{"as_of":"2026-08-21T01:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:19b47940a79be5c35993865f4a692b9312120b67c7f701256f3479ba04b496e2","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:04:05.841223Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.06321/citation-record","integrity":"/paper/2505.06321/integrity","json":"/paper/2505.06321/citation-record.json","paper":"/paper/2505.06321"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:04:06.389169Z","title":"Graph of thoughts: Solving elaborate problems with large language models","venue":null,"work_id":"7dfc6f21-e462-4092-943b-c9271cec6a9c","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.616976Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:9b7de86256855f45ff767cf85c2b06a8152ab9b9b37c86b08fa11fe2ba314e0b","observation_id":"851ba6f2-30a6-4cdc-8e93-b944b8513a2f","resolution":{"observed_at":"2026-08-15T23:04:06.393797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.375533Z","title":null,"venue":null,"work_id":"8df5aaec-0298-43e2-9621-cbe3122ff196","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.621925Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:990d59bc48aa991b28233a7ad5110a4fe680ebd5abe03f969421b4f23d6da5e0","observation_id":"471edefb-d67e-4b8c-a70d-e8c061a4efa6","resolution":{"observed_at":"2026-08-15T23:04:06.379924Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.361343Z","title":"Language models are few-shot learners","venue":null,"work_id":"e70a434a-41f8-4546-a4c7-3a363ca21f50","year":2022},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.626699Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:7e7c575d6ecfab643d7ac14a7e7722e37440be13df3edbb49928d56059e13142","observation_id":"372f2d89-ed87-4598-8369-6e89b9c27fd3","resolution":{"observed_at":"2026-08-15T23:04:06.365756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.347636Z","title":"Navigate through enigmatic labyrinth A survey of chain of thought reasoning: Advances, frontiers and future","venue":null,"work_id":"0c504f60-8994-4ac9-a05c-5cc8aa9fd04f","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.632127Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:f8046be30bc041f13be5a791780b1b5629011cd04efeef2dfccd273ae272121f","observation_id":"b2fdf4ef-e223-48e6-b3f2-e891b6808115","resolution":{"observed_at":"2026-08-15T23:04:06.351827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.333395Z","title":"Chain-of-verification reduces hallucination in large language models","venue":null,"work_id":"9e23562a-de4a-4856-bfaa-89c0abc39ded","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.636955Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:2f470205e09b3f7621bf685ccfa1619fb81b75b312ca8b6345e037bb0156e804","observation_id":"6d87d15c-a203-4f3d-9858-edfaaddf8de0","resolution":{"observed_at":"2026-08-15T23:04:06.338408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.318521Z","title":"Active prompting with chain-of-thought for large language models","venue":null,"work_id":"6db2a079-a9ab-4cf0-a8bb-d07411f03bd2","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.642111Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:306b58434285a992acf8e9888e78b858deeb59af0e57c7e3b70609b8bb97e74c","observation_id":"a6829682-aa46-486d-9ace-4f33a8087285","resolution":{"observed_at":"2026-08-15T23:04:06.323124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.302793Z","title":"Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects","venue":null,"work_id":"035b110d-e0c1-4b58-9448-f72ff4c9fc9e","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.647703Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:f2157f1e8356b85b0e491aecba1c794a49d35d6a4dfa29bb5489e35771d710ca","observation_id":"e5ba0f5b-2123-4421-aafa-ac611ff10a40","resolution":{"observed_at":"2026-08-15T23:04:06.308105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.287530Z","title":"Recent advances in neural machine translation","venue":null,"work_id":"61577c0d-8d6e-4089-92e0-9891aec595b2","year":2022},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.652341Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:4b8f4a6b6dad8c161290cff1f6ebaee2da0634d74ff3c60f06c7a1e01d78f48c","observation_id":"981c98ae-a0d5-4e61-9338-c89c4cf60fda","resolution":{"observed_at":"2026-08-15T23:04:06.292130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.272852Z","title":"Kipf and Max Welling","venue":null,"work_id":"0f81d23c-b372-4632-8641-695a8b74e50f","year":2017},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.656958Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:b2af60b4714bfb80a3c31c561ab053b7e286e99ebe8a9ffc13e34265e1e62932","observation_id":"007234d5-457a-4699-8f60-6e52bd42b4f6","resolution":{"observed_at":"2026-08-15T23:04:06.277684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.257405Z","title":"Konda and John