{"as_of":"2026-08-10T03:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3756b08c6976848484b69fa1c9cea2d53cd2d6d745c19be78f3280673ac4cb73","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:55:42.790390Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T10:20:55.917080Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.09433","snapshot_observed_at":"2026-08-02T10:20:55.917080Z","title":"arXiv preprint arXiv:2506.09433 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22643","last_updated":"2026-06-24T02:40:49Z","snapshot_observed_at":"2026-08-08T03:20:50.943223Z","submitted_at":"2026-06-24T02:40:49Z","title":"Reason Before You Retrieve: Agentic Planning for Multi-modal RAG","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-02T10:20:55.917080Z"},"links":{"cited_paper":"/paper/2506.09433","citing_paper":"/paper/2607.22643"},"observation_digest":"sha256:02b2d52f5ffb9445862e01b44b6e0e9daec5354c3af6fbf6c84c0ec572abc2c9","observation_id":"bc9ca300-234b-4505-ab4d-b5be327efc7c","resolution":{"observed_at":"2026-08-02T10:20:55.917080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.09433/citation-record","integrity":"/paper/2506.09433/integrity","json":"/paper/2506.09433/citation-record.json","paper":"/paper/2506.09433"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2210.01240","last_updated":"2023-03-02T03:54:28Z","snapshot_observed_at":"2026-07-06T13:59:15.998573Z","submitted_at":"2022-10-03T21:34:32Z","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.01240","snapshot_observed_at":"2026-08-07T04:55:41.036022Z","title":"Language models are greedy reasoners: A systematic formal analysis of chain-of-thought","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.036022Z"},"links":{"cited_paper":"/paper/2210.01240","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:1b50bd218fbaaf5df253124308207eed5cc5eb33cfcff979a3dec7d3fb3f6b42","observation_id":"1ed45c00-0b3e-470f-8b0b-6b1b48ec6afd","resolution":{"observed_at":"2026-08-07T04:55:41.036022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05867","last_updated":"2020-05-05T17:33:38Z","snapshot_observed_at":"2026-08-07T18:32:48.669874Z","submitted_at":"2020-02-14T04:23:28Z","title":"Transformers as Soft Reasoners over Language","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05867","snapshot_observed_at":"2026-08-07T04:55:41.136542Z","title":"Transformers as soft reasoners over language","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.136542Z"},"links":{"cited_paper":"/paper/2002.05867","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:d91c181cfc3b8503eb0a52dc026635c1c8f14396590f4560153aa91649a40efa","observation_id":"d0a4929f-3690-4f86-a960-6ba499652381","resolution":{"observed_at":"2026-08-07T04:55:41.136542Z","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":"2026-08-07T04:55:43.447499Z","title":"Large language models as commonsense knowledge for large-scale task planning","venue":null,"work_id":"148448f5-526d-4dca-a4e2-0aff28daa67b","year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.254570Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:2a4202dc805a32bb02a75d1bf50e80184e3c6040254d6ba7a8491b00c4e89597","observation_id":"807422d9-58f3-4cb3-a287-3acec30ea7da","resolution":{"observed_at":"2026-08-07T04:55:43.451036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.17256","last_updated":"2023-09-09T18:32:00Z","snapshot_observed_at":"2026-08-04T23:47:27.994871Z","submitted_at":"2023-05-26T20:56:30Z","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.17256","snapshot_observed_at":"2026-08-07T04:55:41.407619Z","title":"Large language models can be lazy learners: Analyze shortcuts in in-context learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.407619Z"},"links":{"cited_paper":"/paper/2305.17256","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:8a461aa72b4aa1d7ed88205f2dcaa8252450b88c3e6321051338b8b1d9698656","observation_id":"9d54675c-7808-48f6-8490-14f21a60502a","resolution":{"observed_at":"2026-08-07T04:55:41.407619Z","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":"2026-08-07T04:55:41.618437Z","title":"Spurious correlations in machine