{"as_of":"2026-08-14T19:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d71cf365f202886bf7b11a545a1c91a216796464204d08b7d20106f638551d19","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T13:02:25.700489Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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/2509.01016/citation-record","integrity":"/paper/2509.01016/integrity","json":"/paper/2509.01016/citation-record.json","paper":"/paper/2509.01016"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2108.07732","last_updated":"2021-08-16T03:57:30Z","snapshot_observed_at":"2026-08-02T19:23:53.535075Z","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":"2026-08-05T13:02:25.389421Z","title":"Program synthesis with large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.389421Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:be51724f5c5c7fcf0568521ebf46066b0ae229f6f2459621b4b3aa0bf041bf3a","observation_id":"2050d73d-75ec-4ceb-a539-ec334a6283e0","resolution":{"observed_at":"2026-08-05T13:02:25.389421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.01547","last_updated":"2019-11-25T13:02:04Z","snapshot_observed_at":"2026-07-06T08:34:41.399203Z","submitted_at":"2019-11-05T00:31:38Z","title":"On the Measure of Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.01547","snapshot_observed_at":"2026-08-05T13:02:25.654585Z","title":"On the measure of intelligence","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.654585Z"},"links":{"cited_paper":"/paper/1911.01547","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:d928e08f5cc9301fce6a29f11d08652b399b883c894ed095c6cb02ef7e4139c3","observation_id":"8c231f64-c131-4801-ae8f-fb18e7044319","resolution":{"observed_at":"2026-08-05T13:02:25.654585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.05823","last_updated":"2021-03-10T02:18:21Z","snapshot_observed_at":"2026-08-14T06:39:53.886774Z","submitted_at":"2021-03-10T02:18:21Z","title":"Fast and flexible: Human program induction in abstract reasoning tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.05823","snapshot_observed_at":"2026-08-05T13:02:25.664657Z","title":"Fast and flexible: Human program induction in abstract reasoning tasks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.664657Z"},"links":{"cited_paper":"/paper/2103.05823","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:b9581b2afb40ba8ebb14c179c4e63fbfbdcd3f73b0f869bfd4233237cc4784f3","observation_id":"a5cfcd01-67d7-40f2-aaba-a88bad32e4fd","resolution":{"observed_at":"2026-08-05T13:02:25.664657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.01186","last_updated":"2018-09-09T21:32:49Z","snapshot_observed_at":"2026-08-08T13:25:02.112641Z","submitted_at":"2018-04-03T22:37:08Z","title":"Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples","version":2},"cited_work":{"arxiv_id":"1804.01186","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.01186","snapshot_observed_at":"2026-08-05T13:02:25.810333Z","title":"Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples","venue":"cs.AI","work_id":"22324cf7-d67c-4e48-a9a7-b136aaa55837","year":2018},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.668037Z"},"links":{"cited_paper":"/paper/1804.01186","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:ad92ac0265169c7344d7b5dac603995c7a7fa4dbbef8de3bca839679039df7b8","observation_id":"87485ab1-cc41-46b0-ab1c-bf5f46ccf7df","resolution":{"observed_at":"2026-08-05T13:02:25.813975Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01855","last_updated":"2016-11-06T22:23:56Z","snapshot_observed_at":"2026-08-13T13:11:35.834756Z","submitted_at":"2016-11-06T22:23:56Z","title":"Neuro-Symbolic Program Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01855","snapshot_observed_at":"2026-08-05T13:02:25.677097Z","title":"Neuro-symbolic program synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.677097Z"},"links":{"cited_paper":"/paper/1611.01855","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:5016fdc95b83b6e85a91006e3d756fd48a78d3c59a0661e2515b55509f76834c","observation_id":"65e5a845-0c26-4d09-afe7-81e587a3d83c","resolution":{"observed_at":"2026-08-05T13:02:25.677097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11227","last_updated":"2022-01-26T22:57:44Z","snapshot_observed_at":"2026-08-13T16:52:39.593800Z","submitted_at":"2022-01-26T22:57:44Z","title":"Synchromesh: Reliable code generation from pre-trained language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11227","snapshot_observed_at":"2026-08-05T13:02:25.683116Z","title":"Synchromesh: Reliable code generation from pre-trained