{"as_of":"2026-08-16T15:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ecbdd37cfa59c031f3bba2ecf0e8dc209ac2337f8d444d473c2429e65260d528","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:41:50.907910Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"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/2505.07883/citation-record","integrity":"/paper/2505.07883/integrity","json":"/paper/2505.07883/citation-record.json","paper":"/paper/2505.07883"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.09798","last_updated":"2024-03-14T18:36:04Z","snapshot_observed_at":"2026-08-16T14:09:41.613949Z","submitted_at":"2024-03-14T18:36:04Z","title":"Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09798","snapshot_observed_at":"2026-08-15T22:41:50.714164Z","title":"Comparing rationality between large language models and humans: Insights and open questions.arXiv preprint arXiv:2403.09798, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.714164Z"},"links":{"cited_paper":"/paper/2403.09798","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:bc764e711da13fec1ac6cb54907971a4468e21a4a90c86a63254f437794e0fe0","observation_id":"16a90c72-9def-48e5-96bf-3646f17de138","resolution":{"observed_at":"2026-08-15T22:41:50.714164Z","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":"2026-08-15T22:41:51.513100Z","title":"Deep learning of representations: Looking forward","venue":null,"work_id":"aecd5a4a-f4fc-43a3-ad82-7946b456ab59","year":2013},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.719813Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:30baba56d6e1f2d8fa1e8ae5d371adf59a95b9723fd53cef0f4880b8521bbdba","observation_id":"ec9528fc-9f5f-44e8-9b8b-76f8b6020523","resolution":{"observed_at":"2026-08-15T22:41:51.517963Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:41:50.724723Z","title":"Using cognitive psychology to understand gpt-3.Proceedings of the National Academy of Sciences, 120(6):e2218523120, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.724723Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:f4cbd89e2ef7d3442b465b3ea0d7cdd62a6ba19e6200af7197911b43425762bd","observation_id":"b66fc586-7332-4a9e-b72d-c695f292e13a","resolution":{"observed_at":"2026-08-15T22:41:50.724723Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.07143","last_updated":"2021-04-14T22:04:48Z","snapshot_observed_at":"2026-08-13T01:03:06.240132Z","submitted_at":"2021-04-14T22:04:48Z","title":"An Interpretability Illusion for BERT","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.07143","snapshot_observed_at":"2026-08-15T22:41:50.729699Z","title":"An interpretability illusion for bert.arXiv preprint arXiv:2104.07143, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.729699Z"},"links":{"cited_paper":"/paper/2104.07143","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:b5ac151018acb8fc1a7fecbafca59c1363a14929ceb26350cf87211811fad59d","observation_id":"1a67009e-afc0-4b94-9e35-3417fcd244a6","resolution":{"observed_at":"2026-08-15T22:41:50.729699Z","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":"2026-08-15T22:41:50.734775Z","title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.734775Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:8c49ef7d5136731173df5f821274bc82a1cef0a95b171c57a8c185ade94b1e11","observation_id":"7cf96e5d-1da0-40a8-8cda-0a47f4b16fc6","resolution":{"observed_at":"2026-08-15T22:41:50.734775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03599","last_updated":"2018-04-10T15:48:18Z","snapshot_observed_at":"2026-08-14T19:27:23.675013Z","submitted_at":"2018-04-10T15:48:18Z","title":"Understanding disentangling in $\\beta$-VAE","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03599","snapshot_observed_at":"2026-08-15T22:41:50.739519Z","title":"Understanding disentangling in β-V AE.arXiv preprint arXiv:1804.03599, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.739519Z"},"links":{"cited_paper":"/paper/1804.03599","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:69c1fe1189cc1db10480ed7c1a0ac2a63e825ed9ee1652ef37136d27ce3349ad","observation_id":"fdfc84cb-913a-4b77-8b91-e61a83f0f890","resolution":{"observed_at":"2026-08-15T22:41:50.739519Z","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":"2026-08-15T22:41:51.475990Z","title":"Isolating sources of disentanglement in variational autoencoders.