{"as_of":"2026-08-17T16:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8e054cb8fefde656c68aaa90229c6790227abc1f5d7bd3a4955e9e70b365b2b8","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:43:46.995409Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"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/2608.04285/citation-record","integrity":"/paper/2608.04285/integrity","json":"/paper/2608.04285/citation-record.json","paper":"/paper/2608.04285"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:48.068448Z","title":"Boxe: a box embedding model for knowledge base completion","venue":null,"work_id":"c9e97e7b-a26c-4cc5-9f9e-1963ee6258fd","year":2020},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.790789Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:c8ee80d5b94a2c501b04cb5d63b09bc89193e935e73a148cb8a805c0ef7fd6a9","observation_id":"c7fb15cc-c994-4774-b039-aeb29b558513","resolution":{"observed_at":"2026-08-15T14:43:48.075622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:48.052889Z","title":"Lie point symmetry and physics-informed networks.Advances in Neural Information Processing Systems, 36:42468–42481, 2023","venue":null,"work_id":"5db17bd1-4a05-45c0-83c2-f6ed4e746d1f","year":2023},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.799607Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:e3b7f04aeb35b31de98c8aad8836263b61a27c4a1432d76e99bac544dbfe2168","observation_id":"f6100829-bb46-4b65-be45-baf463937a21","resolution":{"observed_at":"2026-08-15T14:43:48.057726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2108.07732","last_updated":"2021-08-16T03:57:30Z","snapshot_observed_at":"2026-08-15T17:40:38.050939Z","submitted_at":"2021-08-16T03:57:30Z","title":"Program Synthesis with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07732","snapshot_observed_at":"2026-08-15T14:43:46.804733Z","title":"Program synthesis with large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.804733Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:3c0f58bd04b0cd45b63d4fcdcda763a48ec7fc38c1cbe8d125abd4375bfb353b","observation_id":"eb20eb6f-0443-463c-b9c2-f70fb8a01602","resolution":{"observed_at":"2026-08-15T14:43:46.804733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:48.038042Z","title":"Logic tensor net- works.Artificial Intelligence, 303:103649, 2022","venue":null,"work_id":"199eb48b-a7ac-4b63-be70-d7c8ce0d7d03","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.811321Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:ccc9341e70c5548a6e042edeab3db913f257636f9f5b57b50b94a5cbe953eb8b","observation_id":"4d4c21be-3b5e-409f-9d16-000e7d7a7c26","resolution":{"observed_at":"2026-08-15T14:43:48.042763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2603.27116","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.619995Z","title":"The price of meaning: Why every semantic memory system forgets, 2026","venue":null,"work_id":"45c5888b-a85b-497c-a3ee-dc7ab8caf814","year":2026},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.816352Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:023b882236aaddff695a9c6d595c9b964732554ad704581fd5f1a0d6691e4c66","observation_id":"4716ce6b-a025-4600-a4e8-283358eb9671","resolution":{"observed_at":"2026-08-15T14:43:47.629066Z","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":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:48.021856Z","title":"E(3)-equivariant graph neural networks for data- efficient and accurate interatomic potentials.Nature Communications, 13(1):1–11, 2022","venue":null,"work_id":"8279326b-3705-46ee-bc84-ae2805c572e0","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.821844Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:e6c68a2280f889ab4e0fc9bc4efb12a5268642951b90914df8288cbff234d6d9","observation_id":"e21409cd-dbc6-43c4-bffc-b77f86b8aaac","resolution":{"observed_at":"2026-08-15T14:43:48.027358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:48.006461Z","title":"Lamb, Priscila Vieira Lima, Leo de Penning, Gadi Pinkas, et al","venue":null,"work_id":"26c9dc0f-6acc-4626-8ac4-21e162615e57","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.827401Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:026cab2711886e1ecd9906d96ace2affd97e31a3fa9dc0b026028c6bf4165dfe","observation_id":"c72f064f-1a53-426c-8d42-557cea3b5871","resolution":{"observed_at":"2026-08-15T14:43:48.011169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T14:43:46.832245Z","title":"Automated