{"as_of":"2026-08-16T21:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1c5d4e71208f2dd6a579ca5397fe8aa1fdd5d1b73fd084f4772323ae248f6251","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:00:10.945137Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.18285/citation-record","integrity":"/paper/2506.18285/integrity","json":"/paper/2506.18285/citation-record.json","paper":"/paper/2506.18285"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1906.02226","last_updated":"2020-02-18T14:49:33Z","snapshot_observed_at":"2026-08-14T16:20:17.549955Z","submitted_at":"2019-06-05T18:09:55Z","title":"Gradient-Based Neural DAG Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02226","snapshot_observed_at":"2026-08-15T19:00:10.870190Z","title":"Gradient-based neural dag learning.arXiv preprint arXiv:1906.02226,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.870190Z"},"links":{"cited_paper":"/paper/1906.02226","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:c1f60c5f20caccdba9b511907fa6dc7b468c7c33b8e49fc5a098fcfd0b21c769","observation_id":"e3c5c4e2-e6e2-4f58-8438-df8385747e29","resolution":{"observed_at":"2026-08-15T19:00:10.870190Z","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":"2385.3480","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:00:11.151848Z","title":"Hyperparameters, including sparsity constraint coefficients and thresholds, are extensively tuned 15 to optimize SHD performance","venue":null,"work_id":"d69d0320-12fd-445c-b1c8-a241448641ea","year":2017},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.932269Z"},"links":{"citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:a71c7b3f4e81f7fb509fe7a02aae5377f803a026656c3be4eeefbbe523b2336e","observation_id":"ed990953-fd75-4313-8254-cf9ac7c7cd83","resolution":{"observed_at":"2026-08-15T19:00:11.166554Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.12138","last_updated":"2025-05-17T20:42:23Z","snapshot_observed_at":"2026-08-15T20:38:11.122053Z","submitted_at":"2025-05-17T20:42:23Z","title":"Transformer learns the cross-task prior and regularization for in-context learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.12138","snapshot_observed_at":"2026-08-15T19:00:10.889049Z","title":"Transformer learns the cross-task prior and regularization for in-context learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.889049Z"},"links":{"cited_paper":"/paper/2505.12138","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:be8874400a8edcfba727f09d177b01331ae5f784c7f218950d98de476487f10e","observation_id":"12ce7a86-dad9-4ff2-9306-86d297565572","resolution":{"observed_at":"2026-08-15T19:00:10.889049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15319","last_updated":"2024-10-20T07:22:23Z","snapshot_observed_at":"2026-08-16T13:07:42.170987Z","submitted_at":"2024-10-20T07:22:23Z","title":"Causality for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15319","snapshot_observed_at":"2026-08-15T19:00:10.919460Z","title":"Causality for large language models.arXiv preprint arXiv:2410.15319,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.919460Z"},"links":{"cited_paper":"/paper/2410.15319","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:7b31f04868de7f14951141c7991851207ecaf1bc59ed5911a36dc42b2af44cad","observation_id":"9c77f1eb-c359-47ee-a205-97261dcc5ef8","resolution":{"observed_at":"2026-08-15T19:00:10.919460Z","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":"2026-08-15T19:00:11.434345Z","title":"Towards causal foundation model: on duality between optimal balancing and attention","venue":null,"work_id":"f6f67b3c-ccc7-45d3-bb9c-109834ce3322","year":2017},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.925612Z"},"links":{"citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:759533e0c5cc395bc442af7f3343696dd9eb7c0694e4081fe7bb0e464d9cb058","observation_id":"a6b755d5-cfe7-4aac-a2d8-bb250b20548e","resolution":{"observed_at":"2026-08-15T19:00:11.440043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T19:00:11.416842Z","title":"We leave such theoretical investigations to a future work","venue":null,"work_id":"f9f1fe2e-a0cf-4040-9f74-bc72ae7f0668","year":2024},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.938487Z"},"links":{"citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:bb2dbba31eb1fe2606458c4bdec00b663a91207ba4841ed3451e82ea2fad4b8e","observation_id":"47a070b1-25c2-4c7f-a011-8f00485c9d85","resolution":{"observed_at":"2026-08-15T19:00:11.422672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T19:00:11.393787Z","title":null,"venue":null,"work_id":"ff298ff5-7126-439b-b94c-37b65c84e3e6","year":2025},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.945137Z"},"links":{"citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:2bab3e440142af4caa09bf3572ec816ee17c631a8ccde377c1d1b0681d9a1299","observation_id":"f3bad25d-90cf-48ee-bd52-c233c4c4f898","resolution":{"observed_at":"2026-08-15T19:00:11.404069Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1202.3757","last_updated":"2012-02-14T16:41:17Z","snapshot_observed_at":"2026-08-15T04:19:18.680584Z","submitted_at":"2012-02-14T16:41:17Z","title":"Identifiability of Causal Graphs using