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":"2de23546-8a0a-46ff-b115-7e893c6db8ed","year":2018},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.745041Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:d0a775ab9d7d9922141c1dacbd98fe0597e0549b1fb61841691f8aeb05d44eb6","observation_id":"91632720-02a0-40ad-9c04-21924761d399","resolution":{"observed_at":"2026-08-15T22:41:51.481248Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:41:50.749591Z","title":"Group equivariant convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.749591Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:ed6558a6f99488207960be5499f9a59d0b94af047724718f0585b986cf56253f","observation_id":"7cce7327-6e9e-4e62-be98-02df5df0f10e","resolution":{"observed_at":"2026-08-15T22:41:50.749591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08600","last_updated":"2023-10-04T13:17:38Z","snapshot_observed_at":"2026-08-16T13:37:26.527260Z","submitted_at":"2023-09-15T17:56:55Z","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08600","snapshot_observed_at":"2026-08-15T22:41:50.753877Z","title":"Sparse autoen- coders find highly interpretable features in language models.arXiv preprint arXiv:2309.08600, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.753877Z"},"links":{"cited_paper":"/paper/2309.08600","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:e8602f9ac12e5a1e714853f006a9fde38dfd67b3b5771689b64da39ab7d61ab2","observation_id":"64424a4f-93b0-45c7-9862-3970cca0ff45","resolution":{"observed_at":"2026-08-15T22:41:50.753877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01280","last_updated":"2024-10-02T06:51:12Z","snapshot_observed_at":"2026-08-16T13:13:29.614899Z","submitted_at":"2024-10-02T06:51:12Z","title":"Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01280","snapshot_observed_at":"2026-08-15T22:41:50.758598Z","title":"Sparse autoencoders reveal temporal difference learning in large language models.arXiv preprint arXiv:2410.01280, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.758598Z"},"links":{"cited_paper":"/paper/2410.01280","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:5959de346310073cb4728288ce7148e8f4b1b9d7f4f448f60aaefd347c52633e","observation_id":"3a8519eb-c283-462f-9d9d-4a69bfed5081","resolution":{"observed_at":"2026-08-15T22:41:50.758598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-15T22:41:50.763595Z","title":"The Llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.763595Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:fe1c88a68117b23b9bfbbcf3d1300b7eb96e33c807188464bfdcb401ad7bf738","observation_id":"9aa35b10-6b92-4edf-87fc-fdff43965894","resolution":{"observed_at":"2026-08-15T22:41:50.763595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.10652","last_updated":"2022-09-21T20:49:26Z","snapshot_observed_at":"2026-07-06T13:54:56.779166Z","submitted_at":"2022-09-21T20:49:26Z","title":"Toy Models of Superposition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.10652","snapshot_observed_at":"2026-08-15T22:41:50.768076Z","title":"Toy models of superposition.arXiv preprint arXiv:2209.10652, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.768076Z"},"links":{"cited_paper":"/paper/2209.10652","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:f8a2e67d353652ee3d1209df9217910217ba30072f5a72d3f734a3199df31c83","observation_id":"029ba942-cfee-464d-ad3e-8025f643e779","resolution":{"observed_at":"2026-08-15T22:41:50.768076Z","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":"2026-08-15T22:41:50.772525Z","title":"A mathematical framework for transformer circuits.Transformer Circuits Thread, 1(1):12, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.772525Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:5de21a123611a86727794e0aaac4456dfce17837667a36f521d92a307387bc2f","observation_id":"2f29237b-9b8e-4102-9c9f-b88b91e3805d","resolution":{"observed_at":"2026-08-15T22:41:50.772525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08295","last_updated":"2024-04-16T12:52:47Z","snapshot_observed_at":"2026-08-03T03:29:01.959523Z","submitted_at":"2024-03-13T06:59:16Z","title":"Gemma: Open Models Based on Gemini Research and