{"as_of":"2026-08-17T15:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:da869a77db15e8c937fdb8d4d7240d5a2aa82b6b3e920fc60f954e503c04389a","coverage":[{"denominator":144,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:37:34.477317Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.03036/citation-record","integrity":"/paper/2509.03036/integrity","json":"/paper/2509.03036/citation-record.json","paper":"/paper/2509.03036"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:33.953571Z","title":"Newton and the relation of mathematics to natural philosophy","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.953571Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:0ed00c0b23480d988a3c3b994eb6045fa527fa66bc5d299c30884b039a3608b6","observation_id":"2e11ef41-d1b1-4c12-b3c4-c16d5ce50ba5","resolution":{"observed_at":"2026-08-15T16:37:33.953571Z","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":"2026-08-15T16:37:33.959386Z","title":"Guicciardini","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.959386Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:c7c4faf853b09d93507ea7fc3d2db7b83bda68655e0c7f4c9fc70d457b7614a4","observation_id":"e8565bb3-56aa-4105-8791-aa24954ef95c","resolution":{"observed_at":"2026-08-15T16:37:33.959386Z","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":"2026-08-15T16:37:33.965050Z","title":"Newton, Maclaurin, and the authority of Mathematics","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.965050Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:89cfb8dc3688ecd2288633f666ffebf4967429033893f5684588f5c8f9611c9c","observation_id":"36f149c6-d1dc-4e54-b301-38dc2ea08a5c","resolution":{"observed_at":"2026-08-15T16:37:33.965050Z","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":"2026-08-15T16:37:33.969981Z","title":"Revisiting the mathematisation thesis: Galileo, Descartes, Newton, and the Language of Na- ture","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.969981Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:9085053f882bce39013d7d8f93e47925b20abf2ee48a40ee8c5095d1e839c702","observation_id":"1d89df72-9cee-4dd5-80c1-4e2f0cee1fa0","resolution":{"observed_at":"2026-08-15T16:37:33.969981Z","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":"2026-08-15T16:37:33.975111Z","title":null,"venue":null,"work_id":null,"year":1973},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.975111Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:6ffdab894514780f7793648eaaeae7e512695593a17549cb60a99b742d6b63f3","observation_id":"b778c5b1-c897-43ee-9a83-3d7868e64382","resolution":{"observed_at":"2026-08-15T16:37:33.975111Z","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":"2026-08-15T16:37:33.980325Z","title":null,"venue":null,"work_id":null,"year":1963},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.980325Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:99a48d00b0d728bb6238a2547d34b122040630515246e9e54fa41bf89b91f0bc","observation_id":"ffa96cd2-778b-45e3-911e-f0203fe36319","resolution":{"observed_at":"2026-08-15T16:37:33.980325Z","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":"2026-08-15T16:37:33.985798Z","title":"Using math in physics: Overview","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.985798Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:98368ac1f9ca46a9bbfe8952ab70c786f7acc5d9284645c9ae75389df092b658","observation_id":"a79c38a1-4666-4f90-9076-c1d05b7c30ca","resolution":{"observed_at":"2026-08-15T16:37:33.985798Z","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":"2026-08-15T16:37:33.990497Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.990497Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:4b043d82b0a96f77d38f1636bbd2d274f30104a750c741be7fac8bc52a7b84f5","observation_id":"0daf4526-43e7-4d39-9041-c395f2f073ae","resolution":{"observed_at":"2026-08-15T16:37:33.990497Z","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":"2026-08-15T16:37:33.995091Z","title":"The mathematization of economic theory","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.995091Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:b34d18b2bd91553c95fd712966225538d9afd886e7c2236363b2e150d859e705","observation_id":"ab5a0015-8c89-4fc3-ad74-b08bd9e0a5ad","resolution":{"observed_at":"2026-08-15T16:37:33.995091Z","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":"2026-08-15T16:37:33.999620Z","title":null,"venue":null,"work_id":null,"year":1954},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:33.999620Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:adc6dba272a065b8cd2f09b28ea881db79d7d3f0713bec60185d8e0a0c4593b5","observation_id":"b9f35dc2-4b15-4a44-bbae-a4a0ed222426","resolution":{"observed_at":"2026-08-15T16:37:33.999620Z","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":"2026-08-15T16:37:34.004501Z","title":"The general theory of relativity","venue":null,"work_id":null,"year":1922},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.004501Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:51af19ce5dcdb7833f73a53d476766317b0dd1e704bfd3a06178413dd6d0a52c","observation_id":"570272f2-3136-4d13-9137-5fecd9c154de","resolution":{"observed_at":"2026-08-15T16:37:34.004501Z","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":"2026-08-15T16:37:34.009296Z","title":"What did mathematics do to physics?","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.009296Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:aa0d74f78811b22df7b727540b4aa94600e9262ab9a951bbae87197c8b1cb164","observation_id":"056b4248-5b82-4c9a-a570-32eb5b7940e5","resolution":{"observed_at":"2026-08-15T16:37:34.009296Z","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":"2026-08-15T16:37:34.013923Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.013923Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:8895fadc299c1b874b10fd694a8d0b8304b95d000287e0d885f6273f0a4b10ab","observation_id":"857eaca5-a187-42b4-9eb2-cd72dce7bb80","resolution":{"observed_at":"2026-08-15T16:37:34.013923Z","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":"2026-08-15T16:37:34.019116Z","title":null,"venue":null,"work_id":null,"year":1962},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.019116Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:9be1079604b018f51680adee8eaba0baf5e7f1f43f60b202551f9ff2b58a2148","observation_id":"9410016d-7e4b-4a9a-aebf-d06090d5460e","resolution":{"observed_at":"2026-08-15T16:37:34.019116Z","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":"2026-08-15T16:37:34.025244Z","title":"Fostering