program refinement: Guide and verify code large language model with refinement calculus.Proc","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.832245Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:46f74d2771dd533ebcc1ee36fe1fdf0738cb6748d3f12591360b7f8263fc5f6c","observation_id":"b317cb61-df37-40c2-9c43-56f0c7a1855f","resolution":{"observed_at":"2026-08-15T14:43:46.832245Z","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":"2026-08-15T14:43:46.837876Z","title":"Knowledge graph completion: A review.IEEE Access, 8:192435–192456, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.837876Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:a76aa764e388d9d2bf422903fa323688158b5c808a71835a0831e5afca41c2f0","observation_id":"04493df0-edde-41b0-86d1-b242ee6260a3","resolution":{"observed_at":"2026-08-15T14:43:46.837876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.990661Z","title":"Evolving sci- entific discovery by unifying data and background knowledge with ai hilbert.Nature Communications, 15(1):5922, 2024","venue":null,"work_id":"7c577d6c-a5c3-41ba-9b14-65e6d8fd1fdb","year":2024},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.842728Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:13d2e30ddf7d6a4ff6dae60847780379e540681562014901d9cae8598d5085bf","observation_id":"dd88da56-9366-4bb9-be8c-7ea246184d97","resolution":{"observed_at":"2026-08-15T14:43:47.995412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.975636Z","title":"Inductive logic programming at 30: A new introduction","venue":null,"work_id":"8f64433b-06e8-4916-9b32-42d7503a37ad","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.847737Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:ceb54cebb93106c159679e950f507bc3e41a2cd07e632ea0cbb512a2646e4362","observation_id":"b3f53349-1566-4a06-a99c-8ce1da585774","resolution":{"observed_at":"2026-08-15T14:43:47.980552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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/s10915-022-01939-z.pdf","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.107489Z","title":"Scientific machine learning through physics-informed neural networks: Where we are and what’s next.Journal of Scientific Computing, 92(3):1–56, 2022","venue":null,"work_id":"724b3cd8-397b-47e6-89c5-2ffa1b82a922","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.852600Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:f12f3f287098daad8781bc4fc29265e94652f84b2e1bb4cc86e06e75d7fe9718","observation_id":"ec8e18b4-a6f5-4f5a-ba58-863ac3067046","resolution":{"observed_at":"2026-08-15T14:43:47.112915Z","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":"2026-08-15T14:43:46.857215Z","title":null,"venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.857215Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:c73f0383d4dd359fc3fb5d5e061757555cb2fc3a7bac7335d5ff651b8ea2655f","observation_id":"ff393096-88ee-40c3-a6e3-8365168f4613","resolution":{"observed_at":"2026-08-15T14:43:46.857215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.960779Z","title":"Lamb, and Dov M","venue":null,"work_id":"a5158661-05f7-4811-8e15-b5375122879b","year":2009},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.862300Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:27416b8ccc900cfd3e88652e9cd1fcd4ba0bb3ab8f739a58c6e22ff08aa1999e","observation_id":"7dd9cdd8-e1f9-460f-b314-27f4a823b0dd","resolution":{"observed_at":"2026-08-15T14:43:47.965584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.947678Z","title":"Discovering faster matrix multiplication algorithms with reinforcement learning.Nature, 610 (7930):47–53, 2022","venue":null,"work_id":"da139ab1-a9e7-45d8-beda-7653d997532b","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.866800Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:84d1583c55a22410e9c0a8d8e073dc7def3c5721c7883af5dd99ba2e6eed593a","observation_id":"10f6f1fc-7130-4c7f-9ee5-4e77d7f956ed","resolution":{"observed_at":"2026-08-15T14:43:47.951820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T14:43:46.871298Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.871298Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:8a1ad93a640a0ff47394ede835d4ec64681f08eecfb33c047ad59847a788c388","observation_id":"a2c80bfb-d115-4d7a-b209-47ca77f4e415","resolution":{"observed_at":"2026-08-15T14:43:46.871298Z","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":"2026-08-15T14:43:46.876100Z","title":"CCN+: A neuro-symbolic framework for deep learning with requirements.International Journal of Approximate Reasoning, 171:109124, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.876100Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:30c4277df44da57dd0e7a1697a9951fe7edae00a1fee413d078a07dea68e7c6d","observation_id":"fbb142c0-12ab-41d6-8a02-a39d8c51cab3","resolution":{"observed_at":"2026-08-15T14:43:46.876100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.934042Z","title":"Hamiltonian neural networks.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"f6592708-2d8a-4468-ad14-57a43046d6bc","year":2019},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.880541Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:3099760843c9d7df90091dd5ba8b866e9f2d8bee5cd0a28b107b7636e7adb48e","observation_id":"0188a278-9188-4cc8-a90e-51c8e57ca90f","resolution":{"observed_at":"2026-08-15T14:43:47.938263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T14:43:46.885118Z","title":"Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab, and Antoine Zimmermann","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.885118Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:262a5e5e3678a0cec851bebbfe9423da9f59eda75dceac07b58c5efb3df93fde","observation_id":"0f14e4a9-5e15-4939-a33c-79ddd0b161dc","resolution":{"observed_at":"2026-08-15T14:43:46.885118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.10872","last_updated":"2018-12-12T09:56:40Z","snapshot_observed_at":"2026-08-14T19:10:25.760336Z","submitted_at":"2018-05-28T11:33:00Z","title":"DeepProbLog: Neural Probabilistic Logic Programming","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.10872","snapshot_observed_at":"2026-08-15T14:43:46.890220Z","title":"DeepProbLog: Neural probabilistic logic programming","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.890220Z"},"links":{"cited_paper":"/paper/1805.10872","citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:934f723e94fca12d33928e2ba3626d01d60a328317de3b88aa3ca34c047551f8","observation_id":"5d5b43cd-fa9e-4daa-9e8e-c6d6ad722a55","resolution":{"observed_at":"2026-08-15T14:43:46.890220Z","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":"10.1007/978-3-030-30179-8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-17T11:03:46.409680Z","title":"An in- troduction to anyburl","venue":"Lecture notes in computer science","work_id":"fecfdcb2-76b9-4fd6-95b3-73ce358fa840","year":2019},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.894857Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:10d6f8857c986a07bcf08d3e0cb74621bbfb0a2baeb44523c80dbbace885a4b7","observation_id":"079e99c6-9788-4419-9faa-94eca606dcc5","resolution":{"observed_at":"2026-08-15T14:43:47.070907Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.919116Z","title":"Pearl and D","venue":null,"work_id":"363eec6f-6ecf-4460-9a1f-7a67c1c30a49","year":2018},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.900536Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:257ce7708ce66a4dac9f84b3436895a96c9d8aa543f4a6b1e499ee5a3d8c64b8","observation_id":"458e6e5a-a107-401a-9982-d1b7a6558d09","resolution":{"observed_at":"2026-08-15T14:43:47.923639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.901769Z","title":"Cambridge University Press, 2000","venue":null,"work_id":"9f021b88-863d-4645-9060-b7d4a721cced","year":2000},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.905398Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:3d651a5603e36cec6e81876af88215b896782ca040a935661eab1c540d322fab","observation_id":"610a29cf-f375-4009-b65f-ffb5c55d1eb0","resolution":{"observed_at":"2026-08-15T14:43:47.907743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.884061Z","title":"Purohit, Y","venue":null,"work_id":"c6923248-4f48-4762-b250-75d48fd1ef54","year":2024},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.910448Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:af708a23629f3fc3b9f5c8ce3bb09043d5b9e12ad517f568faa18cfbeac3a551","observation_id":"0da5529c-752a-4220-bab0-7a5abfb83e5f","resolution":{"observed_at":"2026-08-15T14:43:47.889073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.864570Z","title":null,"venue":null,"work_id":"11f7f9ef-ff4f-4b99-8b0d-638a82a0542d","year":2019},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.916051Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:e987435078b1c662af159e6f90f5592d633b0975003895fb85dad9619ac8248e","observation_id":"5d9c7b72-eafd-4346-8c05-4afc898c2b5d","resolution":{"observed_at":"2026-08-15T14:43:47.869746Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.848985Z","title":"Toolformer: Language models can teach them- selves to use tools.Advances in Neural Information Processing Systems, 36:68539–68551, 2023","venue":null,"work_id":"789b2376-8b25-4286-95b0-819610eb77a9","year":2023},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.927294Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:17b017634353aeec5ddb0de02810946b791bb7326c8797a597d01d6b9daf5ec6","observation_id":"aad64a98-c4ad-4ca2-80bf-2a4186a7c23e","resolution":{"observed_at":"2026-08-15T14:43:47.853763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.832692Z","title":"Toward causal representation learning.Proceedings of the IEEE, 109(5): 612–634, 2021","venue":null,"work_id":"822af354-4de8-4738-bbc2-408698e6b6ab","year":2021},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.932523Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:61ff8ef4ee89a07b33a3a1586cf13b3537a3cc3a1caf8a586fe5cb37d9da604e","observation_id":"7c018599-b75c-432d-aa1f-e00777a928ed","resolution":{"observed_at":"2026-08-15T14:43:47.837924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.813362Z","title":"Estimating the causal impact of recommendation systems from observational data","venue":null,"work_id":"6f1efb05-c72f-4475-86a1-48442ba03cae","year":2015},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.937377Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:75299f9bc036b6bc0369a5b466a1f712ec2a5a7fb7220b52cb6f7a0a34f839b6","observation_id":"e53a6ac0-98ce-4c61-8e23-bf8b20443e00","resolution":{"observed_at":"2026-08-15T14:43:47.821204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T14:43:46.942915Z","title":"Mastering the game of go with deep neural networks and tree search.nature, 529(7587):484–489, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.942915Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:fdc2e49c8cae646c9c8876616517497e1a9610ea0d520afafca9403b0babe549","observation_id":"ecdc990b-0f44-48d2-9034-87582605cf64","resolution":{"observed_at":"2026-08-15T14:43:46.942915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.783509Z","title":"ViperGPT: Visual inference via python execution for reasoning","venue":null,"work_id":"b4c8ca13-015a-4b01-8931-422ed0f93917","year":2023},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.948168Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:6a7d071ef0d8eb529b4f81b140c731724a6e9ad2c70a74b636844fc845b9fcf8","observation_id":"a4429aeb-3ef9-419c-9589-eb9055167b6c","resolution":{"observed_at":"2026-08-15T14:43:47.788544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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/s10489-021-02394-3","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.050196Z","title":"Modular design patterns for hybrid learning and reasoning systems: a taxonomy, patterns and use cases.Applied Intelligence, 51(9):6528–6546, September 2021","venue":null,"work_id":"629b4d0d-08c2-46e1-9d92-e9b92da99747","year":2021},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.953330Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:9b8ff31388861f78c47248c9e2256e3e61d3612e8b2519cda6b652e725b079e9","observation_id":"96aa9b43-4de0-40c0-a9df-5a16e5e676a3","resolution":{"observed_at":"2026-08-15T14:43:47.054816Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.766018Z","title":"Elsevier, 2008","venue":null,"work_id":"0911f4bc-318a-46f8-aeda-3904246b8ef1","year":2008},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.960451Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:64b7fc861fd3b2ff3cbf6fd14404f682fe18d0008ec2fa8cdf453883fc3ceb2d","observation_id":"a7ad16af-ce1d-4a5e-b519-9fc70916735d","resolution":{"observed_at":"2026-08-15T14:43:47.771356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.746390Z","title":"Analyzing differentiable fuzzy logic