{"as_of":"2026-08-18T15:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f79e1fb065d61d7be171e14d8d64b855e228d4d8a292946450cf4d37531c0ac7","coverage":[{"denominator":91,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":91,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:39:44.587149Z","state":"measured"},{"denominator":93,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":93,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:57:00.950744Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-16T07:00:43.314495Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.07907","snapshot_observed_at":"2026-08-16T10:57:00.950744Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.16920","last_updated":"2025-08-11T13:29:28Z","snapshot_observed_at":"2026-08-17T18:16:06.091886Z","submitted_at":"2025-04-23T17:45:42Z","title":"Summary statistics of learning link changing neural representations to behavior","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-16T10:57:00.950744Z"},"links":{"cited_paper":"/paper/2507.07907","citing_paper":"/paper/2504.16920"},"observation_digest":"sha256:b5b65fde87d0ade3d57c125bf16371d1140c2340eda8dc7a443dad1adf7e1d67","observation_id":"16d859fb-611f-4494-970c-5230899e6163","resolution":{"observed_at":"2026-08-16T10:57:00.950744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"cited_work":{"arxiv_id":"2507.07907","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.07907","snapshot_observed_at":"2026-06-23T04:13:39.099253Z","title":"and Mori, F","venue":null,"work_id":"84342f08-df28-47a4-9715-dac7c383c077","year":null},"citing_paper":{"arxiv_id":"2602.04774","last_updated":"2026-05-08T16:24:57Z","snapshot_observed_at":"2026-08-15T04:58:48.280086Z","submitted_at":"2026-02-04T17:11:36Z","title":"Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-16T06:58:38.927268Z"},"links":{"cited_paper":"/paper/2507.07907","citing_paper":"/paper/2602.04774"},"observation_digest":"sha256:5f0a1ed12ddcdaa7c85c638c0d84d742115e2fe59afe9ec93045b64f6f5c785c","observation_id":"73d71fe1-5ee9-4800-bba5-413e9bac63e0","resolution":{"observed_at":"2026-06-23T04:13:39.099253Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.07907/citation-record","integrity":"/paper/2507.07907/integrity","json":"/paper/2507.07907/citation-record.json","paper":"/paper/2507.07907"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.482331Z","title":"Botvinick and Jonathan D","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.482331Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:fef3c99ce2d55121ebf74280fdde3c182e667509d32e295da5d4e9777dba4c55","observation_id":"52f1f0de-6ba2-43e4-b595-1d24dcd9fe94","resolution":{"observed_at":"2026-08-06T18:39:37.482331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.543303Z","title":"The easy-to-hard effect in human (homo sapiens) and rat (rattus norvegicus) auditory identification.Journal of Comparative Psychology, 122(2):132, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.543303Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:8522870efc0aa823e8486f66ef5e95ea4ed37f5b13266d29be7c8f2e84d860f5","observation_id":"ce6fb437-88a0-4be5-8244-434513096f3b","resolution":{"observed_at":"2026-08-06T18:39:37.543303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.613934Z","title":"Springer Nature, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.613934Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:831d8325fa0eac9fc8b07044d16a2a3f9b19a982cdb2bfcb6f6b3fb98f090cf2","observation_id":"592325bb-69bf-4633-a667-c3113e620610","resolution":{"observed_at":"2026-08-06T18:39:37.613934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.658215Z","title":"Random search for hyper-parameter optimization.The journal of machine learning research, 13(1):281–305, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.658215Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:3684cbebb599adc75b92a826a538753518527a25e666e11dcf31aa924be5742a","observation_id":"1b2de035-50c9-4737-802c-53ddfcf13ccc","resolution":{"observed_at":"2026-08-06T18:39:37.658215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.718171Z","title":"Practical bayesian optimization of machine learning algorithms.Advances in neural information processing systems, 25, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.718171Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:68303881582d87748e76242f9cfc77bb4f407e516318311ea88ac1058a454e6f","observation_id":"2d1f71b3-9005-4812-9ca8-464b6898e919","resolution":{"observed_at":"2026-08-06T18:39:37.718171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.782205Z","title":"Gradient-based hyperparameter opti- mization through reversible learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.782205Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:3082cd06632fef92a49e6868b4ab33db7553300e9add48a67eda596056f33645","observation_id":"283b93ba-10f0-4ac1-bbad-ae01dc638884","resolution":{"observed_at":"2026-08-06T18:39:37.782205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.844820Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.844820Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:142c340dbb07e0ad7a6e1c6d6baaf23071e6141d35a5f4f259bdac4b34dd0042","observation_id":"a3c4d8d9-d987-406e-8bc8-12d947cea1e2","resolution":{"observed_at":"2026-08-06T18:39:37.844820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.910355Z","title":"Engel and C","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.910355Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:e39ee534dffe2bd4d23e749c39468776e9dd6319807c4b54bcb20ac8b5cd806f","observation_id":"80c20d4e-f629-41a9-92bf-5689f86bef52","resolution":{"observed_at":"2026-08-06T18:39:37.910355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:37.999550Z","title":"Optimal errors and phase transitions in high-dimensional generalized linear models.Proceedings of the National Academy of Sciences, 116(12):5451–5460, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:37.999550Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:3a41a338ba1d5839b6d5e5f4ea8217f152b2d44564293e7ba012457bb5a2e8ba","observation_id":"8c65f617-ffdc-46f6-8b0b-a75fccb66e41","resolution":{"observed_at":"2026-08-06T18:39:37.999550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:38.052672Z","title":"Learning