hooks and shifts: Tutorial tactics for guided mathematical discovery","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.025244Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:bbeb593bc397b035bebd4c096538f928bbe8092aed6e14dd700ddbefc7952e8a","observation_id":"0a76e542-e241-47d9-86f9-146865dfbdd6","resolution":{"observed_at":"2026-08-15T16:37:34.025244Z","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":"2026-08-15T16:37:34.030151Z","title":"Naturalising mathematics? a wittgensteinian perspective","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.030151Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:63ff8f1556f173172735ed10684ded01df9c891c14cb0fa43ab801717f2b9a0c","observation_id":"57ea6a0f-5f73-45aa-86a4-173d5dfaab0c","resolution":{"observed_at":"2026-08-15T16:37:34.030151Z","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":"2026-08-15T16:37:34.035294Z","title":"How a scientific discovery is made: A case history","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.035294Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:c31e784dfddd0350a0affc157c922bb95f178aebaaf555a8864d53628af36788","observation_id":"98af6696-09f2-4407-bdf6-81ddc0aee37a","resolution":{"observed_at":"2026-08-15T16:37:34.035294Z","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":"2026-08-15T16:37:34.040296Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.040296Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:d537c866d963d1cb9a7023b2f9a0a762d47f6ced384b8a23a8d0c400790c26ea","observation_id":"ec82076e-0aa2-45ee-9a63-a899dfc018f7","resolution":{"observed_at":"2026-08-15T16:37:34.040296Z","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":"2026-08-15T16:37:34.045211Z","title":"Stevens, V","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.045211Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:a9286029189de1457fdd32d982dfa6210462fbdcd1efa1d9aca4f1dfdce423ba","observation_id":"f451ff9a-3f61-44be-bc37-2d0c17c147ef","resolution":{"observed_at":"2026-08-15T16:37:34.045211Z","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":"2026-08-15T16:37:34.049589Z","title":"AI and science: what 1,600 researchers think","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.049589Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:fb51e8edeff8df2554ec3b669adedcd33e06574fdecbfa6ee28468b5f84ffdd5","observation_id":"665d6cfc-3e23-43f0-82a7-554a9bb0d0e1","resolution":{"observed_at":"2026-08-15T16:37:34.049589Z","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":"2026-08-15T16:37:34.054119Z","title":"On scientific understanding with artificial intelligence","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.054119Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:542eb976df361a7cf794b5abbcdd127992ae7696d55d3509a5617affce8039a5","observation_id":"8e3a1a5e-87b8-410b-9705-dae2531dda59","resolution":{"observed_at":"2026-08-15T16:37:34.054119Z","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":"2026-08-15T16:37:34.058670Z","title":"AI and the transformation of social science research","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.058670Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:0513f5e7ab9c6cd749111cab306b0226787fe89d335aa68f86d150833178bb2d","observation_id":"dead9139-320c-4f3d-b3a4-914a36705fa4","resolution":{"observed_at":"2026-08-15T16:37:34.058670Z","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":"2026-08-15T16:37:34.063384Z","title":"From big data analysis to personalized medicine for all: challenges and opportunities","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.063384Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:3d5af5439f3e8e89b619dbc02f0277e40951ff391de864d46e439a4bc50e379c","observation_id":"6140836e-21c9-4ed4-92c4-33f75c740bdf","resolution":{"observed_at":"2026-08-15T16:37:34.063384Z","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":"2026-08-15T16:37:34.068162Z","title":"Economics in the age of big data","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.068162Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:8ab52f70a4dd9d1d9ba62d6c7e586f3e9d2816148bf25792fcdee3aa55cc6750","observation_id":"2ef42dcd-9512-4455-885a-f31af83601dc","resolution":{"observed_at":"2026-08-15T16:37:34.068162Z","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":"2026-08-15T16:37:34.072939Z","title":"AI meets physics: a comprehensive survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.072939Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:7c3a1e3a1b40f3d8af2cedcd6497576105ee4f96a50bc1b4c24856cc3f3bcdb0","observation_id":"6d24fd63-9efd-4008-b6d5-979f42bc6e55","resolution":{"observed_at":"2026-08-15T16:37:34.072939Z","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":"2026-08-15T16:37:34.077631Z","title":"The artificial intelligence revolution in digital finance in Saudi Arabia: A comprehensive review and proposed framework","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.077631Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:1a055b196709bb7b010ba26dfa5ade57d1c427a62692cadca2af5e1547b6bec2","observation_id":"c6483d8e-5688-42c8-8101-a96dc8f81007","resolution":{"observed_at":"2026-08-15T16:37:34.077631Z","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":"2026-08-15T16:37:34.082806Z","title":"Fifth revolution: Applied AI & human intelligence with cyber physical systems","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.082806Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:0cc548d7967116e4bde62c0b537a57d2a9156abf6fde7777c1be487820ee9cfb","observation_id":"4ae5c8ef-1356-4ebb-98e2-82d257de376d","resolution":{"observed_at":"2026-08-15T16:37:34.082806Z","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":"2026-08-15T16:37:34.087773Z","title":"A survey on explainable artificial intelligence (xai): Toward medical xai","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.087773Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:5dff4949443bf458bf10547abd69164fcd3cc06da50458aff4d44f7700593e18","observation_id":"392fc4b9-50bb-48ee-96a2-57990117427e","resolution":{"observed_at":"2026-08-15T16:37:34.087773Z","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":"2026-08-15T16:37:34.093147Z","title":"Opening the black box: the promise and limitations of explainable machine learning in cardiology","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.093147Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:bdd6df1a5f2274cbdfe5fbd3bb97d32510924b742633323f697611727678272a","observation_id":"c87f9e76-8e79-4969-9ce3-f3007086450b","resolution":{"observed_at":"2026-08-15T16:37:34.093147Z","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":"2026-08-15T16:37:34.100023Z","title":"Opening the black box: interpretable machine learning for geneti- cists","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.100023Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:f17a1d2458b8e07b0b234946d6e24c22b7d4b0d396b5b61e682242660976ca8b","observation_id":"53990504-39be-4f5d-ae08-7aef7b2a877a","resolution":{"observed_at":"2026-08-15T16:37:34.100023Z","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":"2026-08-15T16:37:34.105468Z","title":"Meaningful explanations of black box AI decision systems","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.105468Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:faf7fce6cd9f852bb7864ce83ddb3ab91f99eb35fc83e3cb2fc16eb361da95b2","observation_id":"3e1bb313-52f3-4614-94ee-02e62a71182b","resolution":{"observed_at":"2026-08-15T16:37:34.105468Z","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":"2026-08-15T16:37:34.110667Z","title":"Causability and explainability of artificial intelligence in medicine","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.110667Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:1ecc1622ed8ecb494bc45777434a8514c7c01ad960f401a4d1366f7dc93b23fd","observation_id":"a1aa0c1d-eb62-43c3-891e-feb49bc41100","resolution":{"observed_at":"2026-08-15T16:37:34.110667Z","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":"2026-08-15T16:37:34.115506Z","title":"Interpretable scientific discovery with symbolic regression: a review","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.115506Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:2100061ae9805ed617b4cc9400d22348c6dc2879852338dfb2482930915f574c","observation_id":"8bc44304-b11b-4d2c-9dca-659a3ef02ab6","resolution":{"observed_at":"2026-08-15T16:37:34.115506Z","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":"2026-08-15T16:37:34.120500Z","title":"Kronberger, B","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.120500Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:bd74983045d203b341178a245df58b722895fe63bc63f2239f4920408ddc91f7","observation_id":"505b5008-c48f-45f2-9c55-e194489825a9","resolution":{"observed_at":"2026-08-15T16:37:34.120500Z","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":"2026-08-15T16:37:34.125487Z","title":"Symbolic regression in materials science","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.125487Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:2ba70ca831bc6649e5bc2b0ed3bd92afc107c5def68e256442d7808cd3dde5b8","observation_id":"88098e29-a7a9-40b1-b9d4-e656f04251d1","resolution":{"observed_at":"2026-08-15T16:37:34.125487Z","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":"2026-08-15T16:37:34.130407Z","title":"Artificial intelligence in physical sciences: Symbolic re- gression trends and perspectives","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.130407Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:7c04208c1c1aa8c13e7f820991f1e671533d9a745a68dcc0bd639feae6c6008b","observation_id":"c1e477b9-bac6-48bc-9b55-56f610c51448","resolution":{"observed_at":"2026-08-15T16:37:34.130407Z","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":"2026-08-15T16:37:34.134996Z","title":"AI Feynman: A physics-inspired method for symbolic regression","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.134996Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:fec810ec79edaad0b99151dc004c6b029190546f5c8db5a59737425508877e53","observation_id":"cf55a86a-f199-4861-9822-cc047a718b5c","resolution":{"observed_at":"2026-08-15T16:37:34.134996Z","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":"2026-08-15T16:37:34.139480Z","title":"Distilling Free-Form Natural Laws from Experimental Data","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.139480Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:39589bcee9e351ef2686043f62ee0214fd4d4d1bf0eb6ce5fce85300888fa9a3","observation_id":"6658c938-e11b-44f8-86b2-87c5b9921d99","resolution":{"observed_at":"2026-08-15T16:37:34.139480Z","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":"10.3390/app9142899","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:35.193954Z","title":"Automated Rediscovery of the Maxwell Equations","venue":null,"work_id":"a20ae491-bf97-4f81-853d-e6f386436b29","year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.143960Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:51c0a8147272497245f3f3015c06b0262e6597ebfc363e7c7c67c7c75c1d6223","observation_id":"ee3667cf-a78c-4151-9ea3-198b326661ba","resolution":{"observed_at":"2026-08-15T16:37:35.199422Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T16:37:34.148652Z","title":"Discovering symbolic models from deep learn- ing with inductive biases","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.148652Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:3cd2992c8cfa00d9314fd8f6d58e22be7093859b73699c55f717fdc4ef314d74","observation_id":"f5a6d90e-8bc9-4623-bbd6-99afd0dd8dc7","resolution":{"observed_at":"2026-08-15T16:37:34.148652Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T16:37:34.158314Z","title":"Discovering governing equations from data by sparse iden- tification of nonlinear dynamical systems","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.158314Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:14d87207192b61f0e6e515d3b50ea67fb98ba371564543d4d7073b7e7da8f4ed","observation_id":"3db77944-17f8-4097-9303-c1ad6f1fae0a","resolution":{"observed_at":"2026-08-15T16:37:34.158314Z","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":"2026-08-15T16:37:34.169175Z","title":"Multi-objective symbolic regression for physics-aware dynamic modeling","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.169175Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:349844c9ea629d6d5302410e21b99b489304cc9c1afa16078b4c5f73f83b0d67","observation_id":"7b39ccd7-de95-45a0-964d-16fa3fb8e298","resolution":{"observed_at":"2026-08-15T16:37:34.169175Z","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":"2026-08-15T16:37:34.173778Z","title":"Toward