{"as_of":"2026-08-09T13:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:302d60435723d3411e66b73b445386883fdea76c5a0ac24e1e9f8741e1a9f188","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T14:57:06.132639Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.22553/citation-record","integrity":"/paper/2509.22553/integrity","json":"/paper/2509.22553/citation-record.json","paper":"/paper/2509.22553"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-07-06T18:03:47.096406Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14219","snapshot_observed_at":"2026-08-04T14:57:05.967802Z","title":"Phi-3 technical report: A highly capable language model locally on your phone","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.967802Z"},"links":{"cited_paper":"/paper/2404.14219","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:14803f0cb12ccfb550bec794ae7b6af9b101c01cd12ccaaa39aea7d86e01f23f","observation_id":"d237b6d7-cb0a-403f-83f5-af2ffc67ee4d","resolution":{"observed_at":"2026-08-04T14:57:05.967802Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-04T14:57:05.971542Z","title":"GPT -4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.971542Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:fbc4f5df2fdadf2ac5e20f8ba940c09f3b5b7389d90e0c8c951a6e3bb9f147ba","observation_id":"6ba09028-70f1-46ed-9b4d-7180c385b2bb","resolution":{"observed_at":"2026-08-04T14:57:05.971542Z","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":"2026-08-04T14:57:05.975083Z","title":"Interventional causal representation learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.975083Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:1c0fb411f82d56046ab2fd1cc6130f9e2aee9f237245981dc508c6fcf33b4980","observation_id":"bc50ede7-2b82-4ef7-95a8-9da9819c953d","resolution":{"observed_at":"2026-08-04T14:57:05.975083Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13673","last_updated":"2025-05-19T11:12:27Z","snapshot_observed_at":"2026-08-08T23:24:12.994765Z","submitted_at":"2023-05-23T04:28:16Z","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13673","snapshot_observed_at":"2026-08-04T14:57:05.979008Z","title":"Physics of language models: Part 1, learning hierarchical language structures","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.979008Z"},"links":{"cited_paper":"/paper/2305.13673","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:386ae59c4534a66f9f8009e600f9e9b52a991c20e8e3537c339b926a2a721f63","observation_id":"33624871-afa5-4a19-8ecf-49759c3a92c3","resolution":{"observed_at":"2026-08-04T14:57:05.979008Z","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":"2026-08-04T14:57:05.982393Z","title":"A latent variable model approach to PMI -based word embeddings","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.982393Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:dc57e5fb0efb07bc20dbc556bee2cd6096a04a6f3c2322f2b3dd84c852d6f9c1","observation_id":"5151b62b-802f-499d-893b-9859f89afc5a","resolution":{"observed_at":"2026-08-04T14:57:05.982393Z","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":"2026-08-04T14:57:05.985435Z","title":"GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow , March 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.985435Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:07e238919275d7ee482ad10bdd45e44e256374896e08808c6cd0f2187924a3b1","observation_id":"ca71de8e-8931-426c-bdee-dca8d9c29bfb","resolution":{"observed_at":"2026-08-04T14:57:05.985435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12712","last_updated":"2023-04-13T20:41:31Z","snapshot_observed_at":"2026-08-03T04:49:15.195814Z","submitted_at":"2023-03-22T16:51:28Z","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.12712","snapshot_observed_at":"2026-08-04T14:57:05.989293Z","title":"Sparks of artificial general intelligence: Early experiments with GPT -4","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.989293Z"},"links":{"cited_paper":"/paper/2303.12712","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:79a94a6fdd334e6c383cf7cd74ad1b9a2d3fc9c9c60cbda50c28b057cf9bf2ac","observation_id":"0d933759-5271-4a22-8098-4f33aa5cd61f","resolution":{"observed_at":"2026-08-04T14:57:05.989293Z","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":"2026-08-04T14:57:05.992766Z","title":"Learning linear causal representations from interventions under general nonlinear