N","venue":null,"work_id":"fe95fa90-84a1-427f-a4d1-b86a0141427b","year":1999},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.661373Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:fcbc910303cdf21142c37a9cc14192ddd3352d7a8e979dd4f97d1c89795610d6","observation_id":"225adccd-a3b0-4c0e-8a8b-0c40aa5c6b09","resolution":{"observed_at":"2026-08-15T23:04:06.262044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.242246Z","title":"u ttler, Mike Lewis, Wen - tau Yih, Tim Rockt \\","venue":null,"work_id":"5e167865-e54e-49f6-826d-68abd43804b7","year":2020},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.667154Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:59dab51979582045dca361493c729f163253c04d4b85c3e9acd85d81b6be34ee","observation_id":"432cedcb-96ca-44eb-b863-b5c4abbfd699","resolution":{"observed_at":"2026-08-15T23:04:06.247330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.227312Z","title":"Large language models understand and can be enhanced by emotional stimuli, 2023","venue":null,"work_id":"72f49803-2e79-4cb3-bfd0-1c1bb4980ce7","year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.671641Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:c386f63923b7f41c15920e40c795d0d0961bc2da17f5a1158c5d991671c1c7c3","observation_id":"25e39925-cb33-4dfc-b12e-3fc870f30891","resolution":{"observed_at":"2026-08-15T23:04:06.231988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:05.676219Z","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.676219Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:e84981054ba74b9eb956414182cedd571bad35f97eee981174e8fdfaa6ac52ea","observation_id":"4193cc14-807c-4913-a0c0-d6b2f1a9e8c9","resolution":{"observed_at":"2026-08-15T23:04:05.676219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.08291","last_updated":"2023-05-15T01:18:23Z","snapshot_observed_at":"2026-08-20T11:15:33.226264Z","submitted_at":"2023-05-15T01:18:23Z","title":"Large Language Model Guided Tree-of-Thought","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.08291","snapshot_observed_at":"2026-08-15T23:04:05.680502Z","title":"Large language model guided tree-of-thought","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.680502Z"},"links":{"cited_paper":"/paper/2305.08291","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:a816aaa649690e5a93006c0bd93bed2e058b6262efd733c1fc3c0765600b0a4a","observation_id":"a6f01200-aff2-4171-9038-b7ee771942de","resolution":{"observed_at":"2026-08-15T23:04:05.680502Z","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":"2026-08-15T23:04:06.201429Z","title":"Directgpt: A direct manipulation interface to interact with large language models","venue":null,"work_id":"4eff282c-778f-407b-9d0c-e436aa2f7454","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.685357Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:642b4d8ebe0118f4bf075eae10b602a49a9dd0d2de48b31bbf2386a06a5f3a9a","observation_id":"88d209da-f1ce-4968-a949-24b4ae5180a3","resolution":{"observed_at":"2026-08-15T23:04:06.206193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.187495Z","title":"Liar, liar, logical mire: A benchmark for suppositional reasoning in large language models","venue":null,"work_id":"36cb450a-2e46-4c5d-9071-590888a9f7d5","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.689927Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:1d1d19533a1c6586cfa6c62f4744bacdb9ae9f746cf2a47fe8a8a2c25df526cc","observation_id":"c4fc99bc-519c-4c87-8fb7-71a04e8845ec","resolution":{"observed_at":"2026-08-15T23:04:06.191554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.13474","last_updated":"2023-02-27T21:26:48Z","snapshot_observed_at":"2026-08-13T14:36:56.609471Z","submitted_at":"2022-03-25T06:55:15Z","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.13474","snapshot_observed_at":"2026-08-15T23:04:05.694531Z","title":"Codegen: An open large language model for code with multi-turn program synthesis","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.694531Z"},"links":{"cited_paper":"/paper/2203.13474","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:3002ac8e74bc1c0c13d289d914a8a39d7b7bb5c2865885d66136de53f47b122e","observation_id":"7bf8e91b-b44f-4d79-b3b4-4ed5c92f5726","resolution":{"observed_at":"2026-08-15T23:04:05.694531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-15T23:04:05.701760Z","title":"GPT-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.701760Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:e49df3459b087d46f108fcf8e388314f7dbe4967a814352853301b94f0928fa3","observation_id":"f4f47189-ebff-4924-8a4b-d0a38ad8052a","resolution":{"observed_at":"2026-08-15T23:04:05.701760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.09014","last_updated":"2023-03-16T01:04:45Z","snapshot_observed_at":"2026-08-18T04:54:46.080762Z","submitted_at":"2023-03-16T01:04:45Z","title":"ART: Automatic multi-step reasoning and tool-use for large language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.09014","snapshot_observed_at":"2026-08-15T23:04:05.724468Z","title":"Lundberg, Sameer Singh, Hannaneh Hajishirzi, Luke Zettlemoyer, and Marco T \\' u lio