language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.683116Z"},"links":{"cited_paper":"/paper/2201.11227","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:0b645b57cde7e53cf9d0432558300a8ae7eaed41c6e504f619ef197786c69f88","observation_id":"2b96d003-fa18-4c0f-86b1-87b6f26ffb05","resolution":{"observed_at":"2026-08-05T13:02:25.683116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03314","last_updated":"2023-06-05T23:55:37Z","snapshot_observed_at":"2026-08-11T04:53:44.472967Z","submitted_at":"2023-06-05T23:55:37Z","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03314","snapshot_observed_at":"2026-08-05T13:02:25.686347Z","title":"Multi-agent collaboration: Harnessing the power of intelligent llm agents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.686347Z"},"links":{"cited_paper":"/paper/2306.03314","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:259b3d36bcc01eaa93946a862663dbed299ea483b77a7f3d15c3d916903bf9e8","observation_id":"8abaa7d9-45a1-42d3-b576-2f6aa39dcd9e","resolution":{"observed_at":"2026-08-05T13:02:25.686347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18354","last_updated":"2024-02-14T21:15:31Z","snapshot_observed_at":"2026-08-13T11:32:16.840125Z","submitted_at":"2023-05-26T16:32:17Z","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18354","snapshot_observed_at":"2026-08-05T13:02:25.692131Z","title":"Llms and the abstrac- tion and reasoning corpus: Successes, failures, and the importance of object-based representations","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.692131Z"},"links":{"cited_paper":"/paper/2305.18354","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:b33526fef5dfdb06de7206758623268f1f31c3ea06739f7ae86ce0075fcc0ce0","observation_id":"124961d5-7bfa-4f46-8737-c33680050746","resolution":{"observed_at":"2026-08-05T13:02:25.692131Z","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":"2026-08-05T13:02:25.910667Z","title":null,"venue":null,"work_id":"0f540fb0-2547-4589-8715-a0682cb68799","year":2023},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.695031Z"},"links":{"citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:a1a3169eb2614b59f6ddcf41c034ee97ae5bd38bae92758c999fa120a586de9e","observation_id":"1cb7339b-2974-4e70-b30f-3ce39cd11387","resolution":{"observed_at":"2026-08-05T13:02:25.913633Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T13:02:25.891915Z","title":"Human learners reach 0.521, slightly higher than hypothesis search at 0.487","venue":null,"work_id":"0a585200-11f3-4ef4-ae64-79827885f193","year":2024},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.700489Z"},"links":{"citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:a5e6715f7b50ae817f1596f1e132f21faba4ec03e150baa4b4587e9cc58a5501","observation_id":"f3c856b5-d319-4bf8-b45d-ce4a8df13af2","resolution":{"observed_at":"2026-08-05T13:02:25.895429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T13:02:25.901643Z","title":"[2024], where Codex was evaluated under Direct Program Generation","venue":null,"work_id":"a95c70c5-f6d8-4571-ac8a-49b8f7b12381","year":2024},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":1000,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.697765Z"},"links":{"citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:ed471f51c8dcbcfe1a6574cb3005eb64bcc335bdee0ba4e896879bd9ffac984e","observation_id":"a0057f78-198d-4e9c-9583-be53aceda6ae","resolution":{"observed_at":"2026-08-05T13:02:25.904676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06025","last_updated":"2024-10-25T22:26:41Z","snapshot_observed_at":"2026-08-13T04:23:02.347813Z","submitted_at":"2024-02-08T19:57:29Z","title":"Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning","version":7},"cited_work":{"arxiv_id":"2402.06025","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.06025","snapshot_observed_at":"2026-08-05T13:02:25.765952Z","title":"Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning","venue":"cs.AI","work_id":"550a594e-bfec-4cd8-812a-4153127b61ed","year":2024},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":1868,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.680146Z"},"links":{"cited_paper":"/paper/2402.06025","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:3ae52b51e970fc23de34957d631c029f971f7daf26db6db66fb1a1e64d2a3ec1","observation_id":"035562de-61bb-4dc9-a17f-ee36bdc0f4aa","resolution":{"observed_at":"2026-08-05T13:02:25.771453Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09359","last_updated":"2024-12-10T16:24:48Z","snapshot_observed_at":"2026-08-12T22:45:01.527094Z","submitted_at":"2024-09-14T08:17:30Z","title":"Symbolic Regression with a Learned Concept Library","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.09359","snapshot_observed_at":"2026-08-05T13:02:25.661491Z","title":"Symbolic regression with a learned concept library","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.661491Z"},"links":{"cited_paper":"/paper/2409.09359","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:4c75b1f51ff5417e38c943fa2fb9d544caf3314f7aa128ea39c9a23d5fc8c46e","observation_id":"76490900-134b-43c7-a68a-89e6983d81df","resolution":{"observed_at":"2026-08-05T13:02:25.661491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19555","last_updated":"2024-01-02T22:30:00Z","snapshot_observed_at":"2026-08-13T11:28:51.422270Z","submitted_at":"2023-05-31T04:50:29Z","title":"Large