{"as_of":"2026-08-19T22:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dc67b10739c2cd16d40b401126e46d00d2f288a22448d83106785addc1f522b9","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":20,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T22:57:01.806123Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":1,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-11T22:57:01.806123Z","title":"Tinygsm: achieving >80 URL https://arxiv.org/abs/2312.09241","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.02980","last_updated":"2024-12-09T22:23:41Z","snapshot_observed_at":"2026-08-15T13:18:49.671776Z","submitted_at":"2024-12-04T02:47:45Z","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","version":2},"reference_index":114,"source":"arxiv_source","source_observed_at":"2026-08-11T22:57:01.806123Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2412.02980"},"observation_digest":"sha256:1ff458b196a8293f4fb4cd995268b6c22bdedcc786c7ff4cdc972d83925c6dbc","observation_id":"f4de4c5f-8337-42fa-a51e-01a43efb4122","resolution":{"observed_at":"2026-08-11T22:57:01.806123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-11T15:47:53.570902Z","title":"Liu, et al., Tinygsm: achieving¿ 80% on gsm8k with small language models.arXiv preprint arXiv:2312.09241 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.10673","last_updated":"2024-12-14T04:20:47Z","snapshot_observed_at":"2026-08-18T00:11:38.473299Z","submitted_at":"2024-12-14T04:20:47Z","title":"Proposing and solving olympiad geometry with guided tree search","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T15:47:53.570902Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2412.10673"},"observation_digest":"sha256:de11870f23c938111ce0529127c9c4768834671a23d5717131bbab7c4a8b971b","observation_id":"70c1638b-bb12-497c-909d-ae58ab738edd","resolution":{"observed_at":"2026-08-11T15:47:53.570902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-11T15:47:21.267762Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.10675","last_updated":"2024-12-14T04:23:14Z","snapshot_observed_at":"2026-08-15T20:20:48.990404Z","submitted_at":"2024-12-14T04:23:14Z","title":"Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T15:47:21.267762Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2412.10675"},"observation_digest":"sha256:2d25d290a14f3a31d2dbd538d356acad18a1e458f2486177cf207d65b9800b61","observation_id":"99640ccc-657f-44d5-8058-9f77df5c207f","resolution":{"observed_at":"2026-08-11T15:47:21.267762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-11T05:58:55.066821Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16964","last_updated":"2024-12-24T11:43:25Z","snapshot_observed_at":"2026-08-17T16:43:01.758405Z","submitted_at":"2024-12-22T10:49:27Z","title":"System-2 Mathematical Reasoning via Enriched Instruction Tuning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T05:58:55.066821Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2412.16964"},"observation_digest":"sha256:2921e686ff3ceeb03e12d432bca5c4135bcb0777331f4598c8a6960851d652e8","observation_id":"72361e13-963d-4b7a-b88c-1dee1cede574","resolution":{"observed_at":"2026-08-11T05:58:55.066821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2501.05465","last_updated":"2026-05-14T16:52:31Z","snapshot_observed_at":"2026-08-14T18:35:28.225116Z","submitted_at":"2025-01-03T19:53:57Z","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-23T05:47:48.488826Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2501.05465"},"observation_digest":"sha256:026c988d80fd5efbeaf0e58b808dc1d660caff4fb624fc2517076951aab12dc0","observation_id":"671813f5-9b31-4143-ad8a-e3807df93b9d","resolution":{"observed_at":"2026-05-23T05:52:37.294007Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-07T14:27:49.328172Z","title":"TinyGSM: Achieving >80% on GSM8K with Small Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18952","last_updated":"2025-05-25T02:56:18Z","snapshot_observed_at":"2026-08-12T01:21:12.055173Z","submitted_at":"2025-05-25T02:56:18Z","title":"Online Knowledge Distillation with Reward