physically plausible data-driven models: A novel neural network approach to symbolic regression","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.173778Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:054fa6d0d72f507a167376f49589a85ddb487e375fabcb11693f25252e07f280","observation_id":"dae79f21-46ea-4e95-b43c-a532f8452586","resolution":{"observed_at":"2026-08-15T16:37:34.173778Z","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":"2026-08-15T16:37:34.179436Z","title":"Effectiveness of generative artificial intelligence for scientific content analysis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.179436Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:25eb6cc349848b6413ff95c8d680469cea7cd2b5494e9b96ef8a7351f1f7c422","observation_id":"235b2bd5-797b-46ea-85e4-57bd86f8847a","resolution":{"observed_at":"2026-08-15T16:37:34.179436Z","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":"2026-08-15T16:37:34.184187Z","title":"Theory-guided data science: a new paradigm for scientific discovery from data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.184187Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:54cd3f312939e1dae1ad20409918e4a47906c8cdd2c5d917ea3e7b3c4582833e","observation_id":"0a406314-b4e3-40cb-b4f0-1fa674d5f50c","resolution":{"observed_at":"2026-08-15T16:37:34.184187Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T16:37:34.189153Z","title":"Automated discovery systems, part 2: new developments, current issues, and philosophical lessons in machine learning and data science","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.189153Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:a5f2aa532f197a7b4f483f2bfc0cc074aaa95318b47cc777c4c9958d44c599c4","observation_id":"36c792f3-e46a-4d14-a44f-c206d1702f0a","resolution":{"observed_at":"2026-08-15T16:37:34.189153Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T16:37:34.193984Z","title":"The rise of self-driving labs in chemical and materials sciences","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.193984Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:d6dced6582fe0b272bb3f5332c039b5e59c857624f91f9107fb3dc904d7095a3","observation_id":"f1cc1633-2fbc-4434-aa78-79c9f933de21","resolution":{"observed_at":"2026-08-15T16:37:34.193984Z","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":"2026-08-15T16:37:34.198683Z","title":"Towards robot scientists for autonomous scientific discovery","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.198683Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:4a24758f536f85cd1685bb6304971ac6a20845edc7eb1ff048e711c268507331","observation_id":"5773b331-e140-433c-8880-e2584b03596b","resolution":{"observed_at":"2026-08-15T16:37:34.198683Z","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":"10.1016/j.coche.2015.07.001","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:35.120790Z","title":"Automatic discovery and optimization of chemical processes","venue":null,"work_id":"4e6e232d-8dcf-47cf-8f6d-a9c07b4bb798","year":2015},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.204148Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:0132a91223c55f25399c25b55a1d99cdd094c14ae62a059b424a9ba44041a89d","observation_id":"e1f543e1-ed58-4c0b-b4e6-ffbfa6a78d30","resolution":{"observed_at":"2026-08-15T16:37:35.126015Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"sconf/2024493","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:36.167555Z","title":"On the issue of automation of processes during scientific research","venue":null,"work_id":"e05c2d8c-3d57-4b8c-9f7a-63b1b4690475","year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.209364Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:c57de06c8c6aecb9c65f5212259e127633bc4025921e3e22d74e3b9d4e2cb5a5","observation_id":"1e2344f7-942a-4bf6-b807-156d96ec13aa","resolution":{"observed_at":"2026-08-15T16:37:36.176900Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1177/17456916221091833","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:35.103738Z","title":"Computational scientific discovery in psychology","venue":null,"work_id":"2e2b6572-e1c7-46ee-88fb-da5e73628ec0","year":2022},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.214014Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:d329e64911ccf25055c9fcc24bf3026e5d309f4bdcf873685cf4a3a75098859c","observation_id":"18efe035-a39e-40d0-956a-fbe9a442887b","resolution":{"observed_at":"2026-08-15T16:37:35.109049Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.02251","last_updated":"2025-05-26T08:59:45Z","snapshot_observed_at":"2026-07-06T15:22:51.488613Z","submitted_at":"2023-05-03T16:35:41Z","title":"Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.02251","snapshot_observed_at":"2026-08-15T16:37:34.218913Z","title":"Kramer, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.218913Z"},"links":{"cited_paper":"/paper/2305.02251","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:e04c192042f4507161ab7ea8f56ebda7fd561b361834f9f5b7eff7fa34b8f472","observation_id":"20d0a5b3-877d-4327-8194-452ad23e89a1","resolution":{"observed_at":"2026-08-15T16:37:34.218913Z","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":"2026-08-15T16:37:34.224732Z","title":"BACON: A Production System That Discovers Empirical Laws","venue":null,"work_id":null,"year":1977},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.224732Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:f5c0ed4cd85a7e7c0e4b8a50517ff0a3e31025910dd6704ab93d7b1a336292ba","observation_id":"8fca339d-f2b4-40be-8128-241f584dad20","resolution":{"observed_at":"2026-08-15T16:37:34.224732Z","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":"2026-08-15T16:37:34.229569Z","title":null,"venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.229569Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:0fc5d8bf2e8e346757ecc186d18525f25589da31d61b84c33e42867038c19f18","observation_id":"88b8084e-f5d5-43d6-a677-bca0c995051e","resolution":{"observed_at":"2026-08-15T16:37:34.229569Z","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":"2026-08-15T16:37:34.234191Z","title":"Discovering dynamics","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.234191Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:360e0f5fa45f3eb350350aa8df8ee4ffcd1d31c50781e3275460c97b69e7b7bf","observation_id":"d78fd7b1-2648-4d1d-a0ef-e52971b361e6","resolution":{"observed_at":"2026-08-15T16:37:34.234191Z","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":"2026-08-15T16:37:34.239354Z","title":"Genetic