":"2026-08-07T01:03:52.726496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12293","last_updated":"2023-02-07T17:28:17Z","snapshot_observed_at":"2026-07-06T12:32:20.389256Z","submitted_at":"2022-01-28T17:58:38Z","title":"Understanding Why Generalized Reweighting Does Not Improve Over ERM","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12293","snapshot_observed_at":"2026-08-07T01:03:52.827991Z","title":"Z., and Ravikumar, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.827991Z"},"links":{"cited_paper":"/paper/2201.12293","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:49d7610994c637eb70b5a9f55a38ae97769cbae3a60e17e38a1b0da52242a30c","observation_id":"e12304df-3a09-453b-a64e-718aab9a25b0","resolution":{"observed_at":"2026-08-07T01:03:52.827991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.07346","last_updated":"2023-07-31T20:52:20Z","snapshot_observed_at":"2026-07-06T14:30:40.323044Z","submitted_at":"2022-12-14T17:17:10Z","title":"Learning useful representations for shifting tasks and distributions","version":3},"cited_work":{"arxiv_id":"2212.07346","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.07346","snapshot_observed_at":"2026-08-07T01:03:54.144316Z","title":"Learning useful representations for shifting tasks and distributions","venue":"cs.LG","work_id":"4e050221-4876-49e5-a66d-4ef9a7bcc984","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.903819Z"},"links":{"cited_paper":"/paper/2212.07346","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:c98555653a4463c12be51a744cd3025244f9906ed8b47055dc8d08d6bfcc42b3","observation_id":"3055f6c7-0bf1-4883-9589-0387a62f47b2","resolution":{"observed_at":"2026-08-07T01:03:54.310302Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.15516","last_updated":"2022-07-08T14:38:47Z","snapshot_observed_at":"2026-07-06T12:54:07.797296Z","submitted_at":"2022-03-24T20:39:33Z","title":"Rich Feature Construction for the Optimization-Generalization Dilemma","version":2},"cited_work":{"arxiv_id":"2203.15516","doi":null,"metadata_source":"pith","pith_arxiv_id":"2203.15516","snapshot_observed_at":"2026-08-07T01:03:53.951848Z","title":"Rich Feature Construction for the Optimization-Generalization Dilemma","venue":"cs.LG","work_id":"a7a96b60-2160-4bd6-80c1-e7020c76f075","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.997689Z"},"links":{"cited_paper":"/paper/2203.15516","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:e5cb06f2556b5c3ce153be888942b49187872962fb5b761d18e8d0c6c86e6045","observation_id":"37770d28-d54e-47df-99eb-5b03268a7da9","resolution":{"observed_at":"2026-08-07T01:03:54.014315Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08423","last_updated":"2025-07-24T21:15:25Z","snapshot_observed_at":"2026-07-06T15:54:47.352645Z","submitted_at":"2023-07-17T12:14:14Z","title":"Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08423","snapshot_observed_at":"2026-08-07T01:03:53.067970Z","title":"F., Tehrani, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:53.067970Z"},"links":{"cited_paper":"/paper/2307.08423","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:4551c32d98b90a4d47f572b25383dc767440c00a91a9e1bdfc66020ca8816ec1","observation_id":"4c47a369-f202-4ba9-91fa-0d2be9c56329","resolution":{"observed_at":"2026-08-07T01:03:53.067970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.10713","last_updated":"2022-11-23T06:40:24Z","snapshot_observed_at":"2026-08-07T19:55:02.955605Z","submitted_at":"2020-12-19T15:24:04Z","title":"Fundamental Limits and Tradeoffs in Invariant Representation Learning","version":4},"cited_work":{"arxiv_id":"2012.10713","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.10713","snapshot_observed_at":"2026-08-07T01:03:53.789503Z","title":"Fundamental Limits and Tradeoffs in Invariant Representation Learning","venue":"cs.LG","work_id":"2b146f40-0b2e-4ecc-97d8-ba25ae592afc","year":2020},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:53.141546Z"},"links":{"cited_paper":"/paper/2012.10713","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:9146768ddc93ae98b3ee1aea25e01a239f82f387aceeaa6988373ec2f9136a99","observation_id":"2faa4dd4-206a-482b-b1f2-24d8c77e975f","resolution":{"observed_at":"2026-08-07T01:03:53.842677Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.06046","last_updated":"2023-12-04T22:16:14Z","snapshot_observed_at":"2026-07-06T15:53:07.429379Z","submitted_at":"2023-07-12T09:49:15Z","title":"A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.06046","snapshot_observed_at":"2026-08-07T01:03:53.209426Z","title":"Graph neural networks: A review of methods and applications.AI Open, 1:57–81, 