curves of generic features maps for realistic datasets with a teacher-student model.Advances in Neural Information Processing Systems, 34:18137–18151, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.052672Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:fd832c7ddd6b0d7dfec01e44be3be96521bfbe87f5e9d3af359307dd426fdef3","observation_id":"b837e9e2-c2e6-491f-a3ed-cf25c26f8fa1","resolution":{"observed_at":"2026-08-06T18:39:38.052672Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:38.133041Z","title":"The role of regularization in classification of high-dimensional noisy Gaussian mixture","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.133041Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:633f2be191889a37df5522ddc21f238339c829ca8b05b1262c5f556cee5af37b","observation_id":"7267e221-9cf0-4dc3-b6dc-1b59a696f661","resolution":{"observed_at":"2026-08-06T18:39:38.133041Z","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":"2026-08-06T18:39:55.286991Z","title":"Gener- alisation error in learning with random features and the hidden manifold model","venue":null,"work_id":"4aa7892c-8df9-4360-a033-0c28aecb6e73","year":2020},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.191066Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:93b910e8b01cce0a3c319a8f14f936cc9b56da6cff4df757f7ef36f72da931e7","observation_id":"8e2fc506-c714-4380-aa70-effed298c75d","resolution":{"observed_at":"2026-08-06T18:39:55.339313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:55.158887Z","title":"Dy- namics of stochastic gradient descent for two-layer neural networks in the teacher-student setup","venue":null,"work_id":"1d9baf62-0917-4aa8-813e-0c5a98f1b24f","year":2019},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.263656Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:259c32f53faf9dfbc6610922736ca7e308f75eb09263bf39e8e4a316d520fdac","observation_id":"b0a5135e-f6ce-42e8-97d1-1a22c5dabb02","resolution":{"observed_at":"2026-08-06T18:39:55.220479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:55.035603Z","title":"Dynamical mean-field theory for stochastic gradient descent in gaussian mixture classification.Advances in Neural Information Processing Systems, 33:9540–9550, 2020","venue":null,"work_id":"c7aecbb6-358c-4f07-844c-bbb9929743bb","year":2020},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.343415Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:4a87dee74f2fc86f2c6266736284dfcc1c82e032c6aa6a2dc243959d7c43e1b6","observation_id":"2b0c1db0-c7b6-4134-b087-6dea6f7834ca","resolution":{"observed_at":"2026-08-06T18:39:55.082169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:38.407723Z","title":"Self-consistent dynamical field theory of kernel evolution in wide neural networks.Advances in Neural Information Processing Systems, 35:32240–32256, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.407723Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:efb8797b923d80f8e8d7b58c88ae825e81c3b5bcc0351c7b66b65baa59e73b38","observation_id":"2c7a530f-abdc-41cd-b929-7b1eb6f1353d","resolution":{"observed_at":"2026-08-06T18:39:38.407723Z","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":"2026-08-06T18:39:54.905819Z","title":"An analytical theory of curriculum learning in teacher-student networks","venue":null,"work_id":"d4a29635-84ce-4609-b8ee-f6846bbdb4ff","year":2022},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.472295Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:a5d2e2818dbaa193bbed18bcb472f569fa9063446f07afd23b9092cee2b376b4","observation_id":"bb764f37-37f5-4788-b0d3-498ffb1eeda1","resolution":{"observed_at":"2026-08-06T18:39:54.945914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:54.761508Z","title":"Why do animals need shaping? a theory of task composition and curriculum learning","venue":null,"work_id":"c67e94fe-c57d-44cc-9819-85faf5002823","year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.546431Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:e468e82d73e21f86939c4b1dc66ff21006fd79a8751b799c0554eb670b829ae1","observation_id":"f6ee6bca-79f5-4704-a1f5-eac4089e52a4","resolution":{"observed_at":"2026-08-06T18:39:54.821832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:54.547704Z","title":"Curriculum learning in humans and neural networks, Mar 2025","venue":null,"work_id":"3f4f7942-59e6-4da1-94b9-ab610aefdf20","year":2025},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.627073Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:ddc85fabf88ff51a2791eeb942c6b2a37ca1f1c9fc094781da7433dd397638c2","observation_id":"133a8815-a4bb-45cd-a5f0-909fe21117b0","resolution":{"observed_at":"2026-08-06T18:39:54.637764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:54.374521Z","title":"High-dimensional learning of narrow neural networks.Journal of Statistical Mechanics: Theory and Experiment, 2025(2):023402, 2025","venue":null,"work_id":"ab9308f8-ce16-4e1c-bdf1-8685ef653abf","year":2025},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.700719Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:2f4639b36b7222ecbe5b373f7ae29a39ac3827f706f82a74d7a79a16426bfd9e","observation_id":"5470782c-f97d-481f-b096-84a49b1b6541","resolution":{"observed_at":"2026-08-06T18:39:54.460619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:38.772814Z","title":"Learning by on-line gradient descent.Journal of Physics A: Mathematical and general, 28(3):643, 1995","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.772814Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:9555088e973ea89730dd61ceab485e280c9ca21150a65bdf62594c374759c7fc","observation_id":"0873e939-db2b-4cff-8722-1ea390868025","resolution":{"observed_at":"2026-08-06T18:39:38.772814Z","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":"2026-08-06T18:39:54.109268Z","title":"Exact solution for on-line learning in multilayer neural