mixing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.992766Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:f4b9ee26e82761150a469dbe589f5124ee9d20e45e6ce5db566f74e3bf82904a","observation_id":"65b9d872-7d4c-4fa0-8125-66c04b322445","resolution":{"observed_at":"2026-08-04T14:57:05.992766Z","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":"2026-08-04T14:57:05.995730Z","title":"Invariance, causality and robustness","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.995730Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:1ca6ce157dad1278b10bdc27551af7b68c96fa624830c562a09c244c59444980","observation_id":"3bbbcdf8-f172-4dc9-8dd9-350d19f3b1e4","resolution":{"observed_at":"2026-08-04T14:57:05.995730Z","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":"2026-08-04T14:57:05.998967Z","title":"Causal inference of general treatment effects using neural networks with a diverging number of confounders","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:05.998967Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:85eaac9cb70130d48a356dc45b5ce3dca71ea49cdce007f0a0c479dfb19bed1a","observation_id":"c371356b-740b-4ded-baf9-be2a53cd9e84","resolution":{"observed_at":"2026-08-04T14:57:05.998967Z","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":"2026-08-04T14:57:06.002371Z","title":"Independent component analysis, a new concept? Signal Processing, 36 0 (3): 0 287--314, 1994","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.002371Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:dfaf9aabc625bd9709870f74de5e116f68c43677a6b3f878d1d8e27f8c9aca0c","observation_id":"af4cb13a-71f8-4401-861b-1b457b84165e","resolution":{"observed_at":"2026-08-04T14:57:06.002371Z","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":"2026-08-04T14:57:06.006173Z","title":"Analyse g \\'e n \\'e rale des liaisons stochastiques: etude particuli \\`e re de l'analyse factorielle lin \\'e aire","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.006173Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:3bc05f8629fe491fd34221c74e1ad6c326135997c20296a92e9a0ba3a10d3597","observation_id":"a1967e33-87b1-4e63-9526-19f87148a882","resolution":{"observed_at":"2026-08-04T14:57:06.006173Z","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":"2026-08-04T14:57:06.009556Z","title":"Identifying the consequences of dynamic treatment strategies: A decision theoretic overview","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.009556Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:82191bdc4e1618d14199107f805211a2adb88e9029c36429027e0c2ef83f2457","observation_id":"a6540e20-9497-41a1-982e-0ef448e4e044","resolution":{"observed_at":"2026-08-04T14:57:06.009556Z","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":"2026-08-04T14:57:06.012873Z","title":"On random graphs","venue":null,"work_id":null,"year":1959},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.012873Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:830423d98fae28c6e42034e2a1c79aa278a78eee7c18fbeb7684be9f36f22109","observation_id":"45b5f90d-5971-4ec3-a040-e08be84ddc78","resolution":{"observed_at":"2026-08-04T14:57:06.012873Z","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":"2026-08-04T14:57:06.016328Z","title":"Causal disentanglement for single-cell representations and controllable counterfactual generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.016328Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:db10536b7167dfdd807295a1d670694bb1352ec3f936fb0df5c3c3275d8b739e","observation_id":"4b60dd83-c319-4a65-bb71-a9c59719ae0e","resolution":{"observed_at":"2026-08-04T14:57:06.016328Z","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":"2026-08-04T14:57:06.019785Z","title":"Measuring statistical dependence with hilbert-schmidt norms","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.019785Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:fce86ff7c88ec79f4f53cde7154a8d3bebcdf10962a68f37a43a68ad3c87a30d","observation_id":"035c92f0-e1e4-4fc4-a860-965ffd7b2970","resolution":{"observed_at":"2026-08-04T14:57:06.019785Z","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":"2026-08-04T14:57:06.022932Z","title":"Independent component analysis: Algorithms and applications","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.022932Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:9609c22c5161204d0722222cab6c3ccd175e481bf5d2029e4a243ea1f1c7ad10","observation_id":"897d0d3d-2bab-4bdf-9c97-69d320b422e8","resolution":{"observed_at":"2026-08-04T14:57:06.022932Z","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":"2026-08-04T14:57:06.026206Z","title":"Learning