learning: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.618437Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:c844276e131c78151aaca675ec2781e43cfd1de169f1fa85e9f732b34b585c29","observation_id":"c3aee9da-d10f-4ff1-ab4e-d9a1559b4dc1","resolution":{"observed_at":"2026-08-07T04:55:41.618437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05229","last_updated":"2025-08-27T16:24:39Z","snapshot_observed_at":"2026-07-06T19:29:09.714725Z","submitted_at":"2024-10-07T17:36:37Z","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05229","snapshot_observed_at":"2026-08-07T04:55:41.708836Z","title":"Gsm-symbolic: Understanding the limitations of mathematical reasoning in large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.708836Z"},"links":{"cited_paper":"/paper/2410.05229","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:8abe9ba990e1c5d9b8d050a1919e2e84afdcf18f2610e7a4f1549526668ed24d","observation_id":"0ffadb2a-c55b-4cb4-9910-e0de9a10bab2","resolution":{"observed_at":"2026-08-07T04:55:41.708836Z","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":"2026-08-07T04:55:43.436854Z","title":"Diab, and Bernhard Sch \\\"o lkopf","venue":null,"work_id":"17749431-e415-4e32-a1c0-d43cc9e16703","year":2024},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.786478Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:7ff22b10b72eee2e991d83bf80385a7cd8d62bcf5184f89d5a97cdc63817cfd9","observation_id":"8ddc70d2-f597-4535-8ed5-35830d61d33b","resolution":{"observed_at":"2026-08-07T04:55:43.440254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14695","last_updated":"2023-10-26T19:02:27Z","snapshot_observed_at":"2026-08-07T05:57:50.042487Z","submitted_at":"2023-05-24T03:59:18Z","title":"A Causal View of Entity Bias in (Large) Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14695","snapshot_observed_at":"2026-08-07T04:55:41.849980Z","title":"A causal view of entity bias in (large) language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.849980Z"},"links":{"cited_paper":"/paper/2305.14695","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:2f5b1d0d69eea80af02505b421f1c0562a2e2cebe487b35bcc65bd2340580bc8","observation_id":"86859aa8-13cf-49d4-a799-25a51dcb978b","resolution":{"observed_at":"2026-08-07T04:55:41.849980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05052","last_updated":"2022-01-12T02:41:09Z","snapshot_observed_at":"2026-08-09T05:54:48.037693Z","submitted_at":"2021-09-10T18:29:44Z","title":"Entity-Based Knowledge Conflicts in Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05052","snapshot_observed_at":"2026-08-07T04:55:41.935911Z","title":"Entity-based knowledge conflicts in question answering","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:41.935911Z"},"links":{"cited_paper":"/paper/2109.05052","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:c214efdf89fa2af721771ba721f7313b9527740fb225f659ae5b4aca619ced83","observation_id":"4d27c738-9f60-47d1-b289-4bb920464350","resolution":{"observed_at":"2026-08-07T04:55:41.935911Z","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":"2026-08-07T04:55:43.425084Z","title":"Counterfactual inference for text classification debiasing","venue":null,"work_id":"8c748dc5-e799-451b-a521-79b8c046cb8f","year":2021},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.048616Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:6c8981fce378e95021c475966de2148349abf7b0672d0771a539beebaa71ff99","observation_id":"2841933c-a075-4f8b-b189-db491acfe206","resolution":{"observed_at":"2026-08-07T04:55:43.429435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:43.413721Z","title":"Cladder: Assessing causal reasoning in language models","venue":null,"work_id":"a2fc43f5-0039-48a1-a923-689615bb7654","year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.168917Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:357a8dff141543f9450837c1d9c8c60dc26963795dd1b42e77696a80599ba77a","observation_id":"3cb2b9e3-da2c-437e-83de-2ed5534c3b30","resolution":{"observed_at":"2026-08-07T04:55:43.418177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12295","last_updated":"2023-10-19T01:54:27Z","snapshot_observed_at":"2026-08-07T13:11:49.965934Z","submitted_at":"2023-05-20T22:25:38Z","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12295","snapshot_observed_at":"2026-08-07T04:55:42.284502Z","title":"Logic-lm: Empowering large language models with symbolic solvers for faithful logical