Technology","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-15T22:41:50.776900Z","title":"Gemma: Open models based on gemini research and technology.arXiv preprint arXiv:2403.08295, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.776900Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:3c70698bcb7f6207c8aad60be4255de94c01550d1d4143f10ea3e23127004132","observation_id":"1a1db8d1-15b0-4114-93a5-9302f2b6d9d3","resolution":{"observed_at":"2026-08-15T22:41:50.776900Z","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":"2026-08-15T22:41:50.781533Z","title":"On calibration of modern neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.781533Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:62e46233ef0a240030c7e8b1b61be16deca084989f28e52f1c0d93c3fc7b9fe1","observation_id":"6e0eccc0-03b3-4ecf-a9a7-f4311788d0df","resolution":{"observed_at":"2026-08-15T22:41:50.781533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.01610","last_updated":"2023-06-02T21:52:17Z","snapshot_observed_at":"2026-08-13T11:50:37.433001Z","submitted_at":"2023-05-02T17:13:55Z","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.01610","snapshot_observed_at":"2026-08-15T22:41:50.785870Z","title":"Finding neurons in a haystack: Case studies with sparse probing.arXiv preprint arXiv:2305.01610, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.785870Z"},"links":{"cited_paper":"/paper/2305.01610","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:84344ff62c81d241fb3761480269f7fbaf1eb71a295f387df31b17b8bc4a6d70","observation_id":"08284514-5534-4b73-99dc-445649be6fe6","resolution":{"observed_at":"2026-08-15T22:41:50.785870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-08-13T19:48:28.322536Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-15T22:41:50.790449Z","title":"Gaussian error linear units (gelus).arXiv preprint arXiv:1606.08415, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.790449Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:6e15a9240f48cce47376c7444d46ef72558caa82a9bfd8789a82f1e8bccaa310","observation_id":"453fa5c3-866c-4e80-b8ab-f21dd456ca23","resolution":{"observed_at":"2026-08-15T22:41:50.790449Z","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":"2026-08-15T22:41:51.429826Z","title":"beta-V AE: Learning basic visual concepts with a constrained variational framework.International Conference on Learning Representations, 3, 2017","venue":null,"work_id":"4955acc3-04fe-4291-b25e-a3d2bd7b45b1","year":2017},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.794961Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:2dc92d12c7e19e3452d540edb9062cef1e73ff35d9a21dbef9c9696729046f84","observation_id":"4364d622-aa55-4e8a-84ba-f11df918cac7","resolution":{"observed_at":"2026-08-15T22:41:51.434656Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:41:50.799454Z","title":"Large language models as simulated economic agents: What can we learn from homo silicus? Technical report, National Bureau of Economic Research, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.799454Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:7084ba3e7f7a1ad41a12f46156256c19e2bdb8ad5079154f88125228a2d20053","observation_id":"42146d0a-2b0e-4afc-b6f2-3ae2dedbfe79","resolution":{"observed_at":"2026-08-15T22:41:50.799454Z","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":"2026-08-15T22:41:50.804433Z","title":"Nonlinear independent component analysis for principled disentanglement in unsupervised deep learning.Patterns, 4(10), 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.804433Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:a4750ac25f48f4e30f977db13f591a3f6866b228d84ed32116a3251e9bfadec2","observation_id":"5cc73f31-b565-478a-9641-b92c421acfae","resolution":{"observed_at":"2026-08-15T22:41:50.804433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05972","last_updated":"2024-11-01T00:50:56Z","snapshot_observed_at":"2026-08-16T14:47:59.810843Z","submitted_at":"2024-06-10T02:14:19Z","title":"Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05972","snapshot_observed_at":"2026-08-15T22:41:50.809131Z","title":"Decision-making be- havior evaluation framework for llms under uncertain context.arXiv preprint