programming as a means for programming computers by natural selection","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.239354Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:d5ab7deca91b510bb55427f1b5b3c488f4a3ec5631c9ba3c310ae1a17e006b19","observation_id":"628d3675-7a63-45d7-9042-56c37d9cf89e","resolution":{"observed_at":"2026-08-15T16:37:34.239354Z","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":"2026-08-15T16:37:34.245149Z","title":"Discovering dynamics with genetic programming","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.245149Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:ffb85a9d15adb37720ec0ee163851ef7210fd7d5829b84309eceb15b77e6a6ca","observation_id":"38259318-6979-46b9-9590-f4e34032d48b","resolution":{"observed_at":"2026-08-15T16:37:34.245149Z","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":"2026-08-15T16:37:34.249858Z","title":"Functional genomic hypothesis generation and experimentation by a robot scientist","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.249858Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:701927e13eb303cdb35157b01765a5399633ad817d8ac927fc6df205f0b75693","observation_id":"687894b2-5998-4496-b8b8-86c84defba3e","resolution":{"observed_at":"2026-08-15T16:37:34.249858Z","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":"2026-08-15T16:37:34.254573Z","title":"The automation of science","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.254573Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:275047e03daf12d95a92d63b9bd2f0153766e637cf73b9e80df6883fe5ea8ab9","observation_id":"a3d95d72-cd1b-449c-ad1f-e54280b00504","resolution":{"observed_at":"2026-08-15T16:37:34.254573Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1111/phc3.12800","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:35.075990Z","title":"Automated discovery systems, part 1: historical origins, main research programs, and method- ological foundations","venue":null,"work_id":"7df2bc50-0a86-4aa3-91fd-c91274f7bdc9","year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.259383Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:e6b1fc4858f10a7455ca7281367529508e55107363b1cd53bf58854219151443","observation_id":"a111038d-8ac6-4b7e-b00d-adfa03bd2676","resolution":{"observed_at":"2026-08-15T16:37:35.081430Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T16:37:34.264408Z","title":"Toward an artificial intelligence physicist for unsupervised learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.264408Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:b1eae633367a9abb0f535786a8f92768a98975b5d4f06f3556d32d87cca756b3","observation_id":"4b98611d-8f76-4eca-931e-fecb95c84237","resolution":{"observed_at":"2026-08-15T16:37:34.264408Z","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":"2013.65579","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:36.059452Z","title":"Modeling hierarchy using symbolic regression","venue":null,"work_id":"6f9af943-6852-4a76-bb60-2de6a0c7d59c","year":2013},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.269325Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:53cf698201999f54588ac846a536d05ddc071b6289e0eed64eba8bf382d595f1","observation_id":"e72681ed-03d1-42b3-aa50-60afd83a6099","resolution":{"observed_at":"2026-08-15T16:37:36.069340Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-030-39958-0_5","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-17T11:03:46.409680Z","title":"Symbolic regression by exhaustive search: reducing the search space using syntactical constraints and efficient semantic structure deduplication","venue":"Genetic and evolutionary computation","work_id":"b1801b46-5b1e-4d11-aebd-16f2d0d3274b","year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.274267Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:2d61d9d8519b5fd0c2996d68a0b31fd2a4e0dd8b0cb08b6fed70b1024078a269","observation_id":"0a925968-a828-4b8d-9ce0-38f902c645f7","resolution":{"observed_at":"2026-08-15T16:37:35.054637Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.14131","last_updated":"2021-06-27T03:26:35Z","snapshot_observed_at":"2026-08-16T18:14:15.296933Z","submitted_at":"2021-06-27T03:26:35Z","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.14131","snapshot_observed_at":"2026-08-15T16:37:34.279795Z","title":"Symbolicgpt: a generative transformer model for symbolic regression","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.279795Z"},"links":{"cited_paper":"/paper/2106.14131","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:e49c5d40bf815d727c949d84b4c45c99db621441a81da69091e2cac9dae27541","observation_id":"937bd05f-dbb8-4dbc-9831-b003a2e25f20","resolution":{"observed_at":"2026-08-15T16:37:34.279795Z","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":"2026-08-15T16:37:34.285953Z","title":"Interpretable scientific discovery with symbolic regression: a review","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.285953Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:315fcc408f9243194dc8f950fead9bbb27289d6e262fbbbc42b0aa83d3ef47c7","observation_id":"f8d5c2bd-8679-4c51-8e76-45f0ebb79661","resolution":{"observed_at":"2026-08-15T16:37:34.285953Z","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":"10.1016/j.neucom.2017.10.047","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:35.005679Z","title":"Block building programming for symbolic regression","venue":null,"work_id":"6a449c33-a30d-434f-bfb5-a5627bb6f122","year":2018},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.291860Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:6ed11f2fdad24f349e2ca396d7dff5b8405cb4f7d7950c3d7e9714ad05afede8","observation_id":"a4eeb508-0648-4cba-991a-5b22d2b58fa1","resolution":{"observed_at":"2026-08-15T16:37:35.010938Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.08892","last_updated":"2020-01-16T02:11:21Z","snapshot_observed_at":"2026-08-13T21:34:01.334892Z","submitted_at":"2019-10-20T04:28:50Z","title":"Bayesian Symbolic Regression","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.08892","snapshot_observed_at":"2026-08-15T16:37:34.296957Z","title":"Bayesian symbolic