causal representations from general environments: Identifiability and intrinsic ambiguity","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.026206Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:d4b736c303fc824d552c2bbc3ed884d4115fca6668c5f5cb537865c27273cdd2","observation_id":"c2d29d32-c349-4927-b84d-5a807a193cfb","resolution":{"observed_at":"2026-08-04T14:57:06.026206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.19335","last_updated":"2025-02-03T17:24:50Z","snapshot_observed_at":"2026-07-06T20:29:07.258163Z","submitted_at":"2025-01-31T17:35:21Z","title":"What is causal about causal models and representations?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.19335","snapshot_observed_at":"2026-08-04T14:57:06.029184Z","title":"What is causal about causal models and representations? arXiv preprint arXiv:2501.19335, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.029184Z"},"links":{"cited_paper":"/paper/2501.19335","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:3d20bf8b7cbc4b8c2217f5eb22417d8579c8bebd19ea8fce10d350e53bc3e29d","observation_id":"ea65090f-e8fc-4c36-b735-07b47362ef54","resolution":{"observed_at":"2026-08-04T14:57:06.029184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.00050","last_updated":"2024-08-20T17:16:20Z","snapshot_observed_at":"2026-07-06T15:21:19.790554Z","submitted_at":"2023-04-28T19:00:43Z","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.00050","snapshot_observed_at":"2026-08-04T14:57:06.033343Z","title":"Causal reasoning and large language models: Opening a new frontier for causality","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.033343Z"},"links":{"cited_paper":"/paper/2305.00050","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:e4da3f96ec32f644a1036f01bd9bf7b6d688ba75e5d92071458096dcbdeeb5aa","observation_id":"ed244df1-27b3-46f3-9058-653445eb3658","resolution":{"observed_at":"2026-08-04T14:57:06.033343Z","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":"2026-08-04T14:57:06.036643Z","title":"Optimality of the J ohnson- L indenstrauss lemma","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.036643Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:7b805ab60effff8a7fbf6529cee48269e8605bd383117166f7ae6e649068f881","observation_id":"f1fd01ba-1319-4c2b-8d9f-f579f05fa5d5","resolution":{"observed_at":"2026-08-04T14:57:06.036643Z","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":"2026-08-04T14:57:06.040221Z","title":"Factor analysis as a statistical method","venue":null,"work_id":null,"year":1962},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.040221Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:bb755b1a4f473cdcad0a058750208ca9a6469fcc29b0ac58ac5d84b5e3b74174","observation_id":"87155193-dedd-415a-9f38-af9e65d38e06","resolution":{"observed_at":"2026-08-04T14:57:06.040221Z","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":"2026-08-04T14:57:06.043390Z","title":"Causal estimation of memorisation profiles","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.043390Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:ad46e8e2c046ef5026dfd36cd24281337288797fb641af14566abcbe184d072f","observation_id":"b92a8f1a-da94-44be-ac96-00fbf2fd53e6","resolution":{"observed_at":"2026-08-04T14:57:06.043390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-04T14:57:06.046867Z","title":"Deep S eek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.046867Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:daa78955047eedc0cce43c35d1af707a3fb98dbc81de056c936f74000806684b","observation_id":"305d73f4-0a5d-4ce1-be6c-5ae1d70f78b4","resolution":{"observed_at":"2026-08-04T14:57:06.046867Z","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":"2026-08-04T14:57:06.050290Z","title":"The Llama 3 family of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.050290Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:c675d0c108b2987cbc9057a9471fbaa42d727b9bec23dd9d14492a2ffb9a2250","observation_id":"2ed4928f-4360-44e1-bcf8-05e592929f33","resolution":{"observed_at":"2026-08-04T14:57:06.050290Z","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":"2026-08-04T14:57:06.053346Z","title":"Fourth moments and independent component