Ribeiro","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.724468Z"},"links":{"cited_paper":"/paper/2303.09014","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:a1e42304aa0c8ed30b04a64ca84916225f39a06bf897f6a87502916f4898ceb5","observation_id":"af7e62ea-c344-4599-ba3d-2ee6a4647319","resolution":{"observed_at":"2026-08-15T23:04:05.724468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.05149","last_updated":"2022-04-11T14:30:27Z","snapshot_observed_at":"2026-08-16T17:07:46.527614Z","submitted_at":"2022-04-11T14:30:27Z","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.05149","snapshot_observed_at":"2026-08-15T23:04:05.757330Z","title":"Carbon emissions and large neural network training","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.757330Z"},"links":{"cited_paper":"/paper/2204.05149","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:f52f3a987dfa758480e95e3643c590052e72555cc456e8666ba2d8d6aef739bf","observation_id":"27231659-b8e3-4dba-9a14-6e2b9480ff8a","resolution":{"observed_at":"2026-08-15T23:04:05.757330Z","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":"2026-08-15T23:04:06.174063Z","title":"Reasoning with language model prompting: A survey","venue":null,"work_id":"eec1e127-d2e7-4d02-9af8-98c1fc18702c","year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.773295Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:ef79facd860f92eafb1f9fbbf7710373dcc0f68053bf8ccce9f064db938cc9d1","observation_id":"182fcb0f-e99c-4c49-8b03-8dd83ab1fbfd","resolution":{"observed_at":"2026-08-15T23:04:06.178203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.159514Z","title":"Improving language understanding by generative pre-training","venue":null,"work_id":"0fa157d8-2cdd-4c59-907c-b8b407bc5499","year":2018},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.777299Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:f9b584cc41bf802472f6ad697f50e3a5d325653b297b46b62c1685de15fbc369","observation_id":"6ea2a5ce-ad65-4f2c-b599-51ba01b2f2fc","resolution":{"observed_at":"2026-08-15T23:04:06.163628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-08-20T07:04:06.309989Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-15T23:04:05.781099Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.781099Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:aa89f636b563563e6d2bdbcc792d1e1b7579b43788e001f126586332e0231901","observation_id":"9cb88ba5-b92d-4dfb-9cee-489e1d258719","resolution":{"observed_at":"2026-08-15T23:04:05.781099Z","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":"2026-08-15T23:04:06.144077Z","title":"Algorithm of thoughts: Enhancing exploration of ideas in large language models","venue":null,"work_id":"8be0ed18-04c8-4081-93e9-d1f12580d354","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.785250Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:109bb260b5e1176ed975ca0da276ab443cc22e63dd6b3f96018e0cf1e60db98e","observation_id":"5d889c66-3168-4ac0-9575-9ff28c34711d","resolution":{"observed_at":"2026-08-15T23:04:06.148673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03514","last_updated":"2022-06-27T08:14:54Z","snapshot_observed_at":"2026-08-19T05:51:15.818767Z","submitted_at":"2022-01-10T18:17:05Z","title":"Black-Box Tuning for Language-Model-as-a-Service","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03514","snapshot_observed_at":"2026-08-15T23:04:05.789001Z","title":"Black-box tuning for language-model-as-a-service","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.789001Z"},"links":{"cited_paper":"/paper/2201.03514","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:0eb67e658ee01edd11463f319fc019da1beb416152d5faf614eb9574c5a94361","observation_id":"35037ca9-cc35-4016-9c8f-31d9bab0cb59","resolution":{"observed_at":"2026-08-15T23:04:05.789001Z","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":"2026-08-15T23:04:05.793013Z","title":"Le, Ed H","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.793013Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:15cdf805cfa9f4e4b4f62fd34fc0909dd633acb17d05dffe88ccc504fa231896","observation_id":"70725625-5b96-4769-a9b7-503581835379","resolution":{"observed_at":"2026-08-15T23:04:05.793013Z","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":"2026-08-15T23:04:05.796919Z","title":"Chi, Quoc V","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.796919Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:65b41a94764c03e2363e73a5ba2fb4a6a6d6937e1a188ab6de33c0671a1271a0","observation_id":"5ded1882-70be-46a4-b7af-85bbf639d3b0","resolution":{"observed_at":"2026-08-15T23:04:05.796919Z","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":"2026-08-15T23:04:05.801006Z","title":"A comprehensive survey on graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.801006Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:af602e3a0337056ed7f7a055c0adde29160858eef5a3f70d36d12ec566df6593","observation_id":"2262c70e-5752-4cb4-9ac7-1386764182b0","resolution":{"observed_at":"2026-08-15T23:04:05.801006Z","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":"2026-08-15T23:04:05.804890Z","title":"Tree of thoughts: Deliberate problem solving with