regression","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.296957Z"},"links":{"cited_paper":"/paper/1910.08892","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:8bc946ae4921817c80c3dbd361c6bada32608fff9c39acc154d86a85dcd364f6","observation_id":"d6921f5b-af1c-4e81-b9c1-ccbcbf978208","resolution":{"observed_at":"2026-08-15T16:37:34.296957Z","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":"2026-08-15T16:37:34.308470Z","title":"A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.308470Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:fa7364dd660b6c51a913b4cf870353e8aaa9012f52ec9c86656bcb4d499c6b21","observation_id":"5513ca02-b17d-49e1-808f-de90b42a995c","resolution":{"observed_at":"2026-08-15T16:37:34.308470Z","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":"2026-08-15T16:37:34.313314Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.313314Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:b3d338aa0c0af49942a8d86f4ad44fd5e26de2d1ed1af4a027777d5c8ad59814","observation_id":"e2b9525f-20cb-4517-b22c-9e6c9ecf9cc2","resolution":{"observed_at":"2026-08-15T16:37:34.313314Z","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":"2026-08-15T16:37:34.318363Z","title":"The science of brute force","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.318363Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:6f85a8958156872a1f57c43f8bf34192d1dd86c084392f7bee1b9d7cc619cc47","observation_id":"980fea65-41c3-414e-8c68-847e41030e5c","resolution":{"observed_at":"2026-08-15T16:37:34.318363Z","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":"2026-08-15T16:37:34.323548Z","title":"Discovering governing equations from data by sparse iden- tification of nonlinear dynamical systems","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.323548Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:a3c6d65ccada6bc33b4b2fd13e267ca259ab6691acce9af5fb14fa8f83367fa1","observation_id":"e99cefb6-9a1f-4ced-9975-a7c690f98dc3","resolution":{"observed_at":"2026-08-15T16:37:34.323548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.08481","last_updated":"2022-01-26T04:49:48Z","snapshot_observed_at":"2026-08-16T17:42:12.291700Z","submitted_at":"2021-11-12T19:01:23Z","title":"PySINDy: A comprehensive Python package for robust sparse system identification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.08481","snapshot_observed_at":"2026-08-15T16:37:34.329147Z","title":"PySINDy: A comprehensive Python package for robust sparse system identifica- tion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.329147Z"},"links":{"cited_paper":"/paper/2111.08481","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:b6601fe56bac12f073d674f39f23f1ab242381b0b149bde942abd956f5c46bde","observation_id":"20ed31af-612f-484c-9cc4-957d7e60c5a6","resolution":{"observed_at":"2026-08-15T16:37:34.329147Z","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":"2026-08-15T16:37:34.334384Z","title":"Contemporary Symbolic Regression Methods and Their Relative Performance","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.334384Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:92ef46e8288076099a2de2e8baa3c93ec0a9315ba3ed212128c57b7c838f08db","observation_id":"4fc7fa51-1af9-40fc-93b0-3459cd7ca64f","resolution":{"observed_at":"2026-08-15T16:37:34.334384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.04871","last_updated":"2021-04-05T22:29:16Z","snapshot_observed_at":"2026-08-15T22:16:07.409239Z","submitted_at":"2019-12-10T18:25:48Z","title":"Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.04871","snapshot_observed_at":"2026-08-15T16:37:34.339293Z","title":"Deep symbolic regression: recovering mathematical expressions from data via risk-seeking policy gradients","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.339293Z"},"links":{"cited_paper":"/paper/1912.04871","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:fe5c53ebf578744de8ba3e64d26d1823689ec2084d4c427744abaa3b58330ad6","observation_id":"67226221-57f1-41fd-bbe7-1d03fb73bd4b","resolution":{"observed_at":"2026-08-15T16:37:34.339293Z","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":"2026-08-15T16:37:34.344769Z","title":"Where are we now?","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.344769Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:3cacc4936854664451cf272bd7d8152eee870edd354e53b80b38effee14157aa","observation_id":"a09f0c1c-6add-4ab7-8efa-cad732aa53b9","resolution":{"observed_at":"2026-08-15T16:37:34.344769Z","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":"2026-08-15T16:37:34.349622Z","title":"Improving model-based genetic pro- gramming for symbolic regression of small expressions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.349622Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:f9f29843c67b68ec7f3378bebc2b116a5ef434a579a6f8d5c6f35ef2d7a9568d","observation_id":"4bd51944-c7c6-4951-b923-e761cf2a0a8d","resolution":{"observed_at":"2026-08-15T16:37:34.349622Z","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":"2026-08-15T16:37:34.354495Z","title":"Genetic Programming in Python, with a scikit-learn inspired API: gplearn","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.354495Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:55fb871f51f2a843c29e37b5e8afecde0ca4d0566c7f10c12389687cd74a517d","observation_id":"553e26b1-27d7-4b18-b5f2-ea1aca20fb95","resolution":{"observed_at":"2026-08-15T16:37:34.354495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15569","last_updated":"2023-01-08T22:52:55Z","snapshot_observed_at":"2026-08-16T16:56:26.247271Z","submitted_at":"2022-05-31T07:20:17Z","title":"GSR: A Generalized Symbolic Regression Approach","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15569","snapshot_observed_at":"2026-08-15T16:37:34.359275Z","title":"GSR: A Generalized Symbolic Regression Approach","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.359275Z"},"links":{"cited_paper":"/paper/2205.15569","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:b5242baad267ad12bbe2d5db76734f521c833bd554b76bacf1f829ad3e41e077","observation_id":"b4a46439-1d79-4d74-bb5a-818c4aafdbc9","resolution":{"observed_at":"2026-08-15T16:37:34.359275Z","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":"2026-08-15T16:37:34.364768Z","title":"A Unified Framework for Deep Symbolic