networks","venue":null,"work_id":"cf4fe529-798d-4f57-9779-5a8b554cdefb","year":1995},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.846040Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:9020b23c9e2ebd3e4f4eaf9c9edbfb994e65dc83401e51c887e4863fadd48d80","observation_id":"ee986a4b-e6e9-4135-ac0c-83db804774b5","resolution":{"observed_at":"2026-08-06T18:39:54.232347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:53.955030Z","title":"Analysis of on-line training with optimal learning rates.Physical Review E, 58(5):6379, 1998","venue":null,"work_id":"1397513d-b884-4a04-9577-15a576a0cc88","year":1998},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.918212Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:2bee25ce9c5dce63fb1f5742386d3b1c4ef6d804d12cecbfa49c2b116e768789","observation_id":"ddce2ffb-9f31-4ac6-9842-d09b1f2d0117","resolution":{"observed_at":"2026-08-06T18:39:54.033205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19919","last_updated":"2024-07-15T12:07:03Z","snapshot_observed_at":"2026-08-18T07:54:27.354660Z","submitted_at":"2023-10-30T18:29:26Z","title":"Meta-Learning Strategies through Value Maximization in Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19919","snapshot_observed_at":"2026-08-06T18:39:38.993799Z","title":"Meta-learning strategies through value maximization in neural networks.arXiv preprint arXiv:2310.19919, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:38.993799Z"},"links":{"cited_paper":"/paper/2310.19919","citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:4ff43697baccc7bf05d42d3f7a20c5366befd851112af91644fe65e803750b0b","observation_id":"3ad444c6-b75d-4f91-a3f6-00d765b92091","resolution":{"observed_at":"2026-08-06T18:39:38.993799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:39.054136Z","title":"Courier Corporation, 2004","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.054136Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:8a639634cb144ff1e1b8c0967a9678b0ff3c422ce848a8c8b17bacac820c3109","observation_id":"c9872b6a-b8ab-4ab2-845c-04d8e6ae3952","resolution":{"observed_at":"2026-08-06T18:39:39.054136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:39.120325Z","title":"SIAM, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.120325Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:6dc599024958673c3c8249521495bbbb895e2e5039aad3e17f3281789a204f6d","observation_id":"31a490cd-0281-4cc4-a5b0-f3c92416853a","resolution":{"observed_at":"2026-08-06T18:39:39.120325Z","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":"2026-08-06T18:39:53.633953Z","title":"Practical recommendations for gradient-based training of deep architectures","venue":null,"work_id":"5d01ebdc-021a-4abc-b845-172a310a0f8f","year":2012},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.186637Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:ab7bec65cb25b75f95544ebf0a52b0cdc567835d53a044399a964914c29aa800","observation_id":"f9c912ea-a254-485c-8d0f-aae36345d3a3","resolution":{"observed_at":"2026-08-06T18:39:53.788367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:53.456397Z","title":"Why warmup the learning rate? underlying mecha- nisms and improvements.Advances in Neural Information Processing Systems, 37:111760–111801, 2024","venue":null,"work_id":"2c1f18c7-d13b-4eda-b59b-7afa5a4f0372","year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.222636Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:e1fffa9ef49438f5803ffd402f5b9651082002681cf767d05443ae287a08b949","observation_id":"a5c71fdd-f0fc-4144-b5b3-3aa5f6a141d0","resolution":{"observed_at":"2026-08-06T18:39:53.532450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:39.272763Z","title":"Sgdr: Stochastic gradient descent with warm restarts","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.272763Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:c06619fa2cd7cdb31bf1b0b190cd52718345f2dc522273e0af10ac34e203a239","observation_id":"30a7c17c-b881-4505-bb64-0e5b9baf9795","resolution":{"observed_at":"2026-08-06T18:39:39.272763Z","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":"2026-08-06T18:39:53.240573Z","title":"Online learning rate adaptation with hypergradient descent","venue":null,"work_id":"48255eac-9ea1-4ffc-9706-dd9b5d1fb1bb","year":2018},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.346949Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:111b7f44b36a4acfd96de2ed5b7bd7c21f8334f62db5f48da0993eb885bd728d","observation_id":"1f596d8d-8405-488a-ad0d-f0e0f9dbaa97","resolution":{"observed_at":"2026-08-06T18:39:53.334964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:53.029480Z","title":"Globally optimal parameters for on-line learning in multilayer neural networks.Physical review letters, 79(13):2578, 1997","venue":null,"work_id":"060a7af1-2d84-44f5-b88a-0f7c1558b0d1","year":1997},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.399890Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:f4e275557726cfa0b86b028bcf16d1f6aa52df7a593304d6956299864a7ede0a","observation_id":"c3d0100f-2999-44ca-a94b-e7440979f63e","resolution":{"observed_at":"2026-08-06T18:39:53.116098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:52.827119Z","title":"Optimization of on-line principal component analysis.Journal of Physics A: Mathematical and General, 32(22):4061, 1999","venue":null,"work_id":"a3bb18c7-b67c-4072-8b3f-f36710a90df7","year":1999},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.459449Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:3119884842ebc4ab3531604a2e64c6cdb509a76cada7cd0d565bbe8700269ced","observation_id":"087bf65e-18c5-4e4c-9e32-d696057851df","resolution":{"observed_at":"2026-08-06T18:39:52.908411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.04509","last_updated":"2022-02-09T15:15:39Z","snapshot_observed_at":"2026-08-16T17:22:31.362031Z","submitted_at":"2022-02-09T15:15:39Z","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","version":1},"cited_work":{"arxiv_id":"2202.04509","doi":null,"metadata_source":"pith","pith_arxiv_id":"2202.04509","snapshot_observed_at":"2026-08-06T18:39:45.044616Z","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","venue":"cs.LG","work_id":"fe014e07-cd2b-4509-8ad6-15ce7a9a78c6","year":2022},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.539635Z"},"links":{"cited_paper":"/paper/2202.04509","citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:320bc221e0a54ff74c35bc610dfd900bc5cc7367bf57dc28f4920c45821bc640","observation_id":"f25371e4-785c-4b18-b5ac-b47287052cdb","resolution":{"observed_at":"2026-08-06T18:39:45.097555Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:52.619568Z","title":"Optimal