Guidance","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T14:27:49.328172Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2505.18952"},"observation_digest":"sha256:9a93726e88433fd4e0af5f848a5b4d9a2c7da4acd7135c5e0a7fac84511e8ad3","observation_id":"2a94db03-1fd9-44d4-b52f-aaccfd86e1d6","resolution":{"observed_at":"2026-08-07T14:27:49.328172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-07T12:39:05.502062Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24165","last_updated":"2025-05-30T03:14:17Z","snapshot_observed_at":"2026-08-17T00:43:22.793564Z","submitted_at":"2025-05-30T03:14:17Z","title":"Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T12:39:05.502062Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2505.24165"},"observation_digest":"sha256:5acd49f099a5c2df79f0f4594c7142134f1ec295750eff3c5f5dcb5f0806a015","observation_id":"b5f09a3d-156e-4e19-989c-d8df0b841ea7","resolution":{"observed_at":"2026-08-07T12:39:05.502062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-07T05:14:47.355966Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.08446","last_updated":"2025-06-10T04:44:28Z","snapshot_observed_at":"2026-08-17T06:22:42.572723Z","submitted_at":"2025-06-10T04:44:28Z","title":"A Survey on Large Language Models for Mathematical Reasoning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T05:14:47.355966Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2506.08446"},"observation_digest":"sha256:dfe797c878642ef4aa61d4ac03286504ac28406505531b8148319881f54c5fa6","observation_id":"cd0b74e3-e7f8-4123-afa6-7e9b08e39471","resolution":{"observed_at":"2026-08-07T05:14:47.355966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T17:57:17.092837Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15478","last_updated":"2025-09-04T11:23:22Z","snapshot_observed_at":"2026-08-17T08:53:23.609310Z","submitted_at":"2025-08-21T11:56:05Z","title":"SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-05T17:57:17.092837Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2508.15478"},"observation_digest":"sha256:2c7858ffd2002503e1f0a5bc86e74824e58030b6f6804d1dee27a7dcea209393","observation_id":"4f1c0be2-c49c-4bb4-b9bc-83c557d278e0","resolution":{"observed_at":"2026-08-05T17:57:17.092837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T13:35:36.663056Z","title":"Tinygsm: achieving 80% on gsm8k with small language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.00509","last_updated":"2025-08-30T14:03:09Z","snapshot_observed_at":"2026-08-15T08:02:03.455785Z","submitted_at":"2025-08-30T14:03:09Z","title":"Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T13:35:36.663056Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2509.00509"},"observation_digest":"sha256:eb047080257193134924ecebd682524067a0ca43ed6446248aa8a5b28f685924","observation_id":"bea759e0-67c0-4c0e-93dc-3a52fe4a97a1","resolution":{"observed_at":"2026-08-05T13:35:36.663056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2510.04265","last_updated":"2026-05-12T01:55:07Z","snapshot_observed_at":"2026-08-13T07:36:21.999871Z","submitted_at":"2025-10-05T16:14:03Z","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-18T10:04:39.223895Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2510.04265"},"observation_digest":"sha256:78f8963d5ac9a9749337763a3a226f1f0ae93694b0e87551ed9f4383dc638f4a","observation_id":"6046303a-eb30-49b4-bc19-96d503b11dda","resolution":{"observed_at":"2026-05-18T10:06:13.910982Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2602.08167","last_updated":"2026-05-16T05:42:57Z","snapshot_observed_at":"2026-08-16T17:50:48.003461Z","submitted_at":"2026-02-09T00:10:17Z","title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-21T14:03:48.795572Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2602.08167"},"observation_digest":"sha256:66aff193b179a402e8a9de0095629b4544f82197d4ed35b3ceedf217988cf97b","observation_id":"15ef4678-cb6b-4a42-86c5-49ba8403a77c","resolution":{"observed_at":"2026-05-21T14:04:11.970652Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2605.26106","last_updated":"2026-05-25T17:58:24Z","snapshot_observed_at":"2026-08-12T19:19:35.785040Z","submitted_at":"2026-05-25T17:58:24Z","title":"Looped Diffusion Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-29T23:13:12.343355Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2605.26106"},"observation_digest":"sha256:d9cddd550cd4030695754fa814b95b2753c3fbc55e0a9f20e4f098f287e622e5","observation_id":"5d47610c-a9b7-46a5-85c3-645ba74c12c6","resolution":{"observed_at":"2026-06-29T23:14:01.129009Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2605.26496","last_updated":"2026-05-26T03:19:04Z","snapshot_observed_at":"2026-08-13T01:21:16.789063Z","submitted_at":"2026-05-26T03:19:04Z","title":"Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T19:34:17.270161Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2605.26496"},"observation_digest":"sha256:4a114bd41ef74b9be1106f767dda4169eb3f2a115d93f756515b1bb5e9fc414d","observation_id":"bd00998c-4f2f-4b07-b4a8-4bb16cd850fe","resolution":{"observed_at":"2026-06-29T19:43:55.011998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2606.00683","last_updated":"2026-05-30T11:42:19Z","snapshot_observed_at":"2026-08-14T02:59:01.389930Z","submitted_at":"2026-05-30T11:42:19Z","title":"OCC-RAG: Optimal Cognitive Core for Faithful Question Answering","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-06-28T19:02:40.530363Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2606.00683"},"observation_digest":"sha256:81375c59924d9f9e22d0e3e0d64d058745cc17b1cb4bf92beee66726a4dfcdc7","observation_id":"9c2e99aa-f0d8-4a44-a97f-6f108bb97f73","resolution":{"observed_at":"2026-06-28T19:12:34.353666Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2606.02241","last_updated":"2026-06-01T13:36:54Z","snapshot_observed_at":"2026-08-12T14:41:01.533811Z","submitted_at":"2026-06-01T13:36:54Z","title":"BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers","version":1},"reference_index":138,"source":"arxiv_source","source_observed_at":"2026-06-28T15:29:08.917412Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2606.02241"},"observation_digest":"sha256:e4bd87ee958dddb6a86edd567a35b5b3bf5db6a118eae29efc4547b9c240e58c","observation_id":"23eb022b-3af4-4a57-ace2-f961cc82e938","resolution":{"observed_at":"2026-07-01T22:16:16.983935Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2606.12385","last_updated":"2026-06-10T17:47:59Z","snapshot_observed_at":"2026-08-15T14:37:28.125966Z","submitted_at":"2026-06-10T17:47:59Z","title":"Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-27T09:57:14.328157Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2606.12385"},"observation_digest":"sha256:a36f69a2018cf3aef8035322f72fcd1bc5e30d28188520ba56f93f9032ad7f7d","observation_id":"45769b1a-260f-4e16-a74a-edb410f85207","resolution":{"observed_at":"2026-07-03T10:37:56.557828Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2606.21627","last_updated":"2026-06-19T17:30:56Z","snapshot_observed_at":"2026-08-18T23:07:29.967741Z","submitted_at":"2026-06-19T17:30:56Z","title":"Counsel: A Meta-Evaluation Dataset for Agentic Tasks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-06-26T14:07:59.446478Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2606.21627"},"observation_digest":"sha256:5ac39c1b6158619170940b583081c4f73e784051c1d6ff0f2d77f63ad29b64db","observation_id":"d244bc3b-717b-4dba-900d-be1d31ff86d5","resolution":{"observed_at":"2026-07-04T06:49:38.218954Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":"2312.09241","doi":"10.48550/arxiv.2312.09241","metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinygsm: achieving ¿80% on gsm8k with small language models","venue":"arXiv (Cornell University)","work_id":"b8c9bef6-169c-4ef1-b50d-4f43f5818bbb","year":2023},"citing_paper":{"arxiv_id":"2606.24773","last_updated":"2026-06-23T16:33:13Z","snapshot_observed_at":"2026-08-12T11:55:48.946239Z","submitted_at":"2026-06-23T16:33:13Z","title":"Posterior Refinement: Fast Language Generation via Any-Order Flow Maps","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-25T23:55:07.047233Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2606.24773"},"observation_digest":"sha256:4b2c5e6aba64ffbba1fdf9373ae6850d06a71b5b71c80fe0fd85ccffcac6de8b","observation_id":"7d9fdb11-0947-46fb-bed3-9ce98b21e159","resolution":{"observed_at":"2026-07-04T17:09:58.835783Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09241","snapshot_observed_at":"2026-07-31T23:51:55.169989Z","title":"arXiv preprint arXiv:2312.09241 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.23333","last_updated":"2026-07-25T19:11:15Z","snapshot_observed_at":"2026-08-19T04:15:16.784414Z","submitted_at":"2026-07-25T19:11:15Z","title":"Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-07-31T23:51:55.169989Z"},"links":{"cited_paper":"/paper/2312.09241","citing_paper":"/paper/2607.23333"},"observation_digest":"sha256:9a75adc5f2ec5d3e0824eafdd1770142538cb14ad2329679be0e7831c9375e73","observation_id":"67b7a7d1-dd36-4169-ac13-3b223f207cfb","resolution":{"observed_at":"2026-07-31T23:51:55.169989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2312.09241/citation-record","integrity":"/paper/2312.09241/integrity","json":"/paper/2312.09241/citation-record.json","paper":"/paper/2312.09241"},"outbound":[],"paper":{"arxiv_id":"2312.09241","last_updated":"2023-12-14T18:58:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:34:38.785097Z","submitted_at":"2023-12-14T18:58:28Z","title":"TinyGSM: achieving >80% on GSM8k with small language models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2312.09241."}