large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.804890Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:43731c88b1ab3ef116f582b19a95576d1deeda8e81d4ef8cb0136c9be3724907","observation_id":"11507748-a638-45c3-89dd-873e197b367b","resolution":{"observed_at":"2026-08-15T23:04:05.804890Z","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":"2026-08-15T23:04:06.088585Z","title":"Narasimhan, and Yuan Cao","venue":null,"work_id":"fc6b3677-3916-4238-83c7-c79b09514095","year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.808498Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:0c6d12d27aeb630d291c532a24d13c4362a96a1d8ebb42734f9b9e67f7af494e","observation_id":"c4c24dce-c1fe-4fdb-bfb4-ee59672058a1","resolution":{"observed_at":"2026-08-15T23:04:06.093388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09210","last_updated":"2024-10-03T04:35:39Z","snapshot_observed_at":"2026-08-16T14:42:57.735225Z","submitted_at":"2023-11-15T18:54:53Z","title":"Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09210","snapshot_observed_at":"2026-08-15T23:04:05.812514Z","title":"Chain-of-note: Enhancing robustness in retrieval-augmented language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.812514Z"},"links":{"cited_paper":"/paper/2311.09210","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:1f875df25ac2d0fd8974f1e985f3fdf3922d1dd74269301790c43f97757e8313","observation_id":"26434683-87df-4b5e-aedf-407cbd80beda","resolution":{"observed_at":"2026-08-15T23:04:05.812514Z","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":"2026-08-15T23:04:06.073659Z","title":"Automatic chain of thought prompting in large language models","venue":null,"work_id":"b7bd699d-97a7-4086-b2ed-1a5809cfa0aa","year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.817346Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:3cb528917d2c9aba014139e5e9d9bea8d80523b22aa8c60b423e2ce280d74c5d","observation_id":"0938912c-5231-4f06-98c8-fe43b50a77fa","resolution":{"observed_at":"2026-08-15T23:04:06.078448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.057817Z","title":"Enhancing zero-shot chain-of-thought reasoning in large language models through logic","venue":null,"work_id":"2af16a28-2d7e-41c3-9c95-25a4cb3d1c19","year":2024},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.821905Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:e8ee2f93d205e3fafbc1213950556a3991eab116e3e5abef58d5a9c70f1780c2","observation_id":"9f9a2ecf-2f2c-48a5-b203-b77c03c93c5b","resolution":{"observed_at":"2026-08-15T23:04:06.062720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.042041Z","title":"Learning to prompt for vision-language models","venue":null,"work_id":"516fe33c-c2f9-4516-9fd9-20e3afb8b171","year":2022},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.826701Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:e061d39d4b9f47cfa0297ebe74955b2fc9bab5fdc2c843111eb710af24fc0329","observation_id":"99a567cf-fd2d-4a7f-96f1-49437ff17c46","resolution":{"observed_at":"2026-08-15T23:04:06.046897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:04:06.024113Z","title":"Large language models are human-level prompt engineers","venue":null,"work_id":"66353973-027b-4ee4-adf8-a5551bd28eba","year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.831411Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:7b127921a29170fc3253f6a15721f72cc2a3f4bc91c0a1a2677952ccf36d96c4","observation_id":"c03bfbee-d0e8-4ba3-bc6e-9ae5ef9b3456","resolution":{"observed_at":"2026-08-15T23:04:06.031095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08734","last_updated":"2023-11-15T06:54:44Z","snapshot_observed_at":"2026-08-19T23:41:28.070498Z","submitted_at":"2023-11-15T06:54:44Z","title":"Thread of Thought Unraveling Chaotic Contexts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08734","snapshot_observed_at":"2026-08-15T23:04:05.836354Z","title":"Thread of thought unraveling chaotic contexts","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.836354Z"},"links":{"cited_paper":"/paper/2311.08734","citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:18465c99bcb2ff31359d1e28a40c6678dca0697bb798a506f1393b4ce56f26cd","observation_id":"a6372b50-acf4-4257-b6cf-7feba649e2e0","resolution":{"observed_at":"2026-08-15T23:04:05.836354Z","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":"2026-08-15T23:04:05.841223Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T23:04:05.841223Z"},"links":{"citing_paper":"/paper/2505.06321"},"observation_digest":"sha256:124066ad140d9517d9bdf70b047d152dea29cdaf9f00c98547174ec8b4bf85d2","observation_id":"14ef27f6-08b2-40ae-afdd-bb9243a773ad","resolution":{"observed_at":"2026-08-15T23:04:05.841223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.06321","last_updated":"2025-05-17T00:10:14Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T12:00:40.742429Z","submitted_at":"2025-05-09T02:51:22Z","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":21},"total_outbound_references":37},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2505.06321."}