protocols for contin- ual learning via statistical physics and control theory","venue":null,"work_id":"e7cad6de-957c-44c0-9d48-2a18fb98c0ff","year":2025},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.612502Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:bfcbce79fc36beb296b39545e2e8fb3816d2a61e73d524e368f3b3882142e3ca","observation_id":"ec5a4f11-f90d-43bd-ba8c-42ac9317ecb0","resolution":{"observed_at":"2026-08-06T18:39:52.715039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:52.405309Z","title":"Don’t decay the learning rate, increase the batch size","venue":null,"work_id":"c9c96119-bb7e-4541-a87b-b01fda114a5d","year":2018},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.683558Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:3b94f47cde3a4f0401c6bd1d2ca7917a55c0ab021e0e1b7572d58bf52bb4a1e9","observation_id":"3a18c318-9fcc-4246-8672-8a54379891f8","resolution":{"observed_at":"2026-08-06T18:39:52.507181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:52.202870Z","title":"Continual learning in the teacher-student setup: Impact of task similarity","venue":null,"work_id":"5dc899b6-2e14-4f22-b244-6ded12e78f9c","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.747483Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:311c1b459962c7e664ba300c63253e602d7b8c3c76bba4a321adfab7781afe3f","observation_id":"2aedaa07-b91c-413e-9a29-baa686cf8fa1","resolution":{"observed_at":"2026-08-06T18:39:52.284503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:39.809701Z","title":"How catas- trophic can catastrophic forgetting be in linear regression? InConference on Learning Theory, pages 4028–4079","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.809701Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:efba4ba4f6ad7e72e0272b3f4cef0be4acd2d1c9b67c98d00bd5a98aed07c0cc","observation_id":"c14331a8-7684-4f47-afef-fd2293af8acf","resolution":{"observed_at":"2026-08-06T18:39:39.809701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10315","last_updated":"2025-01-26T04:27:17Z","snapshot_observed_at":"2026-08-16T13:34:20.244967Z","submitted_at":"2024-07-14T20:22:36Z","title":"Order parameters and phase transitions of continual learning in deep neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10315","snapshot_observed_at":"2026-08-06T18:39:39.875669Z","title":"Order parameters and phase transitions of continual learning in deep neural networks.arXiv preprint arXiv:2407.10315, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.875669Z"},"links":{"cited_paper":"/paper/2407.10315","citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:5d1f7b0d33efc3f610d2465ea639e88c83251992ba19d4de41e7a2f0fa3fb939","observation_id":"e6c319e7-50f3-4aa4-a436-b51d324a83ea","resolution":{"observed_at":"2026-08-06T18:39:39.875669Z","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":"2026-08-06T18:39:52.015485Z","title":"Provable advantage of curriculum learn- ing on parity targets with mixed inputs","venue":null,"work_id":"b323c836-4eb5-4f59-9963-1f6e5bb68d1c","year":2023},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:39.941072Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:b449dbe26a882980b9d8adc5623e224d29b3b1e8a098f191a9892b89ff55650c","observation_id":"11d5977d-4ec7-4293-9992-cb062df1f4ed","resolution":{"observed_at":"2026-08-06T18:39:52.104731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:51.752336Z","title":"Restoring data balance via generative models of t-cell receptors for antigen-binding prediction.bioRxiv, pages 2024–07, 2024","venue":null,"work_id":"84b6fcaf-850d-4752-9eb0-12ab2c4b3d45","year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.026989Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:36d33587a3ec3b72fbd6aac3e67e93e8f1c2e4b1f80eedb75d03f66ede80f785","observation_id":"2a5483a1-e3b9-4011-bb3f-db4f63e3d885","resolution":{"observed_at":"2026-08-06T18:39:51.907605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:51.561570Z","title":"Bias-inducing geometries: exactly solvable data model with fairness implications","venue":null,"work_id":"550e537c-20e5-4fb7-8229-d80cf8a50469","year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.106104Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:2ab959ad87843d05b66d30163173bf088411e841b03911c91805c9ca09a18e70","observation_id":"320d9c14-234c-4bd5-977a-eb5bcde07cc6","resolution":{"observed_at":"2026-08-06T18:39:51.649899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:51.373251Z","title":"Bias in motion: Theoretical insights into the dynamics of bias in sgd training","venue":null,"work_id":"d9cc8af7-c80d-4d13-b3cd-f818d8a77a6b","year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.179025Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:42767f7ac7dab6135618e035aa9295565d9d9b9fbe4cf00d177e37805e47ce78","observation_id":"e6d109c5-9762-4929-b86f-0294b1ec16af","resolution":{"observed_at":"2026-08-06T18:39:51.476035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:40.240849Z","title":"Dropout: a simple way to prevent neural networks from overfitting.The journal of machine learning research, 15(1):1929–1958, 2014","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.240849Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:c80d868806799d3ed3595569da041066d8ff91c128b5de6ab6a27a71ddacfa4d","observation_id":"dcd81077-e14c-4a6a-89dc-0e939e936305","resolution":{"observed_at":"2026-08-06T18:39:40.240849Z","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":"2026-08-06T18:39:51.144163Z","title":"Curriculum