reasoning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.284502Z"},"links":{"cited_paper":"/paper/2305.12295","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:9bdf13c308023d1b71276888f4f9fd2ec7d54beb75131a9383a7c14a975c5950","observation_id":"36030903-62ee-480d-a24d-521272b167a5","resolution":{"observed_at":"2026-08-07T04:55:42.284502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17464","last_updated":"2025-01-08T16:27:29Z","snapshot_observed_at":"2026-08-08T04:45:27.842310Z","submitted_at":"2024-01-30T21:53:30Z","title":"Efficient Tool Use with Chain-of-Abstraction Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17464","snapshot_observed_at":"2026-08-07T04:55:42.330182Z","title":"Efficient tool use with chain-of-abstraction reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.330182Z"},"links":{"cited_paper":"/paper/2401.17464","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:91b050c22d152d96d1bf3cbef2ce3aee55bf0c142d4affa1c48c6551d2c3bc4f","observation_id":"e6526ad7-8cd4-4085-bca8-4551edfd4cbf","resolution":{"observed_at":"2026-08-07T04:55:42.330182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07837","last_updated":"2024-05-17T22:36:13Z","snapshot_observed_at":"2026-08-05T01:59:16.498557Z","submitted_at":"2022-06-15T22:35:06Z","title":"Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization","version":4},"cited_work":{"arxiv_id":"2206.07837","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.07837","snapshot_observed_at":"2026-08-07T04:55:43.137995Z","title":"Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization","venue":"cs.LG","work_id":"a3df5b49-afd8-41f3-bc62-1f815d4218f5","year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.405171Z"},"links":{"cited_paper":"/paper/2206.07837","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:5238f3e3fed39e60ae5ab70361e1039daf4a0a12fc1ae97f3666bc8f0c728359","observation_id":"3d489eb0-fb50-44c5-9e6e-e69a11401232","resolution":{"observed_at":"2026-08-07T04:55:43.142860Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:42.462885Z","title":"Causal inference by using invariant prediction: identification and confidence intervals","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.462885Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:d15d7ec83531a3fc2e4a5105b72ddb9cd9fd64d1fe22638d0d7f6b8832ac99e7","observation_id":"f3ace923-f2a8-439a-94cd-c43743a5198e","resolution":{"observed_at":"2026-08-07T04:55:42.462885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02893","last_updated":"2020-03-27T19:07:58Z","snapshot_observed_at":"2026-07-06T08:05:24.076802Z","submitted_at":"2019-07-05T15:26:26Z","title":"Invariant Risk Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02893","snapshot_observed_at":"2026-08-07T04:55:42.531110Z","title":"Invariant risk minimization","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.531110Z"},"links":{"cited_paper":"/paper/1907.02893","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:84a2d124077ef587dc98502742d6ae1d48d25a24b91e711f389f2180cfb6722c","observation_id":"28a8b6f8-1c09-42d8-822f-ccf354594623","resolution":{"observed_at":"2026-08-07T04:55:42.531110Z","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":"2026-08-07T04:55:43.394244Z","title":"Language models are greedy reasoners: A systematic formal analysis of chain-of-thought","venue":null,"work_id":"c508af8f-9ab9-434d-833b-f3ac0a944c25","year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.656611Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:f9d6d3c26bc552ec4af39256df57dbc67f34210b2c030e5ed12a93ebb1044b3f","observation_id":"bf52f8ac-9cc2-4a04-a76d-2332837ba695","resolution":{"observed_at":"2026-08-07T04:55:43.398470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:42.670887Z","title":"Improving language understanding by generative