analysis","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.053346Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:18a58c5cff7e874b177a8bba818ba3cb8e9f4142aa1f1d8ed91134179cee4e2b","observation_id":"7da37483-bcc9-4746-8bf6-62d7e0a1d009","resolution":{"observed_at":"2026-08-04T14:57:06.053346Z","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":"2026-08-04T14:57:06.056706Z","title":"Linguistic regularities in continuous space word representations","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.056706Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:32d8948f57023383ce98d71a26edc8efddf488fe6cba43de21dd75486bfcfcd1","observation_id":"4f4d0875-fb86-4533-906b-9be389370489","resolution":{"observed_at":"2026-08-04T14:57:06.056706Z","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":"2026-08-04T14:57:06.060151Z","title":"Determining the number of factors from empirical distribution of eigenvalues","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.060151Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:d1bce6a26791444b13a09ccab2d7a13ed62ee123cc8895120a6aa096ae8bf4e3","observation_id":"e15c5264-3451-4094-80ce-25295576313c","resolution":{"observed_at":"2026-08-04T14:57:06.060151Z","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":"2026-08-04T14:57:06.063143Z","title":"The linear representation hypothesis and the geometry of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.063143Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:b86343e13139c33b867aa678dae7ee9525d6e43b003c8ff6eb36a98ee52e21dc","observation_id":"50067741-3a91-4eb5-ae9d-af68632c60ea","resolution":{"observed_at":"2026-08-04T14:57:06.063143Z","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":"2026-08-04T14:57:06.066089Z","title":"Automatic differentiation in PyTorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.066089Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:8aeeb1ac35f86ff9f96eef2d40f2290f3f2cd2f4f0873472f6cd5ab7a37c506f","observation_id":"5a87c866-3c42-4bff-b8f8-00cf501a623a","resolution":{"observed_at":"2026-08-04T14:57:06.066089Z","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":"2026-08-04T14:57:06.068930Z","title":"Elements of causal inference: foundations and learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.068930Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:70ac35aaa5fa2bc2913b4c5c1adeabf4184c5a9c0369cc36f9c33d9395934e07","observation_id":"c28b0a56-5fec-44e1-84a0-51715b4940b8","resolution":{"observed_at":"2026-08-04T14:57:06.068930Z","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":"2026-08-04T14:57:06.071806Z","title":"From causal to concept-based representation learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.071806Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:58b144f5e1820033f3d3cad2cc109d6efa06097e588c49794564452ff883445f","observation_id":"8b80538e-0907-498a-a770-99e0fc306cbc","resolution":{"observed_at":"2026-08-04T14:57:06.071806Z","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":"2026-08-04T14:57:06.074783Z","title":"Consistency and asymptotic normality of FastICA and bootstrap FastICA","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.074783Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:28814a133993007a39aaa41e754df4f543f3ff8675def0b56ed637a049484e53","observation_id":"94f51811-81cd-4c6a-b5b7-1ceaf70fd6ec","resolution":{"observed_at":"2026-08-04T14:57:06.074783Z","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":"2026-08-04T14:57:06.077596Z","title":"a us Kleindessner, Chris Russell, Dominik Janzing, Bernhard Sch \\","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.077596Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:31f44ef50afec29b92e78876e57c7141807965e76c3717c777b76f574fe5716a","observation_id":"6b3ca4b9-ff29-42f4-ab2c-c6f31e6e6bc2","resolution":{"observed_at":"2026-08-04T14:57:06.077596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.05100","last_updated":"2023-06-27T09:57:58Z","snapshot_observed_at":"2026-08-04T18:56:03.233715Z","submitted_at":"2022-11-09T18:48:09Z","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.05100","snapshot_observed_at":"2026-08-04T14:57:06.080466Z","title":"BLOOM : A 176b-parameter open-access multilingual language model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.080466Z"},"links":{"cited_paper":"/paper/2211.05100","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:c08553bec0f4503367dbf3896fb1899323a608ed9449e86a7f244d9f870378be","observation_id":"d1a5245f-bbc2-479b-957f-95ee02d21e54","resolution":{"observed_at":"2026-08-04T14:57:06.080466Z","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":"2026-08-04T14:57:06.083877Z","title":"Toward