Regression","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.364768Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:d08f5ad2755419c309b10b546540171c16e5f3c7ffcdb2777639273e8c38ff9b","observation_id":"b7c63cd8-dab9-41fa-a9b0-d7e77f7c7471","resolution":{"observed_at":"2026-08-15T16:37:34.364768Z","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":"10.24963/ijcai.2024/651","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:34.907189Z","title":"Vertical Symbolic Regression via Deep Policy Gradient","venue":null,"work_id":"6dc02f50-c893-415f-b4b3-cd31e7716b68","year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.370157Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:f961c423a3b69870972779e7bb2055bdfdab5c3f42d9ff2744faa837928f1ae3","observation_id":"5c166512-ccc8-4c18-90d0-bece5e5ebcc7","resolution":{"observed_at":"2026-08-15T16:37:34.912287Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T16:37:34.375200Z","title":"A new formulation for symbolic regression to identify physico-chemical laws from experimental data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.375200Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:97edb0eb53b8f39e3766d84463c19e97413073f9f714a8c7434a98f65ece3ff9","observation_id":"16e4b5a1-ac41-4c66-9b8f-91c41e07e21c","resolution":{"observed_at":"2026-08-15T16:37:34.375200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.04825","last_updated":"2020-08-13T18:40:43Z","snapshot_observed_at":"2026-07-06T08:43:28.341292Z","submitted_at":"2019-12-10T17:07:52Z","title":"Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.04825","snapshot_observed_at":"2026-08-15T16:37:34.380811Z","title":"Integration of neu- ral network-based symbolic regression in deep learning for scientific discovery","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.380811Z"},"links":{"cited_paper":"/paper/1912.04825","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:dd7642a87e9b667d7c25514a55dbbab64e1a36d77e45002147df6148bb574600","observation_id":"048059f8-54f9-4af4-b8f5-964f6e215eef","resolution":{"observed_at":"2026-08-15T16:37:34.380811Z","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":"2026-08-15T16:37:34.386531Z","title":"Racing control variable genetic programming for symbolic regression","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.386531Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:612d76f97e82f7b128859cb487d91c935e318a76def5e62fe91b8c3f8aa5e438","observation_id":"98609c69-fce7-43b8-a1f5-a599e064d7cf","resolution":{"observed_at":"2026-08-15T16:37:34.386531Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2021.11521","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:35.784211Z","title":"Multi-objective symbolic regression for physics-aware dynamic modeling","venue":null,"work_id":"5bfda5e3-c6e0-4d35-9f13-810ecfee59d7","year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.391334Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:8f69b3ea063e67fd40bf2040a35cf062733e5338ce0991995164b15d2d50cce5","observation_id":"4fd02e25-867a-4c16-8d01-475d8e2887f4","resolution":{"observed_at":"2026-08-15T16:37:35.793383Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.07839","last_updated":"2024-12-10T19:00:01Z","snapshot_observed_at":"2026-08-16T23:45:05.686589Z","submitted_at":"2024-12-10T19:00:01Z","title":"Symbolic regression for precision LHC physics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.07839","snapshot_observed_at":"2026-08-15T16:37:34.396459Z","title":"Symbolic Regression for Preci- sion LHC Physics","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.396459Z"},"links":{"cited_paper":"/paper/2412.07839","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:120a88556b9e3cb31f07fb2915cf0be51b60b1f8a977e8db6366f34a2f252a7b","observation_id":"64aa1354-28c9-4f12-a736-60c18eec2e76","resolution":{"observed_at":"2026-08-15T16:37:34.396459Z","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":"2026-08-15T16:37:34.402586Z","title":"Data-driven discovery of tsallis-like distribution using symbolic regression in high-energy physics","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.402586Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:b0bda82bf3feefd8262ff3a9b476011d33da9b78edc9939ddba78cfb7deea556","observation_id":"158c80b7-42ee-41a9-82d2-d0fa4f03d7bd","resolution":{"observed_at":"2026-08-15T16:37:34.402586Z","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":"2026-08-15T16:37:34.407746Z","title":"Deep symbolic regression for physics guided by units con- straints: toward the automated discovery of physical laws","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.407746Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:dc25a12b77059b774c9b1827cf3e597737cf419e17b382cf36a7d4ac328c2ee5","observation_id":"225ff0f4-31c8-401a-b3e3-db346df50f4a","resolution":{"observed_at":"2026-08-15T16:37:34.407746Z","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":"2026-08-15T16:37:34.413067Z","title":"Ai feynman: a physics-inspired method for symbolic regression","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.413067Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:f701424e0aa0eb12dea0a0b9523f5064f9c9518a93a222aaba6f75a652f4ebeb","observation_id":"837d6d9e-7c8f-4282-b27b-0711ffd4b4b1","resolution":{"observed_at":"2026-08-15T16:37:34.413067Z","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":"2026-08-15T16:37:34.419753Z","title":"Physics-informed learning of governing equations from scarce data","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.419753Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:d4dc400557346cec9f8fb36833122a919fbe7de851e0a143268763ab89630118","observation_id":"8f31e15d-851b-4103-9cbb-a452810736a9","resolution":{"observed_at":"2026-08-15T16:37:34.419753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02995","last_updated":"2016-10-10T16:47:36Z","snapshot_observed_at":"2026-08-15T22:16:06.908843Z","submitted_at":"2016-10-10T16:47:36Z","title":"Extrapolation and learning equations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02995","snapshot_observed_at":"2026-08-15T16:37:34.424911Z","title":"Extrapolation and learning equations","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.424911Z"},"links":{"cited_paper":"/paper/1610.02995","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:109be0270d6219f9d1ebc67e60a852dcdb13f0d610f1f8350258b6e38ca21b75","observation_id":"6ffffe62-fe09-4d75-b904-5b9867369ae7","resolution":{"observed_at":"2026-08-15T16:37:34.424911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09579","last_updated":"2024-05-14T18:09:43Z","snapshot_observed_at":"2026-08-16T13:52:42.201145Z","submitted_at":"2024-05-14T18:09:43Z","title":"Scalable