pre-training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.670887Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:86744cd417e6522547f2fb293cc4bd9cb675abfcb4c043c77b6cc6d0e03cccfe","observation_id":"746c1e53-87ef-4f18-83da-dba0d8894513","resolution":{"observed_at":"2026-08-07T04:55:42.670887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T04:55:42.704512Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.704512Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:aa2d0e4ecd919613ead19e8dc71a12135ee61db8dda95335bb864e44c3614e07","observation_id":"3184c190-975f-4838-98f5-45952dfdb584","resolution":{"observed_at":"2026-08-07T04:55:42.704512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-07T04:55:42.707916Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.707916Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:d779346028aa75ceece4a5888ea411d6bd74136f88d2a70f695e95ab11b9c294","observation_id":"b644b313-1b43-4690-81df-4fd988099415","resolution":{"observed_at":"2026-08-07T04:55:42.707916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T04:55:42.711641Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.711641Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:d8c6ad4606fc82cb7948c5becad3cd2e471dab10f4652cb77c926b397a5a00fb","observation_id":"3ea55586-cf92-4758-92bb-a9e938a6d3cd","resolution":{"observed_at":"2026-08-07T04:55:42.711641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-07T04:55:42.714622Z","title":"Training verifiers to solve math word problems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.714622Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:ee57a4f735e7979f2a381cde47b304603910f7267863b3e35353af6e70357c03","observation_id":"76a4ab4b-2784-47b6-b19f-bc9daac3b89e","resolution":{"observed_at":"2026-08-07T04:55:42.714622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.04146","last_updated":"2017-10-23T16:45:03Z","snapshot_observed_at":"2026-08-02T16:52:38.363314Z","submitted_at":"2017-05-11T13:04:47Z","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.04146","snapshot_observed_at":"2026-08-07T04:55:42.718143Z","title":"Program induction by rationale generation: Learning to solve and explain algebraic word problems","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.718143Z"},"links":{"cited_paper":"/paper/1705.04146","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:c6bc0dbe45f345266424baedc376d85b2f20e25df480bfab2b15b8d790ce57ed","observation_id":"9429981a-8f4f-45a3-b996-ecfc2fb4a61b","resolution":{"observed_at":"2026-08-07T04:55:42.718143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00836","last_updated":"2024-03-31T01:02:55Z","snapshot_observed_at":"2026-07-06T16:26:13.862006Z","submitted_at":"2023-10-02T01:00:50Z","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00836","snapshot_observed_at":"2026-08-07T04:55:42.721339Z","title":"Towards logiglue: A brief survey and a benchmark for analyzing logical reasoning capabilities of language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.721339Z"},"links":{"cited_paper":"/paper/2310.00836","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:55dd8482949619693333c62004c60aaf09cac414c6fd985ca7e03c3c19a07f1d","observation_id":"a511f378-6952-4b88-a4ad-6700f82c7933","resolution":{"observed_at":"2026-08-07T04:55:42.721339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.14150","last_updated":"2022-02-15T16:04:04Z","snapshot_observed_at":"2026-07-06T11:13:51.821442Z","submitted_at":"2021-05-29T00:09:06Z","title":"Annotation Inconsistency and Entity Bias in MultiWOZ","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.14150","snapshot_observed_at":"2026-08-07T04:55:42.724577Z","title":"Annotation inconsistency and entity bias in multiwoz","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.724577Z"},"links":{"cited_paper":"/paper/2105.14150","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:2caed61d6159228f2bec6a93ab619c8c67bbfbd0ce412c39c0e27a20b1e23bd0","observation_id":"b38d03dc-c81f-469f-8e8d-06e1f110b0b2","resolution":{"observed_at":"2026-08-07T04:55:42.724577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-07T04:55:42.727261Z","title":"Scaling laws for neural language models","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.727261Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:4d658c5c7e3d952e271a844858aac64dfada4f9087aea7703f792577f296ee5a","observation_id":"d08626ab-b9dc-46a6-95be-0db309399855","resolution":{"observed_at":"2026-08-07T04:55:42.727261Z","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":"2026-08-07T04:55:42.730487Z","title":"Scaling laws of synthetic data for language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.730487Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:333da0d1a3131dde5631309bf77ecd6aad1de6daac1d59192cfbc58b0d815c80","observation_id":"413ea2db-7e24-49a9-a394-2dcd1d65f9a6","resolution":{"observed_at":"2026-08-07T04:55:42.730487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.05518","last_updated":"2025-04-07T21:25:31Z","snapshot_observed_at":"2026-08-07T16:07:46.495122Z","submitted_at":"2025-04-07T21:25:31Z","title":"Evaluating