dropout","venue":null,"work_id":"635fd5bb-9c9c-4078-bea9-865714f7d147","year":2017},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.312494Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:cea45fa3844c66cde60e86c923db618b7455327bf4c50fc925959e690c178e99","observation_id":"538afb0f-065c-400e-a146-1bc58b0226f7","resolution":{"observed_at":"2026-08-06T18:39:51.222926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:50.967932Z","title":"Dropout reduces under- fitting","venue":null,"work_id":"255e75c5-f293-4020-9a81-6ba2a1d6dacf","year":2023},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.370839Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:2828b406c329fb99e21533cc5d2e04a55c017b02630d2f1ded215b8b3357d6df","observation_id":"607a7d12-7da2-4552-9f2a-1c16f332b9f8","resolution":{"observed_at":"2026-08-06T18:39:51.060653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:50.796212Z","title":"Analytic theory of dropout regularization.Phys","venue":null,"work_id":"e7fa13b0-3522-4628-bbe7-fa9e8136aa62","year":2025},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.434947Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:aad8ea14d28914ce1e8a7a5e69d5158610a0b715c3b59dc0d8997a454ab2276e","observation_id":"51ceb9d1-f9ee-4d53-8e8a-b3cb791b24b2","resolution":{"observed_at":"2026-08-06T18:39:50.861781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:40.508200Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.508200Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:208b9a46df8a571628a68f323e8f8badb654c64ef462c2f1a8994ec7a877c9b9","observation_id":"6140ae34-ea7b-496d-92db-0a352f367168","resolution":{"observed_at":"2026-08-06T18:39:40.508200Z","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":"2026-08-06T18:39:50.626842Z","title":"Learning phrase representations using RNN encoder–decoder for statistical machine translation","venue":null,"work_id":"6a71a2a8-84be-4700-8261-c8f8994f7511","year":2014},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.577747Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:352c6a8c95be6af55ec836193240812c38dcdbc0b359568924010eb9044da5f1","observation_id":"5de31c2d-e066-4e91-b718-6ac9da08e044","resolution":{"observed_at":"2026-08-06T18:39:50.687588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:50.355721Z","title":"Gated linear networks","venue":null,"work_id":"df765f4e-5143-477a-a474-7ceff027fdc4","year":2021},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.626790Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:9a02975c6cd011e334a922f78f9c6cc58ab3d9df5e728417321b5628a2af77f6","observation_id":"17d4c5db-05c7-4a3b-a5f7-62d8ff77bdb1","resolution":{"observed_at":"2026-08-06T18:39:50.502074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:50.217442Z","title":"Globally gated deep linear networks.Advances in Neural Information Processing Systems, 35:34789–34801, 2022","venue":null,"work_id":"bb6bc083-4221-4a25-9ae5-6d8e3c795e96","year":2022},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.676027Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:973df1067f481bc36ec32a27c5fb05bb3087fc9f8797f5a46e01e6d918e014ba","observation_id":"23613871-7513-4824-a0f1-2086228c8d96","resolution":{"observed_at":"2026-08-06T18:39:50.274973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:50.056400Z","title":"The neural race reduction: Dynamics of abstraction in gated networks","venue":null,"work_id":"11c2dbf3-f021-4228-b25e-25ddc1035fa5","year":2022},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.739092Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:99c596de7b9d9e8f5f26725a941f7ea045567d230592eaebc62041b68db5060f","observation_id":"8316a1bd-b9c5-4840-9f6b-e319d5022bff","resolution":{"observed_at":"2026-08-06T18:39:50.127031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:49.898414Z","title":"Nonlinear classification of neural manifolds with contextual information.Physical Review E, 111(3):035302, 2025","venue":null,"work_id":"d81b2253-ef26-4e52-9e75-227bb4fd465e","year":2025},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.798765Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:794b804133fb4e794d86b6b7f43b519d19d35145e208fb4b4401b9ee595a28b1","observation_id":"c8888dbb-f764-4364-bfe2-a1df5aa6b25c","resolution":{"observed_at":"2026-08-06T18:39:49.957601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:40.868401Z","title":"Attention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.868401Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:68a6ae04beb7e77a2e56c8f3d582712d7764643c5f3a1317787035c8aa62afeb","observation_id":"6fc760d4-40aa-445b-8776-cd3025c1ef6e","resolution":{"observed_at":"2026-08-06T18:39:40.868401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:40.943435Z","title":"Efficient content-based sparse attention with routing transformers.Transactions of the Association for Computational Linguistics, 9:53–68, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:40.943435Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:ebbd71edbf2e60924b6c47b3f429d2f5fb4e4591605067fdecc9b0670c93f43f","observation_id":"a6ecd214-c1df-447a-9777-20e2154c23ee","resolution":{"observed_at":"2026-08-06T18:39:40.943435Z","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":"2026-08-06T18:39:49.725651Z","title":"Adaptive atten- tion span in transformers","venue":null,"work_id":"ca64d697-5139-401e-9968-63de581a3ca6","year":2019},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.034785Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:6ed4be6c3c44f337fd89acdc61fa74ec2cd8b9243e5f556c1596c6a4ceaf8c61","observation_id":"6dfaa829-cd7f-442b-92cd-a45c03418a9f","resolution":{"observed_at":"2026-08-06T18:39:49.779690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:41.097955Z","title":"Are sixteen heads really better than one?Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.097955Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:9b1408a0d5d0c5d95578ee193b05658ec97eaf770a5a6d5b015f948a840b22a5","observation_id":"dbe94e78-2aaa-424b-a747-179edcd0cdb8","resolution":{"observed_at":"2026-08-06T18:39:41.097955Z","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":"2026-08-06T18:39:49.492053Z","title":"The effects of information order and learning mode on schema abstraction.Memory & cognition, 12(1):20–30, 1984","venue":null,"work_id":"5530d6f3-8817-4fc9-a576-598b3f18806c","year":1984},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.173408Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:431c12081283b2537ceaf8e350e52909fd3561b2336f11d8c1fb8ce9ed7ffea1","observation_id":"1c6716b1-6ac6-4d12-9d27-3abf771821fa","resolution":{"observed_at":"2026-08-06T18:39:49.615918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:49.292705Z","title":"When does fading enhance perceptual category learning? Journal of Experimental Psychology: Learning, Memory, and Cognition, 39(4):1162, 2013","venue":null,"work_id":"48fe9154-1156-4ec0-a1a4-37b16f0abbf6","year":2013},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.252558Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:fd86c872d49fa4546567590e833cd48495e97ad76fe123c695b25b19391cfdfe","observation_id":"baa6e266-40be-47a4-85d0-b0e451067fcc","resolution":{"observed_at":"2026-08-06T18:39:49.362898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:41.339550Z","title":"Curriculum learning","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.339550Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:ebfed226e55dae2b6164c431da3211554c968d83854bb67ba877133ad3411e58","observation_id":"4b2db901-1f1d-4894-bf0f-0e9857e09656","resolution":{"observed_at":"2026-08-06T18:39:41.339550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:41.395215Z","title":"A survey on curriculum learning.IEEE transactions on pattern analysis and machine intelligence, 44(9):4555–4576, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.395215Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:f65dd5bf5562d49df454a4b2846162b6351cf4685083060da03cb0ce3c9236ce","observation_id":"c1ba915b-b44d-4ab4-971e-d262f5fbcba4","resolution":{"observed_at":"2026-08-06T18:39:41.395215Z","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":"2026-08-06T18:39:49.071482Z","title":"On the power of curriculum learning in training deep networks","venue":null,"work_id":"0fa7c1ef-e30a-4396-98b4-60b8b7cdc679","year":2019},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.517224Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:47f0fa000ba6b275a700ee298d65a780906ccd7f8aa5e1fa0e3b9dec84d0a2e4","observation_id":"9498c7bb-2b60-4853-a3c3-ff384c817cc5","resolution":{"observed_at":"2026-08-06T18:39:49.159581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:48.957625Z","title":"When do curricula work? InInternational Conference on Learning Representations, 2021","venue":null,"work_id":"874d66e0-60a7-4a9a-a74d-cc536b6b108d","year":2021},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.616993Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:a72b6473920efb4d6b5535b291d4d31d3b835fe6c20f193e05e1f906af1e5c2e","observation_id":"bf678ef4-9b42-46d8-9c67-cc00b275df85","resolution":{"observed_at":"2026-08-06T18:39:49.023007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:48.834625Z","title":"Theory of curriculum learning, with convex loss functions","venue":null,"work_id":"3956d647-2c5b-4ba0-b566-75072e351243","year":2020},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.704001Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:8bc67f4c3951e58141864eb0ab5fd72cc632001cca1ed467f8abe88080a6ec94","observation_id":"18e144f6-6b0b-47fe-81f5-d9722b119d36","resolution":{"observed_at":"2026-08-06T18:39:48.887455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:48.701850Z","title":null,"venue":null,"work_id":"d3bae9b9-4e28-47af-9df3-3543b73cf6c7","year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.824329Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:27a40412d1721e12c449b6fdbf7f21f744938950ba067bab1a17bdc2b28f0d0c","observation_id":"2a18e7ce-4785-4060-b52e-e7469709107b","resolution":{"observed_at":"2026-08-06T18:39:48.745524Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:48.558949Z","title":"Curriculum learning by optimizing learning dynam- ics","venue":null,"work_id":"5f0d1b5f-5d04-4a46-9016-3ac1f55e3c89","year":2021},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:41.918014Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:394c608121798fb2d2e7247abcaa86c30a448fb46f70c22bddf2eb850e253f81","observation_id":"294fba1d-ef4d-476f-88c3-937ad5604d3a","resolution":{"observed_at":"2026-08-06T18:39:48.620820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:48.398184Z","title":"Rennie, Vaibhava Goel, and Samuel Thomas","venue":null,"work_id":"b5a8b895-56cc-4f75-9cea-46c31dd623b4","year":2014},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.038549Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:6eb92c1ee88940783f551f8124bddb595ef2f5b03de79283190155a0f1c49ba8","observation_id":"15407a7a-1f06-4e1d-804d-c1fb58140c43","resolution":{"observed_at":"2026-08-06T18:39:48.433448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:48.240584Z","title":"Extracting and composing robust features with denoising autoencoders","venue":null,"work_id":"84d11c66-fed0-434e-b54b-ef2befb6f472","year":2008},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.154847Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:b34d45e9c4e8c72c74dfd3685e0d1dfcaae2fc7f42b54ed313454015b0550230","observation_id":"0e0b0eec-91bb-4204-b93b-00053f386750","resolution":{"observed_at":"2026-08-06T18:39:48.283751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:39:42.280382Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.280382Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:29ce08ef4e67b23bd0c8c5e57bf6165e329c227d9bfb13d253618d3107e69f6d","observation_id":"0edaf180-9986-44f7-b8c5-894d63ab8c11","resolution":{"observed_at":"2026-08-06T18:39:42.280382Z","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":"2026-08-06T18:39:48.054372Z","title":"Learning dynamics of linear denoising au- toencoders","venue":null,"work_id":"66e7c98e-0db0-423a-ae32-c02484421c14","year":2018},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.393848Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:dbb95b28df1e498c8af201d9901c2825f09e4ddd4d060dc9eb1310c85d333631","observation_id":"110e0016-9c47-4476-a2fd-81d6369c485c","resolution":{"observed_at":"2026-08-06T18:39:48.147690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.889897Z","title":"High-dimensional