Functional Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1202.3757","snapshot_observed_at":"2026-08-15T19:00:10.906965Z","title":"Identifiability of causal graphs using functional models.arXiv preprint arXiv:1202.3757,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.906965Z"},"links":{"cited_paper":"/paper/1202.3757","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:d9e35112a593dd5fd436007cc653f9ccb26132f27795837e602bb3309468ad41","observation_id":"335d843f-de49-4999-924b-62383fd4a859","resolution":{"observed_at":"2026-08-15T19:00:10.906965Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04697","last_updated":"2020-06-08T15:53:20Z","snapshot_observed_at":"2026-08-14T19:13:11.114767Z","submitted_at":"2020-06-08T15:53:20Z","title":"Supervised Whole DAG Causal Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04697","snapshot_observed_at":"2026-08-15T19:00:10.876752Z","title":"Supervised whole dag causal discovery.arXiv preprint arXiv:2006.04697,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.876752Z"},"links":{"cited_paper":"/paper/2006.04697","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:b3825d13f0a3aeb2de9d2b01f1eb37c4899d390edffc0f9b7753d704a4b6637b","observation_id":"dc94149b-124b-43bc-b128-a4f8243f2a69","resolution":{"observed_at":"2026-08-15T19:00:10.876752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23106","last_updated":"2025-05-29T05:18:30Z","snapshot_observed_at":"2026-08-14T00:12:33.930126Z","submitted_at":"2025-05-29T05:18:30Z","title":"Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.23106","snapshot_observed_at":"2026-08-15T19:00:10.883289Z","title":"Neural interpretable pdes: Harmonizing fourier insights with attention for scalable and interpretable physics discovery.arXiv preprint arXiv:2505.23106,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.883289Z"},"links":{"cited_paper":"/paper/2505.23106","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:c2dc3dbabb5d4f7e15e2bbb3883a75b86b348245c802372f4e3b907a91561ba4","observation_id":"257aae5d-e01a-4878-a326-d403c99f0943","resolution":{"observed_at":"2026-08-15T19:00:10.883289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.16902","last_updated":"2025-08-26T11:41:14Z","snapshot_observed_at":"2026-08-16T15:20:04.092179Z","submitted_at":"2023-06-29T12:48:00Z","title":"Integrating Large Language Model for Improved Causal Discovery","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.16902","snapshot_observed_at":"2026-08-15T19:00:10.858390Z","title":"URLhttps://dx.doi.org/10.1088/1361-6420/ac245d","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.858390Z"},"links":{"cited_paper":"/paper/2306.16902","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:fa108187967013fb73b396b56cd78b1a629298421fb308277d8c09211357c0e4","observation_id":"3ef1d857-94a5-48d9-add4-cd01b493588f","resolution":{"observed_at":"2026-08-15T19:00:10.858390Z","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":"2026-08-15T19:00:10.900866Z","title":"Asymptotic theory of in-context learning by linear attention.arXiv preprint arXiv:2405.11751,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.900866Z"},"links":{"citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:b5897c92ca046cbf1308527ee94607de89c15aecb5376d4d49fe800d5d372e47","observation_id":"290c7487-fdce-4998-9839-062a0b598fb7","resolution":{"observed_at":"2026-08-15T19:00:10.900866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11068","last_updated":"2025-02-15T03:55:33Z","snapshot_observed_at":"2026-08-16T14:17:51.497403Z","submitted_at":"2024-02-16T20:48:53Z","title":"Large Language Models for Causal Discovery: Current Landscape and Future Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11068","snapshot_observed_at":"2026-08-15T19:00:10.913017Z","title":"Bridging causal discovery and large language models: A comprehensive survey of integrative approaches and future directions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.913017Z"},"links":{"cited_paper":"/paper/2402.11068","citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:ba51a9cdf4e3d3bbfc883eee3937a9e064d089b6b7c291169ce5173fc7cdf662","observation_id":"62ec1d04-c151-4fb4-b708-4f652df36be6","resolution":{"observed_at":"2026-08-15T19:00:10.913017Z","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":"2026-08-15T19:00:11.451477Z","title":"Meta-dag: Meta causal discovery via bilevel optimization","venue":null,"work_id":"5129be1d-0d3e-4782-9f97-e7a7d4a94544","year":2023},"citing_paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T19:00:10.895130Z"},"links":{"citing_paper":"/paper/2506.18285"},"observation_digest":"sha256:bf257f6ab940b230af924250f0f78f9456129f0285a83be4e5f98cac1e125903","observation_id":"5f9468ba-4ff4-4513-8ca7-04959a77eacd","resolution":{"observed_at":"2026-08-15T19:00:11.457018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.18285","last_updated":"2025-06-23T04:41:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T19:00:37.625163Z","submitted_at":"2025-06-23T04:41:02Z","title":"Learning Causal Graphs at Scale: A Foundation Model Approach"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":9,"verified_exact":1,"verified_fuzzy":3},"total_outbound_references":14},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2506.18285."}