the Generalization Capabilities of Large Language Models on Code Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.05518","snapshot_observed_at":"2026-08-07T04:55:42.733135Z","title":"Evaluating the generalization capabilities of large language models on code reasoning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.733135Z"},"links":{"cited_paper":"/paper/2504.05518","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:ade84a0b2eb84f5652fde728e4d296d3c8b515745a20a2e3bac0462bb2143f78","observation_id":"d2b4b161-032e-41cf-bcc1-dafd47853b90","resolution":{"observed_at":"2026-08-07T04:55:42.733135Z","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":"2026-08-07T04:55:42.736113Z","title":"Causal inference in statistics: A primer","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.736113Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:151f8da02356b0934cf491bb9a20aa8ff64ee95e4099d648aa7ac7965f0bd942","observation_id":"507ec57b-0930-4689-99bf-3cef7966b4b1","resolution":{"observed_at":"2026-08-07T04:55:42.736113Z","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":"2026-08-07T04:55:43.367470Z","title":"Bias and fairness in large language models: A survey","venue":null,"work_id":"9d6ede89-c649-4e06-83f8-566aff7ff4f6","year":2024},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.739137Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:e6f55943bd3016c851e7e6ad4e77a0595a7b236b08b3931c9a7b2173cf055346","observation_id":"e24c5e6d-7751-4a42-8855-172f87fee381","resolution":{"observed_at":"2026-08-07T04:55:43.371814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:43.356300Z","title":"Some philosophical problems from the standpoint of artificial intelligence","venue":null,"work_id":"3fac91db-989b-45e5-a15a-556662123126","year":1981},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.742300Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:2a31ea2baab33404ed620d9ab11e9e8096959afdbee38cf80d6ded7960055d7d","observation_id":"6cab5e95-c8b7-4a4c-9032-452273fe4661","resolution":{"observed_at":"2026-08-07T04:55:43.360123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:43.344889Z","title":"Inductive logic programming","venue":null,"work_id":"8b29a2af-01bb-4d47-a3d4-89fb28709cd8","year":1994},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.745437Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:59aae77c5edb5b5f91bb84489d12b6058e4f464272da7d5d90b1bf5c237611eb","observation_id":"7d5573e3-924f-47ca-9236-5a33c2842747","resolution":{"observed_at":"2026-08-07T04:55:43.349242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.12217","last_updated":"2022-10-21T19:51:56Z","snapshot_observed_at":"2026-07-06T14:08:53.562621Z","submitted_at":"2022-10-21T19:51:56Z","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","version":1},"cited_work":{"arxiv_id":"2210.12217","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.12217","snapshot_observed_at":"2026-08-07T04:55:42.917595Z","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","venue":"cs.AI","work_id":"6379a7fb-405f-46e5-91ec-d2894fd61503","year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.748198Z"},"links":{"cited_paper":"/paper/2210.12217","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:2cfc419c82dba6b49d1e996514b238d1d27b600f06f7b161211c76a7c705ef89","observation_id":"8a84bb19-2fb6-4943-b0ec-3a1ed6a17a32","resolution":{"observed_at":"2026-08-07T04:55:42.921278Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12443","last_updated":"2022-10-21T20:08:11Z","snapshot_observed_at":"2026-07-06T13:13:37.143547Z","submitted_at":"2022-05-25T02:22:30Z","title":"Generating Natural Language Proofs with Verifier-Guided Search","version":3},"cited_work":{"arxiv_id":"2205.12443","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.12443","snapshot_observed_at":"2026-08-07T04:55:42.903161Z","title":"Generating Natural Language Proofs with Verifier-Guided