opera- tors.Artificial Intelligence, 302:103602, 2022","venue":null,"work_id":"3bfcf374-993f-4bc0-a250-8b60985c5a6a","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.965074Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:75066edb1b2f16d143dcf28248997e7ae00e86ddaf34f00d333cffd129e332d4","observation_id":"00954cf0-56bf-4064-8d15-474b68ab0ed2","resolution":{"observed_at":"2026-08-15T14:43:47.751864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T14:43:46.970658Z","title":"Informed machine learning – a taxonomy and survey of integrating prior knowledge into learning systems.IEEE Transactions on Knowledge and Data Engineering, 35(1):614–633, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.970658Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:83ed51d69c8a712525fb3356a3a925dbb77f9cd89f574d33bc18589a1bd5f4f3","observation_id":"0a684697-0c97-4231-a45a-b604f988da03","resolution":{"observed_at":"2026-08-15T14:43:46.970658Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.724540Z","title":"CodeARC: Benchmarking reasoning capabilities of llm agents for inductive program synthesis","venue":null,"work_id":"cf478ab9-3bac-4720-9c87-c1191105088e","year":2025},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.976516Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:dbc969b58a964de1685b5c7a70cf382c60aaae35f9c37a7bfdcc78deb6fc3efb","observation_id":"27b699de-850e-4b41-8f0a-1f2b3be17f4c","resolution":{"observed_at":"2026-08-15T14:43:47.731740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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/s10994-023-06333-w","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.032020Z","title":"Contrastive counterfactual visual explanations with overde- termination.Machine Learning, 112:3497–3525, 2023","venue":null,"work_id":"37275463-ebe0-4e3c-867f-e8fa3fb1140c","year":2023},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.981754Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:e3c6381d12965669ea54603e8dc535906d9534b18512eaa90502e7e06f6a69b1","observation_id":"6170e8f3-f190-42d7-bd62-2097ff2b20c7","resolution":{"observed_at":"2026-08-15T14:43:47.038229Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.701841Z","title":"ReAct: Synergizing reasoning and acting in language models","venue":null,"work_id":"37e6b634-00b0-469b-ad82-5f73fa1a77d1","year":2022},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.986566Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:de633251f213686cb4ef9f4e28abd7d1416b6c2256ac35cb8f0c1fa4dada685d","observation_id":"04d59640-baf8-43f5-bc86-fc5ea86f3fc3","resolution":{"observed_at":"2026-08-15T14:43:47.707591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.683547Z","title":"Adaptable logical control for large language models.Advances in Neural Information Processing Systems, 37: 115563–115587, 2024","venue":null,"work_id":"4e373c81-9b4d-4457-b9ac-462ef23cb0f5","year":2024},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.991105Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:26b9c0cb84c4222697fee56738808df7dbd06276f6bb4d9c1f7207e96807105a","observation_id":"e226931a-1d1f-45b8-803c-424384cfa6b8","resolution":{"observed_at":"2026-08-15T14:43:47.688791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:43:47.662627Z","title":"Position: Trustworthy AI agents require the integration of large language models and formal methods","venue":null,"work_id":"bc686c40-e414-4855-be01-a99ebaa663b8","year":2025},"citing_paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:46.995409Z"},"links":{"citing_paper":"/paper/2608.04285"},"observation_digest":"sha256:ece3a8a65d65608e344f3b69df86d422936264f7c96ddb34a4452c4d074e91d7","observation_id":"fe9b853d-36c4-4bbe-8d1b-75ff696ab853","resolution":{"observed_at":"2026-08-15T14:43:47.669407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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"}}],"paper":{"arxiv_id":"2608.04285","last_updated":"2026-08-04T23:24:39Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-15T14:38:46.151762Z","submitted_at":"2026-08-04T23:24:39Z","title":"The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":5,"verified_fuzzy":23},"total_outbound_references":39},"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 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2608.04285."}