arXiv:2406.05972, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.809131Z"},"links":{"cited_paper":"/paper/2406.05972","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:abc0b8887dc3db2c1fca9811215a888e92b1e2d38c429f796415c5575ca9a04d","observation_id":"8d297e32-234b-405b-9c0e-2d9d3edb530c","resolution":{"observed_at":"2026-08-15T22:41:50.809131Z","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":"2026-08-15T22:41:50.814089Z","title":"Disentangling by factorising","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.814089Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:bea3bbb98819dfa77f7295735bd8e630c8715666fc3f40893f3cb65693a8f14d","observation_id":"690fdbcb-b3b2-4537-bd22-0cf90a949857","resolution":{"observed_at":"2026-08-15T22:41:50.814089Z","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":"2026-08-15T22:41:51.384068Z","title":"Kingma and Max Welling","venue":null,"work_id":"d71b8383-cd97-4db9-82f4-7fa9a857d6d0","year":2014},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.818680Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:1d9283d44276edb12f55c32608c1d3a6689d577c8f1b9845268c8776b2973c60","observation_id":"305900a9-123d-4f4a-abc6-b630678713cc","resolution":{"observed_at":"2026-08-15T22:41:51.388793Z","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":"2026-08-15T22:41:51.368320Z","title":"Courier Dover Publications, 2018","venue":null,"work_id":"fbbf86a6-1d16-4897-877f-e3474e9f8181","year":2018},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.823280Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:04d82160677967d4df60835f63886ad015f46d35b684cfa721b57e36f7b57302","observation_id":"c3791942-7c31-44f5-a55f-8b3d386bba25","resolution":{"observed_at":"2026-08-15T22:41:51.373500Z","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":"2026-08-15T22:41:51.352792Z","title":"Verified uncertainty calibration.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"2f5acadc-7eb7-4511-bf33-6823942c667c","year":2019},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.827561Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:d526a3b4bf22dd9c3809dad67be5bafdbf5dc02dfabd17caf6af0906796335d2","observation_id":"d26dee81-906d-416f-8709-ee18e1711fa9","resolution":{"observed_at":"2026-08-15T22:41:51.357600Z","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":{"arxiv_id":"2406.17055","last_updated":"2025-03-10T17:42:37Z","snapshot_observed_at":"2026-08-16T13:40:00.107057Z","submitted_at":"2024-06-24T18:15:27Z","title":"Large Language Models Assume People are More Rational than We Really are","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.17055","snapshot_observed_at":"2026-08-15T22:41:50.832161Z","title":"Large language models assume people are more rational than we really are.arXiv preprint arXiv:2406.17055, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.832161Z"},"links":{"cited_paper":"/paper/2406.17055","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:fa826481b69cc250e79305dad464a00d9346f512d4b86d118cc20fbd2f125468","observation_id":"9edc394e-642b-4b8e-b2a8-6c9a36d55d69","resolution":{"observed_at":"2026-08-15T22:41:50.832161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-15T22:41:50.837203Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.837203Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:c3b15e8cd00bc1361d69bafa053889ce71a2b88b71a810f641c54598bcc94a49","observation_id":"111c8037-2ad1-45a2-b6c4-d2dea40e7ca8","resolution":{"observed_at":"2026-08-15T22:41:50.837203Z","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":"2026-08-15T22:41:51.337754Z","title":"Disentangling disentan- glement in variational autoencoders","venue":null,"work_id":"44d42bfc-7a52-45ce-9c9e-fa8704b1fdf3","year":2019},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.841844Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:76227d012ce75d9509db5762774d21d005fb5ebf38d73f0680c6c641fee770f3","observation_id":"1b954b9f-6d8a-4fbb-802d-a6c9f8b57e9d","resolution":{"observed_at":"2026-08-15T22:41:51.342476Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:41:50.846248Z","title":"Sparse autoencoder.CS294A Lecture notes, 