Search","venue":"cs.CL","work_id":"e0df937c-d21e-46c1-85e6-f819311ca3bf","year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.751252Z"},"links":{"cited_paper":"/paper/2205.12443","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:f14f612ff8f5c7892970c280e7b9570a36f1c3a53af639ef2c84f4a590a296be","observation_id":"c29186a1-27e2-462b-a324-8892bdcc0edc","resolution":{"observed_at":"2026-08-07T04:55:42.906986Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:42.754631Z","title":"Chain-of-thought prompting elicits reasoning in large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.754631Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:70668169c26a96f242493c45b51ae5e4ed551557b3243db492cf660c570cbca7","observation_id":"9702fdb7-329d-4636-999e-041da5718753","resolution":{"observed_at":"2026-08-07T04:55:42.754631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-07-06T12:50:22.773056Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-08-07T04:55:42.757389Z","title":"Self-consistency improves chain of thought reasoning in language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.757389Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:334c3a25269c9fd3b496cefbd09cdb4a0090c883f62ca4f0709b5af50ff116a6","observation_id":"b2fc6966-f48e-46a7-ac13-5f3a7581ce2b","resolution":{"observed_at":"2026-08-07T04:55:42.757389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18041","last_updated":"2024-02-28T04:35:51Z","snapshot_observed_at":"2026-08-09T10:35:52.671780Z","submitted_at":"2024-02-28T04:35:51Z","title":"Datasets for Large Language Models: A Comprehensive Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18041","snapshot_observed_at":"2026-08-07T04:55:42.760418Z","title":"Datasets for large language models: A comprehensive survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.760418Z"},"links":{"cited_paper":"/paper/2402.18041","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:5c6b52798d367b1668ee22a01ddbc0ae94a4582be3993121d893d9d7623ac64d","observation_id":"67619092-df70-44c0-b895-3063f98c542f","resolution":{"observed_at":"2026-08-07T04:55:42.760418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.11385","last_updated":"2024-10-15T08:23:31Z","snapshot_observed_at":"2026-08-02T07:36:14.149461Z","submitted_at":"2024-10-15T08:23:31Z","title":"Do LLMs Have the Generalization Ability in Conducting Causal Inference?","version":1},"cited_work":{"arxiv_id":"2410.11385","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.11385","snapshot_observed_at":"2026-08-07T04:55:42.868762Z","title":"Do LLMs Have the Generalization Ability in Conducting Causal Inference?","venue":"cs.CL","work_id":"cf09aecc-14a1-4c59-81c2-4a15023915a6","year":2024},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.763237Z"},"links":{"cited_paper":"/paper/2410.11385","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:6d1e9e1e436e920d6a8fccb4208fe4a1937690dd571da339b55e626d1dc2ed41","observation_id":"36423451-de26-45d6-a1c1-f0747dee2e8a","resolution":{"observed_at":"2026-08-07T04:55:42.874103Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.13067","last_updated":"2023-08-24T20:23:13Z","snapshot_observed_at":"2026-07-06T16:10:11.901106Z","submitted_at":"2023-08-24T20:23:13Z","title":"Causal Parrots: Large Language Models May Talk Causality But Are Not Causal","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.13067","snapshot_observed_at":"2026-08-07T04:55:42.766358Z","title":"Causal parrots: Large language models may talk causality but are not causal","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.766358Z"},"links":{"cited_paper":"/paper/2308.13067","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:94083e9af494c4e6c52721a993bd5a5a44bce932cd128eff9d8490c85f449d73","observation_id":"5ce8841c-397f-47c6-a2a6-2b2c828ef852","resolution":{"observed_at":"2026-08-07T04:55:42.766358Z","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":"2026-08-07T04:55:42.769427Z","title":"The book of why: the new science of cause and effect","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.769427Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:1deca35ac2c1f4aeff9305486e52625dd3ef5f61d08c68d08af787f4c70a4c9d","observation_id":"4a5c81be-8912-44ee-a373-64bd4adc89a8","resolution":{"observed_at":"2026-08-07T04:55:42.769427Z","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":"2026-08-07T04:55:43.319183Z","title":"Zin: When and how to learn invariance without environment partition? Advances in Neural Information Processing Systems, 35: 0 24529--24542, 