causal representation learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.083877Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:5900834eb1b60a32f8852c5cc005599bca71d5861e47e57f5fbbcecae4d5cd95","observation_id":"91334cdd-08c6-4afa-adaa-75e7182a7a44","resolution":{"observed_at":"2026-08-04T14:57:06.083877Z","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":"2026-08-04T14:57:06.086852Z","title":"On a property of the normal distribution","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.086852Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:a9eebd6e28919074cf24a5b490b51fafddbc0c1d88caa380f6be6980667f2a95","observation_id":"e3aee7a0-4bad-4705-b3f7-f0eabbbcf400","resolution":{"observed_at":"2026-08-04T14:57:06.086852Z","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":"2026-08-04T14:57:06.089890Z","title":"Causal temporal representation learning with nonstationary sparse transition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.089890Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:e87c1f166d4d67a7c03be5642951ec0e923839c35bfd5b18868080915d87a446","observation_id":"4014a7ad-6a0c-43d0-a1b1-9cfef787c39e","resolution":{"observed_at":"2026-08-04T14:57:06.089890Z","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":"2026-08-04T14:57:06.092862Z","title":"Linear causal disentanglement via interventions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.092862Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:2179bc64009f472fb5a62de215d5f19300c0dc7435362f0d5fe14e1d035b4ac5","observation_id":"1aa24e5b-c2b3-480c-b117-5ac80d9a1d5f","resolution":{"observed_at":"2026-08-04T14:57:06.092862Z","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":"2026-08-04T14:57:06.095848Z","title":"Causal representation learning from multimodal biomedical observations","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.095848Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:fc5b100aa4abc7f3095764ddbcf2b362cf2385395f18df8df593cb4f121eefdd","observation_id":"d43993c5-dcdb-46fd-8680-77fed4e2bda3","resolution":{"observed_at":"2026-08-04T14:57:06.095848Z","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":"2026-08-04T14:57:06.098908Z","title":"Score-based causal representation learning from interventions: Nonparametric identifiability","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.098908Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:22fb7159706a94d3ad096459b66c6f25805b4054116698ec6147cb6df8f450a6","observation_id":"c86e53e9-13a9-4a1a-902f-c523f5e33e2f","resolution":{"observed_at":"2026-08-04T14:57:06.098908Z","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":"2026-08-04T14:57:06.101862Z","title":"General identifiability and achievability for causal representation learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.101862Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:3499ab2093b1d3caf883e866bb98a79ef89886d302b22bf642394942935af3e5","observation_id":"25e28b86-e45d-42c4-ad41-ce6fd92aba00","resolution":{"observed_at":"2026-08-04T14:57:06.101862Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05937","last_updated":"2024-12-05T03:16:26Z","snapshot_observed_at":"2026-07-06T18:27:54.379381Z","submitted_at":"2024-06-09T23:56:49Z","title":"Linear Causal Representation Learning from Unknown Multi-node Interventions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05937","snapshot_observed_at":"2026-08-04T14:57:06.104962Z","title":"Linear causal representation learning from unknown multi-node interventions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.104962Z"},"links":{"cited_paper":"/paper/2406.05937","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:d685fc9f06cf53e9b508e8ea7373c782140ac5c97a464869ced13c30643cd2f2","observation_id":"d484b82a-2fb6-417b-a08d-3a110d4680cf","resolution":{"observed_at":"2026-08-04T14:57:06.104962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00849","last_updated":"2025-07-19T22:38:11Z","snapshot_observed_at":"2026-08-07T22:04:53.932904Z","submitted_at":"2024-02-01T18:40:03Z","title":"Score-based Causal Representation Learning: Linear and General Transformations","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00849","snapshot_observed_at":"2026-08-04T14:57:06.108333Z","title":"Score-based causal representation learning: Linear and general