72(2011):1–19, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.846248Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:7ae4aca593feaceed0d9e561d4c8c2eea47aacb06330e76b0a197034fd5f9dbe","observation_id":"e7567f25-733b-450c-b103-cd268e65ab3e","resolution":{"observed_at":"2026-08-15T22:41:50.846248Z","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":"2026-08-15T22:41:51.312436Z","title":"Oxford University Press, 2016","venue":null,"work_id":"8e1ccfb1-f523-4817-a717-5882a28c2886","year":2016},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.850954Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:a1e15bdb3f504baed9a6164b3cd6abda6a80cf5c2d614e84495438c4e4077aba","observation_id":"c8676643-b14c-475a-ba74-4ba25715dd0d","resolution":{"observed_at":"2026-08-15T22:41:51.317092Z","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":"2026-08-15T22:41:51.296791Z","title":"Cambridge University Press, 2020","venue":null,"work_id":"b1068939-4d0c-45c7-9dcb-2dca52c51266","year":2020},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.855626Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:7b0c9e95c42595191d2c18f0b9b4c8485a039540be8913083bc4f36d77eabcd4","observation_id":"7f21b72d-67ec-4c3d-a1ae-2dca96501947","resolution":{"observed_at":"2026-08-15T22:41:51.301859Z","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":{"arxiv_id":"2402.09552","last_updated":"2024-05-28T16:27:56Z","snapshot_observed_at":"2026-08-16T14:18:30.741719Z","submitted_at":"2024-02-14T20:05:26Z","title":"STEER: Assessing the Economic Rationality of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09552","snapshot_observed_at":"2026-08-15T22:41:50.860234Z","title":"Rationality report cards: Assessing the economic rationality of large language models.arXiv preprint arXiv:2402.09552, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.860234Z"},"links":{"cited_paper":"/paper/2402.09552","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:19582169b2290ab52ca818f352d5580e2c781c46732448988a7068c5bf702a53","observation_id":"1e12a7a1-ed69-453c-84f9-53e4563cdc14","resolution":{"observed_at":"2026-08-15T22:41:50.860234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12856","last_updated":"2024-12-19T21:25:57Z","snapshot_observed_at":"2026-08-16T13:50:56.049329Z","submitted_at":"2024-05-21T15:13:12Z","title":"LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.12856","snapshot_observed_at":"2026-08-15T22:41:50.865109Z","title":"Llm processes: Numerical predictive distributions conditioned on natural language.arXiv preprint arXiv:2405.12856, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.865109Z"},"links":{"cited_paper":"/paper/2405.12856","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:0427f34c58d5fd95374360fde83ef3a4fb47cb1968978715871af3c3619d7579","observation_id":"8f82cdd9-918e-433e-b114-a39c971a8bc6","resolution":{"observed_at":"2026-08-15T22:41:50.865109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08877","last_updated":"2023-11-15T11:27:44Z","snapshot_observed_at":"2026-08-16T14:43:07.797888Z","submitted_at":"2023-11-15T11:27:44Z","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08877","snapshot_observed_at":"2026-08-15T22:41:50.871546Z","title":"Llamas know what gpts don’t show: Surrogate models for confidence estimation.arXiv preprint arXiv:2311.08877, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.871546Z"},"links":{"cited_paper":"/paper/2311.08877","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:f6fa4000a20d13dd403c8438b56d0234cedcce601ab381d73a0b75b0dbecb9b2","observation_id":"db879c97-fb28-4273-ba7b-119b175ea0b1","resolution":{"observed_at":"2026-08-15T22:41:50.871546Z","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":"2026-08-15T22:41:51.281475Z","title":"Scaling monosemanticity: Extracting interpretable features from Claude 3 Sonnet","venue":null,"work_id":"c2e00382-c182-4916-aa75-1a0827119fea","year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.876665Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:91c5cb84ebb77a8fb793d452c3372bf475e8c3cd6c1f289cafed480b1b204333","observation_id":"a4c0d51f-4811-4d80-ad4e-e7357e28e3cd","resolution":{"observed_at":"2026-08-15T22:41:51.286355Z","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":{"arxiv_id":"2211.00593","last_updated":"2022-11-01T17:08:44Z","snapshot_observed_at":"2026-08-05T06:04:21.031867Z","submitted_at":"2022-11-01T17:08:44Z","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.00593","snapshot_observed_at":"2026-08-15T22:41:50.880976Z","title":"Interpretability