2020a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:53.209426Z"},"links":{"cited_paper":"/paper/2307.06046","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:d612bd906e1cac1fcc16c95b4ecbd18cdba5f649ec17da4bb8fb06e0eefe21db","observation_id":"0e6775d3-6e68-4ba1-a31d-53b804ff8282","resolution":{"observed_at":"2026-08-07T01:03:53.209426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03256","last_updated":"2023-06-05T21:17:48Z","snapshot_observed_at":"2026-07-06T15:38:54.127539Z","submitted_at":"2023-06-05T21:17:48Z","title":"Explaining and Adapting Graph Conditional Shift","version":1},"cited_work":{"arxiv_id":"2306.03256","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.03256","snapshot_observed_at":"2026-08-07T01:03:53.603958Z","title":"Explaining and Adapting Graph Conditional Shift","venue":"cs.LG","work_id":"d3b1c720-7a26-4c66-8fa6-59a041e0e90e","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:53.272935Z"},"links":{"cited_paper":"/paper/2306.03256","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:9c4e10316ae6d79af68b6693bc319069361de79e8a389b7b0b27ed7c6a93d4d7","observation_id":"a7859be1-fc1f-432f-9a48-b33e472cc543","resolution":{"observed_at":"2026-08-07T01:03:53.693431Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.11371","last_updated":"2021-08-25T17:58:21Z","snapshot_observed_at":"2026-07-06T11:41:31.540876Z","submitted_at":"2021-08-25T17:58:21Z","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.11371","snapshot_observed_at":"2026-08-07T01:03:53.378962Z","title":"Understanding the generalization of adam in learning neural networks with proper regularization.arXiv preprint arXiv:2108.11371, 2021a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:53.378962Z"},"links":{"cited_paper":"/paper/2108.11371","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:a7a61a61b8f69942c4aa2dbfad3f59bf741d9e7b2365725eb14e326127dca0cc","observation_id":"9a09d1a1-7803-4ba4-8f88-b454b1bcedfa","resolution":{"observed_at":"2026-08-07T01:03:53.378962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:00.067369Z","title":"Adversarial attacks on neural networks for graph data","venue":null,"work_id":"8d6834be-9202-49a0-8fe2-18f3eebf3557","year":2018},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:53.455714Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:613946ed8808dd5bc76b3be8ec9dc1b5a68e50969b945103218064641bee73e1","observation_id":"1a8fd6fa-d024-4893-b999-90d9b49dba3f","resolution":{"observed_at":"2026-08-07T01:04:00.103857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:02.282913Z","title":"Nuanced metrics for measuring unintended bias with real data for text classification","venue":null,"work_id":"b7e5f905-3b37-4a24-80c6-52ccb3672660","year":2019},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":1996,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.223651Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:9242cc653b93e38b677df80b8686b17e4dc14b2093a23b5798f320d9fbac8d52","observation_id":"51bfceb4-8a55-481d-979b-657706a6f7b1","resolution":{"observed_at":"2026-08-07T01:04:02.377403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.06589","last_updated":"2023-10-26T13:13:16Z","snapshot_observed_at":"2026-07-06T13:52:09.972057Z","submitted_at":"2022-09-14T12:13:59Z","title":"Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks","version":4},"cited_work":{"arxiv_id":"2209.06589","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.06589","snapshot_observed_at":"2026-08-07T01:03:58.483344Z","title":"Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks","venue":"cs.LG","work_id":"7556a124-1e17-4c2f-8cb0-faab08956189","year":2022},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:49.856982Z"},"links":{"cited_paper":"/paper/2209.06589","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:8187440ab0f6d945d949500ebee0d98f349cd272167c7e498861160402e44668","observation_id":"d3f5f3ba-8fcf-44b4-928e-505ad80a7624","resolution":{"observed_at":"2026-08-07T01:03:58.618577Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1607.08022","last_updated":"2017-11-06T14:21:43Z","snapshot_observed_at":"2026-08-05T08:35:49.218794Z","submitted_at":"2016-07-27T10:23:00Z","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.08022","snapshot_observed_at":"2026-08-07T01:03:52.091670Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":1999,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:52.091670Z"},"links":{"cited_paper":"/paper/1607.08022","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:68f6a265964c6a56e1d88bb56ba2faa609ace915f537ab791678719475d02da4","observation_id":"46a4c99b-4e5c-4e64-9198-6c2db8269df0","resolution":{"observed_at":"2026-08-07T01:03:52.091670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:02.093988Z","title":"Understanding and improving graph injection attack by promoting