2022","venue":null,"work_id":"f923d4d9-fe99-45d7-bb46-f28ee6d14b11","year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.772568Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:cabec18ba031588b809ad002a664f2d023cf1ec88fb2bfe504ee98eca1d30fae","observation_id":"8b4a0133-1c26-4383-82a0-f85bcfb27b57","resolution":{"observed_at":"2026-08-07T04:55:43.322907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"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":"2026-08-07T04:55:42.775512Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.775512Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:362e952b8183fa29d9c0231dbe2019812d7ae0bd17137e6f450db20f735bf5aa","observation_id":"2550a337-a156-4cbd-addc-274a48e6c69a","resolution":{"observed_at":"2026-08-07T04:55:42.775512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13048","last_updated":"2021-06-03T19:15:08Z","snapshot_observed_at":"2026-08-08T08:19:06.524784Z","submitted_at":"2020-12-24T00:55:46Z","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13048","snapshot_observed_at":"2026-08-07T04:55:42.778568Z","title":"Proofwriter: Generating implications, proofs, and abductive statements over natural language","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.778568Z"},"links":{"cited_paper":"/paper/2012.13048","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:c8d69d721bf31b09c7dc354b656e96667bb98efadb6f8b5c1d020eef772ef4e4","observation_id":"a374efc8-3b1d-4231-b541-cb205caf8b02","resolution":{"observed_at":"2026-08-07T04:55:42.778568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.00840","last_updated":"2024-10-11T20:08:54Z","snapshot_observed_at":"2026-08-09T17:25:13.891240Z","submitted_at":"2022-09-02T06:50:11Z","title":"FOLIO: Natural Language Reasoning with First-Order Logic","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.00840","snapshot_observed_at":"2026-08-07T04:55:42.781612Z","title":"Folio: Natural language reasoning with first-order logic","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.781612Z"},"links":{"cited_paper":"/paper/2209.00840","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:07aa14e555f5e3c7621cbd4e43fb07066a612e69fbfcf6c29db043a9c3c2ec3d","observation_id":"625eeb89-d441-417a-a1a8-add8febd28ee","resolution":{"observed_at":"2026-08-07T04:55:42.781612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11502","last_updated":"2022-05-24T20:56:39Z","snapshot_observed_at":"2026-07-06T13:12:59.688989Z","submitted_at":"2022-05-23T17:56:48Z","title":"On the Paradox of Learning to Reason from Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11502","snapshot_observed_at":"2026-08-07T04:55:42.784696Z","title":"On the paradox of learning to reason from data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.784696Z"},"links":{"cited_paper":"/paper/2205.11502","citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:b8774814d7df1b624af036a75456904b02e2d827221f3632d52ab5a030bb6a38","observation_id":"e961a336-f6d8-43ee-8df1-8ef5f66990f8","resolution":{"observed_at":"2026-08-07T04:55:42.784696Z","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":"2026-08-07T04:55:42.787497Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.787497Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:1e75e4bb0d052e2f64493c849eabcfb0522ad905875ccce5d4237807eb16af9e","observation_id":"5ba9b4fa-45ab-494f-987f-b000b0333f67","resolution":{"observed_at":"2026-08-07T04:55:42.787497Z","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":"2026-08-07T04:55:42.790390Z","title":"Scikit-learn: Machine learning in python","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:42.790390Z"},"links":{"citing_paper":"/paper/2506.09433"},"observation_digest":"sha256:ec6553241ffb07dc347c57501805644095da7663e53f0b4c2805c51eb2f37379","observation_id":"23b7b8bd-9230-4857-94f0-b75a365519c7","resolution":{"observed_at":"2026-08-07T04:55:42.790390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.09433","last_updated":"2025-06-11T06:30:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T05:55:16.389343Z","submitted_at":"2025-06-11T06:30:28Z","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":34,"verified_exact":4,"verified_fuzzy":9},"total_outbound_references":47},"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 10 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2506.09433."}