Language Models Are Not Strong Abstract Reasoners","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19555","snapshot_observed_at":"2026-08-05T13:02:25.658020Z","title":"Large language models are not abstract reasoners","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.658020Z"},"links":{"cited_paper":"/paper/2305.19555","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:0d03e3a8b2d19e9ec96f92f36673e348b46b8667e4f38b7eca322c286f97b821","observation_id":"c048c413-1338-4c46-8ad1-e97401805e32","resolution":{"observed_at":"2026-08-05T13:02:25.658020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.05660","last_updated":"2024-05-30T23:10:00Z","snapshot_observed_at":"2026-08-13T10:15:48.512306Z","submitted_at":"2023-09-11T17:56:57Z","title":"Hypothesis Search: Inductive Reasoning with Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.05660","snapshot_observed_at":"2026-08-05T13:02:25.689262Z","title":"Hypothesis search: Inductive reasoning with language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.689262Z"},"links":{"cited_paper":"/paper/2309.05660","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:f889cdae1a8348c204aa3ee66fa2626d3f38920535a10daa08cf48ebdee89840","observation_id":"9e1a1121-bf13-4722-9e00-731defa32c84","resolution":{"observed_at":"2026-08-05T13:02:25.689262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04721","last_updated":"2023-10-26T01:27:29Z","snapshot_observed_at":"2026-08-13T10:58:52.207680Z","submitted_at":"2023-07-10T17:32:13Z","title":"Large Language Models as General Pattern Machines","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04721","snapshot_observed_at":"2026-08-05T13:02:25.674181Z","title":"Large language models as general pattern machines","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.674181Z"},"links":{"cited_paper":"/paper/2307.04721","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:2631a509ffef22dc3847eaa57bd3d414733d2626aa6c63260b912afe5ac463a0","observation_id":"98ebe19d-da34-4ac3-bed3-34796327e04c","resolution":{"observed_at":"2026-08-05T13:02:25.674181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12712","last_updated":"2023-04-13T20:41:31Z","snapshot_observed_at":"2026-08-03T04:49:15.195814Z","submitted_at":"2023-03-22T16:51:28Z","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.12712","snapshot_observed_at":"2026-08-05T13:02:25.632997Z","title":"Sparks of artificial general intelligence: Early experiments with gpt-4","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.632997Z"},"links":{"cited_paper":"/paper/2303.12712","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:2af9193bae147fda66a819ed6e84b5d28dcb5d95934e1e6e273eb3b17d31adb1","observation_id":"268f1ab2-9b50-4e92-9afc-a18a717e6f6f","resolution":{"observed_at":"2026-08-05T13:02:25.632997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-05T13:02:25.506651Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.506651Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:89b3175991bc26c6ca1fb49f03578b269081a0c93714fac14a350107b6921179","observation_id":"d4d4a9fd-1748-4182-a042-072b526c0b6c","resolution":{"observed_at":"2026-08-05T13:02:25.506651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-05T13:02:25.650984Z","title":"Evaluating large language models trained on code","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.650984Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:6072284510ab6a488d322714b9f1d55098269c06681e221b4ae27c437d5f5705","observation_id":"66107e61-f80f-4e80-9114-6551f7d88f67","resolution":{"observed_at":"2026-08-05T13:02:25.650984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.12584","last_updated":"2019-04-26T06:50:54Z","snapshot_observed_at":"2026-08-14T16:41:07.492381Z","submitted_at":"2019-04-26T06:50:54Z","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.12584","snapshot_observed_at":"2026-08-05T13:02:25.671084Z","title":"The neuro- symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-05T13:02:25.671084Z"},"links":{"cited_paper":"/paper/1904.12584","citing_paper":"/paper/2509.01016"},"observation_digest":"sha256:f2820a63eb007490c22de5dc4338f4a8a3bed79aa34cf7bca11cc30e7cdf5038","observation_id":"e9d58c0d-fa06-42ac-8b97-83ff83a21afb","resolution":{"observed_at":"2026-08-05T13:02:25.671084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.01016","last_updated":"2025-08-31T22:42:58Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-14T17:09:08.334747Z","submitted_at":"2025-08-31T22:42:58Z","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":2,"verified_fuzzy":2},"total_outbound_references":20},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2509.01016."}