unnoticeability","venue":null,"work_id":"d19e14e8-72c4-4132-af89-d8ba5931b618","year":2024},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2005,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.539027Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:188d083b2912ce5e8a988685ae383417a2ea4ebef4dbcff1a0d707ae0a39a839","observation_id":"c150ef1d-173c-4d16-9998-6e9a72268fd9","resolution":{"observed_at":"2026-08-07T01:04:02.203926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06715","last_updated":"2023-10-05T15:29:01Z","snapshot_observed_at":"2026-08-06T07:17:14.476525Z","submitted_at":"2023-04-13T17:59:03Z","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06715","snapshot_observed_at":"2026-08-07T01:03:47.767738Z","title":"Crabbé, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.767738Z"},"links":{"cited_paper":"/paper/2304.06715","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:166dcf5cd28e94c15264e76700fca14732fd4f190672d47ca301c783e8fe8c70","observation_id":"611f9a34-4e45-4161-854c-dd9f3a4c409c","resolution":{"observed_at":"2026-08-07T01:03:47.767738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15792","last_updated":"2024-04-25T07:43:26Z","snapshot_observed_at":"2026-07-06T15:33:06.904026Z","submitted_at":"2023-05-25T07:16:00Z","title":"IDEA: Invariant Defense for Graph Adversarial Robustness","version":2},"cited_work":{"arxiv_id":"2305.15792","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.15792","snapshot_observed_at":"2026-08-07T01:03:55.551294Z","title":"IDEA: Invariant Defense for Graph Adversarial Robustness","venue":"cs.LG","work_id":"06c8f553-2905-4d4b-8726-5292d227f178","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.875563Z"},"links":{"cited_paper":"/paper/2305.15792","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:6d6f866194e42d8aa0b59a8b000767b4e35ccc2ee0882f31ec9d081a5885a96e","observation_id":"96c3e17f-5212-4d9a-9e5f-6be60f46e44d","resolution":{"observed_at":"2026-08-07T01:03:55.632582Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:00.531242Z","title":"E., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R","venue":null,"work_id":"7d087383-a6db-4421-9535-150701a9b80c","year":1929},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.474436Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:6a62996036f95f800f2c3a7ecda86ec6e3b9c2c6499b49239214744b5d23569f","observation_id":"dab9c4ee-af95-431b-8f8a-53b35b239b94","resolution":{"observed_at":"2026-08-07T01:04:00.634711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.04525","last_updated":"2020-07-09T03:06:06Z","snapshot_observed_at":"2026-08-07T18:33:12.642125Z","submitted_at":"2020-07-09T03:06:06Z","title":"PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.04525","snapshot_observed_at":"2026-08-07T01:03:51.790439Z","title":"A., Hassani, K., Jayaraman, P","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:51.790439Z"},"links":{"cited_paper":"/paper/2007.04525","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:53fa8860836ba8511962a0aafb777dc9fc9701b2b6a9625c1f1d71287fcb2c6a","observation_id":"457e0b37-b11f-491f-832e-07aa266065b8","resolution":{"observed_at":"2026-08-07T01:03:51.790439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.05441","last_updated":"2023-05-25T04:12:52Z","snapshot_observed_at":"2026-07-06T14:50:37.130425Z","submitted_at":"2023-02-10T18:58:03Z","title":"Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features","version":2},"cited_work":{"arxiv_id":"2302.05441","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.05441","snapshot_observed_at":"2026-08-07T01:03:59.736856Z","title":"Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features","venue":"cs.LG","work_id":"29654229-d440-4b44-8614-b9bdce4d5bab","year":2023},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.435707Z"},"links":{"cited_paper":"/paper/2302.05441","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:2b413b7f9e156e00b585e9feb41b27d56b67f33c6894904ada8efd74e5e3d43e","observation_id":"87bab897-4c45-48f0-8201-1e7d8a8c2c7a","resolution":{"observed_at":"2026-08-07T01:03:59.771744Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01261","last_updated":"2018-10-17T17:51:36Z","snapshot_observed_at":"2026-07-06T06:42:54.610341Z","submitted_at":"2018-06-04T17:58:18Z","title":"Relational inductive biases, deep learning, and graph networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01261","snapshot_observed_at":"2026-08-07T01:03:46.980089Z","title":"W., Hamrick, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:46.980089Z"},"links":{"cited_paper":"/paper/1806.01261","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:53c1d6a393bc86079ca5cf0e129163bafea52939944d3b2a4c741dd77093094d","observation_id":"958fd22b-e0bc-483b-a354-f713b85cf71c","resolution":{"observed_at":"2026-08-07T01:03:46.980089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09816","last_updated":"2023-02-15T10:01:31Z","snapshot_observed_at":"2026-08-06T18:01:31.723021Z","submitted_at":"2020-12-17T18:34:45Z","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09816","snapshot_observed_at":"2026-08-07T01:03:46.623707Z","title":"and