asymptotics of denoising autoencoders.Ad- vances in Neural Information Processing Systems, 36:11850–11890, 2023","venue":null,"work_id":"9c2fb7d3-8029-4e57-aad0-3da4d9c49902","year":2023},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.518648Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:09ebcf9660180567c8e8fed95383d1c28424e498214e05774f23b6fd8116f6e8","observation_id":"61128815-a93e-4f82-b686-8b7c7bd73b59","resolution":{"observed_at":"2026-08-06T18:39:47.991457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.777006Z","title":"A solvable model of learning generative diffusion: theory and insights.Advances in Neural Information Processing Systems, 38:5253–5296, 2026","venue":null,"work_id":"d221308a-2831-4611-abd1-10084718afa4","year":2026},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.633370Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:addf803fd9741dc418e43be8dd1bd669971aad93f2ccef256cc181aa7a5b8b85","observation_id":"f4bf8ce0-a759-43c8-861f-4defec3a0c28","resolution":{"observed_at":"2026-08-06T18:39:47.820017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.640352Z","title":"Geras and Charles Sutton","venue":null,"work_id":"54ac36df-6a2c-43fe-9ac7-1eea2db49ecf","year":2015},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.726970Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:103f7c5b9f974bacfcfe1f05356647bf60c4f0f1816e955f24a18b39effb9265","observation_id":"200773d0-0722-41d5-ab0a-596c529269c1","resolution":{"observed_at":"2026-08-06T18:39:47.688160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.538014Z","title":"Non-uniform timestep sampling: Towards faster diffusion model training","venue":null,"work_id":"335d758c-e988-444a-b6ee-c0b100c8f0e7","year":2024},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.811578Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:c8c804a8f848fa7f111a70dcf4eea2023e106369021082563587ccdaac854c75","observation_id":"c01921b0-d2c3-4c48-9496-f01b4fd9dacb","resolution":{"observed_at":"2026-08-06T18:39:47.594273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.419823Z","title":"Marginalized denoising auto- encoders for nonlinear representations","venue":null,"work_id":"504b33a3-7fa5-479f-a739-a9911db5759e","year":2014},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:42.922180Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:6a255a02b7ed541b7b287e4fd5e5c8b93380d625c542e97b4746c6aa2919f859","observation_id":"ce968619-6731-4813-b25b-bcf84f996514","resolution":{"observed_at":"2026-08-06T18:39:47.440290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.345806Z","title":"Modeling the influence of data structure on learning in neural networks: The hidden manifold model.Physical Review X, 10(4):041044, 2020","venue":null,"work_id":"d969f486-56a7-4b7e-b565-d306c89be8b7","year":2020},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.018635Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:0e2f5e35e360116e4dfd9b580ee310cc9177903d64cb358c07cecfa885ab613c","observation_id":"2910953f-2e6c-45a2-89f5-a5361f93c10b","resolution":{"observed_at":"2026-08-06T18:39:47.386593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.215202Z","title":"Classification of heavy-tailed features in high dimensions: a superstatistical approach","venue":null,"work_id":"b0887323-145f-4da1-9829-93c790937694","year":2023},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.107114Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:7c1e9e79320db8e11f24e0d6664079fbbdacf848328360ae77fc987f19a05812","observation_id":"aefd29e1-dc19-43bf-8fdd-62a6a03d64a1","resolution":{"observed_at":"2026-08-06T18:39:47.258091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:47.091351Z","title":"Wakhloo, Tamara J","venue":null,"work_id":"b4062e04-8d3c-4de1-9b83-e2a0be1ba649","year":2023},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.220206Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:9a2e045ee8ea1a6a46cb71337064a348400896b1f3c95c95d584b76a147f230b","observation_id":"7b010d21-1895-4ea0-8d82-3cdccc35e717","resolution":{"observed_at":"2026-08-06T18:39:47.126682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.19644","last_updated":"2025-07-25T19:34:35Z","snapshot_observed_at":"2026-08-17T18:02:32.233346Z","submitted_at":"2025-07-25T19:34:35Z","title":"Hierarchical clustering and dimensional reduction for optimal control of large-scale agent-based models","version":1},"cited_work":{"arxiv_id":"2507.19644","doi":null,"metadata_source":"pith","pith_arxiv_id":"2507.19644","snapshot_observed_at":"2026-08-06T18:39:44.668560Z","title":"Hierarchical clustering and dimensional reduction for optimal control of large-scale agent-based models","venue":"math.OC","work_id":"b5baf479-fde8-45bc-aa3e-8dd266a0e76e","year":2025},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.341374Z"},"links":{"cited_paper":"/paper/2507.19644","citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:64203f00e961c0ce8ffa0b63b421bcac2840057e894bdb3370d0a73a1662c85d","observation_id":"30545258-c068-4a1b-8c4b-1a8b0f234001","resolution":{"observed_at":"2026-08-06T18:39:44.876307Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.961899Z","title":"Some mathematical problems arising in connection with the theory of optimal au- tomatic control systems","venue":null,"work_id":"53e3bb63-070e-42b7-9910-fc64428fd161","year":1957},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.416490Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:58998f51718c12997d58ea7e238f97ff12d1605944c5c66d580aac05e797e6cd","observation_id":"3e1593d8-677b-4137-b4c1-aade41f72657","resolution":{"observed_at":"2026-08-06T18:39:47.019611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.855674Z","title":"Casadi: a software framework for nonlinear optimization and optimal control.Mathematical Programming Computation, 11:1–36, 