in the wild: a circuit for indirect object identification in GPT-2 small.arXiv preprint arXiv:2211.00593, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.880976Z"},"links":{"cited_paper":"/paper/2211.00593","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:6db0ea3a46658031fc4cf9c72ca7a8ddc4047785ffbd0bfcbc15df6dd6967d65","observation_id":"e5fad3e7-c2d3-497b-9c2a-8d904d0f4aea","resolution":{"observed_at":"2026-08-15T22:41:50.880976Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12794","last_updated":"2024-10-31T16:58:51Z","snapshot_observed_at":"2026-08-16T14:25:11.494628Z","submitted_at":"2024-01-23T14:29:17Z","title":"Benchmarking LLMs via Uncertainty Quantification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12794","snapshot_observed_at":"2026-08-15T22:41:50.885772Z","title":"Benchmarking llms via uncertainty quantification.arXiv preprint arXiv:2401.12794, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.885772Z"},"links":{"cited_paper":"/paper/2401.12794","citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:674d6b4627dd40566e82d118b5e79cefceef3e6eb9001b07ba03cf6a08031dd8","observation_id":"57a7a4cc-b903-42ee-bfcb-4c248d6deb4f","resolution":{"observed_at":"2026-08-15T22:41:50.885772Z","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":"2026-08-15T22:41:50.890322Z","title":"Deep sets.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.890322Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:8c74be4c44de3ed1ca0480982964e700ddfb1abf80715e5df9d2837cb4c3a8c9","observation_id":"b800f7a2-af13-4aa8-bf50-6cc5105bffe0","resolution":{"observed_at":"2026-08-15T22:41:50.890322Z","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":"2026-08-15T22:41:50.894781Z","title":"Star: Bootstrapping reasoning with reasoning.Advances in Neural Information Processing Systems, 35:15476–15488, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.894781Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:dd13ebec3f86a351dbfcd858b228400319feef6c1d2e0bc2fc06a0553376cf43","observation_id":"c1666094-f452-42d2-aa6d-562c8f810b87","resolution":{"observed_at":"2026-08-15T22:41:50.894781Z","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":"2026-08-15T22:41:50.899132Z","title":"Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.899132Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:31e2138acb8b46b660c344b465998b2b919d9ff866a7a57a27fcc30d9b682fdf","observation_id":"adbb92fb-9df3-43b8-8591-b540e5e83d19","resolution":{"observed_at":"2026-08-15T22:41:50.899132Z","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":"2026-08-15T22:41:51.236388Z","title":"Incoherent probability judgments in large language models","venue":null,"work_id":"2ec4fd93-d852-4137-9357-ebce43d29d63","year":2024},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.903557Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:b4a736287bb1efeb97fe7abf7e1b598735eb13c47e269a8a75e126341deb711a","observation_id":"91da683d-a3d7-4d47-8a47-0ac0572bb267","resolution":{"observed_at":"2026-08-15T22:41:51.242267Z","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":"2026-08-15T22:41:51.220429Z","title":"<or≤”, “=","venue":null,"work_id":"4e3cec50-de8c-4b21-b5b7-90b9da3074d3","year":2022},"citing_paper":{"arxiv_id":"2505.07883","last_updated":"2025-05-10T19:04:56Z","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:41:50.907910Z"},"links":{"citing_paper":"/paper/2505.07883"},"observation_digest":"sha256:7eb4c102a36305776f7dd460e38ed835c7c20e1e3a655e663287953eb465babe","observation_id":"9e6b385f-042a-4b76-897f-757e631b49d3","resolution":{"observed_at":"2026-08-15T22:41:51.226030Z","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":"2505.07883","last_updated":"2025-05-10T19:04:56Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T22:32:15.166462Z","submitted_at":"2025-05-10T19:04:56Z","title":"Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":0,"verified_fuzzy":12},"total_outbound_references":42},"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 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2505.07883."}