Li, Y","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:46.623707Z"},"links":{"cited_paper":"/paper/2012.09816","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:c87a044cf7bca92ba254ffac45c6a2860440e109d3d68b483d89c36b16812804","observation_id":"b0c73fea-4d4e-4224-a0ba-7902fca8efe4","resolution":{"observed_at":"2026-08-07T01:03:46.623707Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10340","last_updated":"2020-04-21T23:25:13Z","snapshot_observed_at":"2026-08-07T18:30:26.178863Z","submitted_at":"2020-04-21T23:25:13Z","title":"The iWildCam 2020 Competition Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10340","snapshot_observed_at":"2026-08-07T01:03:47.063625Z","title":"The iwildcam 2020 competition dataset.arXiv preprint arXiv:2004.10340,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.063625Z"},"links":{"cited_paper":"/paper/2004.10340","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:c0ce57a836f35591efb2ba7d213bc40c7d7e3a14902cc9176d010c092794d235","observation_id":"29589d60-b248-498d-a070-2bbd511b832f","resolution":{"observed_at":"2026-08-07T01:03:47.063625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:01.469454Z","title":"A closer look at distribution shifts and out-of-distribution generalization on graphs","venue":null,"work_id":"3cb5f3fe-c82c-4cfa-bce4-5d841c71138e","year":2021},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:48.006500Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:6f71a1521e95ae6c3bf6cfcccdb4f92566f71587a66c9886fc944433be1f1e36","observation_id":"02ca1b2d-2b3e-4e1b-bd99-6457b550ea99","resolution":{"observed_at":"2026-08-07T01:04:01.550984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T01:04:01.807304Z","title":"Learning a similarity metric discriminatively, with application to face verification","venue":null,"work_id":"9aafad29-bb56-457a-9205-a8a142249313","year":2005},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.601772Z"},"links":{"citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:0a6c895911348f6575f4b09cb06672e4985c879eedc82a3412ab59606b0c3caf","observation_id":"a518fa1b-4ceb-4481-8ec6-74a962dc57b6","resolution":{"observed_at":"2026-08-07T01:04:01.962476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02893","last_updated":"2020-03-27T19:07:58Z","snapshot_observed_at":"2026-07-06T08:05:24.076802Z","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":"2026-08-07T01:03:46.754352Z","title":"Invariant risk minimization.arXiv preprint arXiv:1907.02893,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:46.754352Z"},"links":{"cited_paper":"/paper/1907.02893","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:0e94bafa69e161ae9853a5d0b9a6199967d9b0b959ff4df09aae72f4431b23c0","observation_id":"abfe5022-f24d-4d7d-a1e8-4a4e7b3721bb","resolution":{"observed_at":"2026-08-07T01:03:46.754352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.15831","last_updated":"2021-06-30T06:21:42Z","snapshot_observed_at":"2026-08-07T18:54:03.039868Z","submitted_at":"2021-06-30T06:21:42Z","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.15831","snapshot_observed_at":"2026-08-07T01:03:46.659507Z","title":"The evolution of out-of-distribution robustness throughout fine-tuning.arXiv preprint arXiv:2106.15831,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:46.659507Z"},"links":{"cited_paper":"/paper/2106.15831","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:38a676ea826c25476a6aec40f7daed3991b79c8b5e4085d848d74c98beb740e9","observation_id":"48038931-74da-400c-ac6d-0d2aadf2f3f2","resolution":{"observed_at":"2026-08-07T01:03:46.659507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11287","last_updated":"2020-11-18T01:16:09Z","snapshot_observed_at":"2026-07-06T09:30:50.462029Z","submitted_at":"2020-06-19T18:00:00Z","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11287","snapshot_observed_at":"2026-08-07T01:03:47.842442Z","title":"W., Xu, R., Cranmer, K., Spergel, D","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:47.842442Z"},"links":{"cited_paper":"/paper/2006.11287","citing_paper":"/paper/2506.12226"},"observation_digest":"sha256:42a2321a1dc4feae1822c68fb2908531ea86553a4dd094ce43bc029d309a39cf","observation_id":"4dbcfa0c-a6ca-4aef-b996-009b12febdd1","resolution":{"observed_at":"2026-08-07T01:03:47.842442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.12226","last_updated":"2025-06-13T21:03:49Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T19:12:57.063735Z","submitted_at":"2025-06-13T21:03:49Z","title":"Learning Causality for Modern Machine Learning"},"reference_resolution":{"displayed":79,"state_counts":{"malformed_identifier":0,"metadata_mismatch":9,"parse_uncertain":0,"unresolved":40,"verified_exact":18,"verified_fuzzy":12},"total_outbound_references":79},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 79 of 79 outbound references and 0 inbound Pith citation observations for arXiv:2506.12226."}