2019","venue":null,"work_id":"6c21a375-f067-45e8-8b1d-9207e8cd3092","year":2019},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.507966Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:3a8ee29e4dce2241cac785041dbc9c1a870eee51a680e6a795ad998d7f79336f","observation_id":"adbb0dba-1874-44a2-86b3-9135c9391f32","resolution":{"observed_at":"2026-08-06T18:39:46.913846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.720220Z","title":"training time","venue":null,"work_id":"05dc7082-b62f-426f-8c43-f33b3ef6c101","year":2025},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.608880Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:890f6e18c79bfe77b175ec2bb200332117df3fa3ae7aafb131d6b66c31f9e2ec","observation_id":"b199d466-69e9-4813-9fc9-b1c5b9e5cde3","resolution":{"observed_at":"2026-08-06T18:39:46.784038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.624176Z","title":null,"venue":null,"work_id":"8c0f4394-0cb7-4398-ab44-0615ab3e617f","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.743647Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:98230aadd3dc4bdc5dc42f2620993ab281ea54da6945d191d8e133fddb62729c","observation_id":"af963b0e-fd76-4152-be97-1b3a6528f2f0","resolution":{"observed_at":"2026-08-06T18:39:46.681522Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.491063Z","title":null,"venue":null,"work_id":"39a55409-a1b4-4893-b468-b65219a7641c","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.867005Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:d4f76c542b942e7a900d944a4ac4e08b879b1b8ef8a5920759ed5620a72c7328","observation_id":"e44eb0cb-b26f-4db0-ba51-4d2df4eb1536","resolution":{"observed_at":"2026-08-06T18:39:46.548044Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.371202Z","title":null,"venue":null,"work_id":"fa10e873-6ec7-4ea3-9b7e-a42aeabdc170","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:43.988866Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:2af6833b4880defd28f8133ce47948fbe11a8150d52d2ff1a5a21dc3e1f86c77","observation_id":"2be27758-0ade-4d3a-a750-4890e34a2ea0","resolution":{"observed_at":"2026-08-06T18:39:46.417450Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.248999Z","title":null,"venue":null,"work_id":"892503f7-54ef-484b-8f91-a102ee69f9ad","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.106634Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:b6c8c7e862b563c98acbe2b5904ba6b5b02d42585a57646b5b15a5d0e49c29fb","observation_id":"fe6c4fc1-5a08-4caf-b2ca-6e1bdb5700fc","resolution":{"observed_at":"2026-08-06T18:39:46.294812Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:46.083413Z","title":null,"venue":null,"work_id":"ec83c61b-8326-45b9-92be-b11ba14f9351","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.230407Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:0b35a9895973837dabd38ebb63c8f416c8bceea30f39379f8ab0ed7a6674769f","observation_id":"6a8acd41-21fd-42d6-bbe3-672d85516348","resolution":{"observed_at":"2026-08-06T18:39:46.186570Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:45.983253Z","title":null,"venue":null,"work_id":"2d7abf28-1434-4278-9eda-f749011de41e","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.327050Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:a390fbb884dec8368087c37a839b4b4aa2bd7c945a305b3b8a67a8bc7ad6730b","observation_id":"4c114b19-0231-43e0-b9f1-2ef556e3654f","resolution":{"observed_at":"2026-08-06T18:39:46.043042Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:45.853823Z","title":null,"venue":null,"work_id":"c187fcfb-f7ed-4a1f-9725-08e1f76dd737","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.408632Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:6bcf881d29fc811764082634cc005518ace0d01712e42bb6bdeb91e97a6bc7fc","observation_id":"1c6f30cc-62c7-4340-a09a-88c8ce9801d2","resolution":{"observed_at":"2026-08-06T18:39:45.894187Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:45.736233Z","title":null,"venue":null,"work_id":"07434975-908e-490d-877e-2f017bc229e2","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.455229Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:f57883aa54a58409049c4aec642c7f14d02a2a1bdd9bc224e5f6e3bdfdac59e1","observation_id":"8784a780-b126-4670-9859-70f4b9028ab2","resolution":{"observed_at":"2026-08-06T18:39:45.779867Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:45.576458Z","title":null,"venue":null,"work_id":"0c148ec2-8124-4470-a95f-e4e6424803e5","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.493638Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:187563e9ce59221c4e52f7a03a43326cdce8164ed5062d1d5e2041e84f6ec488","observation_id":"ff6fc80c-f053-4ba9-a721-afb5321064e0","resolution":{"observed_at":"2026-08-06T18:39:45.664158Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:45.357388Z","title":null,"venue":null,"work_id":"3a44bf40-f460-4b8f-b946-5491c881b919","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.537064Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:54fa27e593dd9bc1eb8369e3809c5368d91e11918057937c01027d9efd03844b","observation_id":"0d7b4d1e-0331-4f24-9fcb-83f3ecd6f128","resolution":{"observed_at":"2026-08-06T18:39:45.508078Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T18:39:45.242561Z","title":"We typically choose the damping parameterγ damp >0.9","venue":null,"work_id":"4205f4c8-4ace-4315-8323-0bd7c9be64db","year":null},"citing_paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T18:39:44.587149Z"},"links":{"citing_paper":"/paper/2507.07907"},"observation_digest":"sha256:f6fdf81ad859e27316f675d1600e15b825ddf1e6522c0a803112cfcde7b700c5","observation_id":"8b114ec7-8a9c-4d89-8fa3-4a01e983e5e8","resolution":{"observed_at":"2026-08-06T18:39:45.283472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.07907","last_updated":"2026-06-22T15:49:10Z","latest_version":2,"primary_category":"cond-mat.dis-nn","snapshot_observed_at":"2026-08-16T15:37:35.648099Z","submitted_at":"2025-07-10T16:39:46Z","title":"A statistical physics framework for optimal learning"},"reference_resolution":{"displayed":91,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":2,"verified_fuzzy":51},"total_outbound_references":91},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 91 of 91 outbound references and 2 inbound Pith citation observations for arXiv:2507.07907."}