transformations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.108333Z"},"links":{"cited_paper":"/paper/2402.00849","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:3e6d4dc83e88c84eae2323c16947ea4b1debfaaed4037f6b463a9637b474f259","observation_id":"01dbb8e7-a9af-4ed5-be30-822cf3676ff7","resolution":{"observed_at":"2026-08-04T14:57:06.108333Z","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":"2026-08-04T14:57:06.111302Z","title":"Dimension reduction via adaptive slicing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.111302Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:3293cb5146609329db7570a5c428f5095f2588d64d6d05ec810be31ee9e82240","observation_id":"ee664493-0939-46f8-9ea9-731b573140ba","resolution":{"observed_at":"2026-08-04T14:57:06.111302Z","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":"2026-08-04T14:57:06.114541Z","title":"Identifiability guarantees for causal disentanglement from purely observational data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.114541Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:38ec228958b6153b7ad3f04077be65bbf38579f1dcf0883d996c5278e66d188a","observation_id":"70d2189f-0134-4a71-92e0-8a40e42c335f","resolution":{"observed_at":"2026-08-04T14:57:06.114541Z","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":"2026-08-04T14:57:06.117954Z","title":"Sketching as a tool for numerical linear algebra","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.117954Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:dbbbaed9677531e694d6f7247a6d8f71846afa5dde0456b53c45dddbd272a9fc","observation_id":"0b899b64-4914-4198-9e39-7d44f859447f","resolution":{"observed_at":"2026-08-04T14:57:06.117954Z","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":"2026-08-04T14:57:06.120895Z","title":"Stability","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.120895Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:c247aa80d46393473fd51467f7632487116ce8c4c8704161cb76c66ffdbd425b","observation_id":"450b2471-2f01-47b6-934b-e04e7fe1cda6","resolution":{"observed_at":"2026-08-04T14:57:06.120895Z","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":"2026-08-04T14:57:06.123738Z","title":"Identifiability guarantees for causal disentanglement from soft interventions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.123738Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:25172a89fc31472d1d67e03d62e3dbb9bad5a3911ce21ea4cb1cb2a35ad7d06d","observation_id":"e34efd3c-2249-46b4-ab3e-ae53eafa64d1","resolution":{"observed_at":"2026-08-04T14:57:06.123738Z","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":"2026-08-04T14:57:06.126698Z","title":"Causal representation learning from multiple distributions: A general setting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.126698Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:0e9fc67d107b4dfb8365367c2d59ed13fc3a52f31b19c5b74931fc18cee82d15","observation_id":"f10c4f61-0f3c-46a5-a379-405167a8c121","resolution":{"observed_at":"2026-08-04T14:57:06.126698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02385","last_updated":"2024-06-04T02:05:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-04T17:54:59Z","title":"TinyLlama: An Open-Source Small Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02385","snapshot_observed_at":"2026-08-04T14:57:06.129509Z","title":"TinyLlama : An open-source small language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.129509Z"},"links":{"cited_paper":"/paper/2401.02385","citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:0724235eaa7c780a0c32c4579bad251cfa489f7cacac00ab46279e75cfbbd849","observation_id":"a65f9a36-e326-4b25-b871-f323ea112445","resolution":{"observed_at":"2026-08-04T14:57:06.129509Z","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":"2026-08-04T14:57:06.132639Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-04T14:57:06.132639Z"},"links":{"citing_paper":"/paper/2509.22553"},"observation_digest":"sha256:acfd12fe802b900cdc50ae9dfa116ff932178868979e1d1140f6ed2d8c0b8b1f","observation_id":"dc714cd4-72e9-4822-a875-6a2845610105","resolution":{"observed_at":"2026-08-04T14:57:06.132639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.22553","last_updated":"2026-05-27T16:30:03Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-08T23:24:41.665940Z","submitted_at":"2025-09-26T16:35:42Z","title":"Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":52},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2509.22553."}