Sparse Regression for Model Discovery: The Fast Lane to Insight","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.09579","snapshot_observed_at":"2026-08-15T16:37:34.430684Z","title":"Scalable Sparse Regression for Model Discovery: The Fast Lane to Insight","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.430684Z"},"links":{"cited_paper":"/paper/2405.09579","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:d3337ee04b5974db8636de7026dc7daede003ed23af1f29e82b15e3fca824297","observation_id":"643d1b20-d43a-41c3-84f9-cc12d90248a5","resolution":{"observed_at":"2026-08-15T16:37:34.430684Z","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":"2026-08-15T16:37:34.435637Z","title":"Large language models are zero- shot rankers for recommender systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.435637Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:7069262ba25517b783f3fe8e65dadf454bdc962a913063342abad99f5257d5a0","observation_id":"e5021f0b-f677-453d-b6cf-7ca8bf2fc600","resolution":{"observed_at":"2026-08-15T16:37:34.435637Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19860","last_updated":"2024-06-18T08:07:01Z","snapshot_observed_at":"2026-08-16T15:27:55.763190Z","submitted_at":"2023-05-31T13:51:26Z","title":"A Survey on Large Language Models for Recommendation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19860","snapshot_observed_at":"2026-08-15T16:37:34.440978Z","title":"A survey on large language models for recommendation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.440978Z"},"links":{"cited_paper":"/paper/2305.19860","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:03e754d95a23119af00e9ba1e35dadc0ce689986e0e64f53c1a9acfab85c9236","observation_id":"5288f29c-f5aa-4024-a455-e87c916abd2f","resolution":{"observed_at":"2026-08-15T16:37:34.440978Z","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":"2026-08-15T16:37:34.446231Z","title":"Recommender systems in the era of large language models (llms)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.446231Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:3c188365ffdbe4c5b1bd09bdbd2542356065ff381ddb899e05f6a53845ef1abb","observation_id":"e9f3538a-7c44-4f5b-a65c-05422803a2ba","resolution":{"observed_at":"2026-08-15T16:37:34.446231Z","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":"10.18653/v1/2023.acl-long.186","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:34.852127Z","title":"Decoding symbolism in language models","venue":null,"work_id":"778e32bb-160b-4fe3-bac5-fdb47baf0c3d","year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.451037Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:6e72269fe253155905214675b21cbbc6768cea4d7a454091cf6e54f57431e510","observation_id":"f756c714-bfd2-4a8f-afcd-b5667a34ea1b","resolution":{"observed_at":"2026-08-15T16:37:34.857119Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T16:37:34.456444Z","title":"Open-source solution for evaluation and benchmarking of large language models for public health","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.456444Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:5feac51377130fb99d710ca90407548a61648a88667bf52b9e83f4a81229ddb8","observation_id":"958ed20f-66dd-49a0-bfb5-7de93968bd84","resolution":{"observed_at":"2026-08-15T16:37:34.456444Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1002/cpt.3161","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:08:47.750906Z","title":"Applications of advanced natural language processing for clinical pharmacology","venue":"Clinical Pharmacology & Therapeutics","work_id":"ed8c933d-8b46-4926-b2e0-5eacc8081166","year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.461227Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:a227e24660a472694b5b6e03ce33093a0851410fa0e72907c618b2c628a2a73b","observation_id":"f2cff705-0fa9-4436-bee4-e18f21b3c1ea","resolution":{"observed_at":"2026-08-15T16:37:34.841017Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11343","last_updated":"2024-06-01T07:08:49Z","snapshot_observed_at":"2026-08-16T14:00:07.969945Z","submitted_at":"2024-04-17T13:03:07Z","title":"Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11343","snapshot_observed_at":"2026-08-15T16:37:34.466616Z","title":"Large Language Models meet Collaborative Fil- tering: An Efficient All-round LLM-based Recommender System","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.466616Z"},"links":{"cited_paper":"/paper/2404.11343","citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:fb00c9826345e4a42d96e2d35cc66e5ee0ded0d4e8e63760cc077507fba3b074","observation_id":"2f4b7ca2-fc4f-44ba-a9bf-0c4689fd6964","resolution":{"observed_at":"2026-08-15T16:37:34.466616Z","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":"2026-08-15T16:37:34.471958Z","title":"Once: Boosting content-based recommendation with both open- and closed-source large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.471958Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:91aae1a8c559a70595aa7fc07f5abafaa7ec653f4a367653621faf458f6e3ba9","observation_id":"b4383a3a-5e21-4151-8a3a-bffef60a9607","resolution":{"observed_at":"2026-08-15T16:37:34.471958Z","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":"2026-08-15T16:37:34.477317Z","title":"Leveraging large language models for sequential recommendation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:34.477317Z"},"links":{"citing_paper":"/paper/2509.03036"},"observation_digest":"sha256:06e9a53670d37c744f874aa7fd842c94fd4d2b74f2ba9c5aa6cdce1b8a2bed16","observation_id":"a12fbab3-8256-409c-ac1d-d8d894a61f14","resolution":{"observed_at":"2026-08-15T16:37:34.477317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.03036","last_updated":"2025-09-03T05:53:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T14:11:01.020682Z","submitted_at":"2025-09-03T05:53:40Z","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":6,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":82,"verified_exact":10,"verified_fuzzy":0},"total_outbound_references":144},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 100 of 144 outbound references and 0 inbound Pith citation observations for arXiv:2509.03036."}