{"as_of":"2026-08-08T06:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f037dc0bb5d2749e8aee97d303fcbc278c509c5bc92dc88c524fdabe719ad31","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":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":29,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T21:21:31.626024Z","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":28,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T21:21:31.626024Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.09690","last_updated":"2025-02-13T17:05:18Z","snapshot_observed_at":"2026-08-07T21:14:25.335681Z","submitted_at":"2025-02-13T17:05:18Z","title":"Trust at Your Own Peril: A Mixed Methods Exploration of the Ability of Large Language Models to Generate Expert-Like Systems Engineering Artifacts and a Characterization of Failure Modes","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T21:21:31.626024Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2502.09690"},"observation_digest":"sha256:1fae8d374a2503ce4ec0fa141bfe6d2ab89debdc33c768fcebeca1d7c426cfff","observation_id":"7f84d06a-b3ae-490e-b5f9-7b1fbebefa3d","resolution":{"observed_at":"2026-08-07T21:21:31.626024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2505.01307","last_updated":"2025-05-02T14:34:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-02T14:34:33Z","title":"Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessments","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-22T17:10:50.025349Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2505.01307"},"observation_digest":"sha256:4d925da620ab17686ed0f4cfa4e91579e85c700344c5840e6dd9500acb5be24a","observation_id":"96678b31-7f61-47ec-836f-8d7a661f6b12","resolution":{"observed_at":"2026-05-22T17:11:49.688072Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T13:53:59.151322Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method.arXiv preprint arXiv:2402.17193, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:59.151322Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:70699313ed9839f0d7eddd5b643ee36f6a3666178c71d56bc5f35430d60da83a","observation_id":"eb936d18-b3e8-45db-b6e0-b3f147d79c15","resolution":{"observed_at":"2026-08-07T13:53:59.151322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T14:21:38.805940Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23790","last_updated":"2025-05-25T22:31:24Z","snapshot_observed_at":"2026-08-07T14:13:52.832188Z","submitted_at":"2025-05-25T22:31:24Z","title":"Rethinking the Understanding Ability across LLMs through Mutual Information","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:21:38.805940Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2505.23790"},"observation_digest":"sha256:e9e3858120af97c51c9fa7b5eca760c6079fb83e67422b5a7150632a46ea4b80","observation_id":"8b00469a-94eb-41f4-85f0-20990a9834f4","resolution":{"observed_at":"2026-08-07T14:21:38.805940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T12:45:30.128496Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24034","last_updated":"2025-06-02T01:49:51Z","snapshot_observed_at":"2026-08-07T23:13:48.148542Z","submitted_at":"2025-05-29T22:14:15Z","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","version":2},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-07T12:45:30.128496Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2505.24034"},"observation_digest":"sha256:d79d442017e98a65d7858d3cd20288bed05a72483d3653fb28f88e31442dd85a","observation_id":"7010431b-99de-49de-b0f4-33e42bccc211","resolution":{"observed_at":"2026-08-07T12:45:30.128496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T05:33:55.846119Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07647","last_updated":"2025-06-09T11:12:02Z","snapshot_observed_at":"2026-08-07T22:34:01.355447Z","submitted_at":"2025-06-09T11:12:02Z","title":"Foundation Model Empowered Synesthesia of Machines (SoM): AI-native Intelligent Multi-Modal Sensing-Communication Integration","version":1},"reference_index":115,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:55.846119Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2506.07647"},"observation_digest":"sha256:726bb7d6fde6b5bd938c0f69801cc345f82a27acfb47eaa01944536df8821a02","observation_id":"4ae00e73-c389-42c5-bcd6-bf017a90b608","resolution":{"observed_at":"2026-08-07T05:33:55.846119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T05:27:33.435879Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07940","last_updated":"2025-09-03T09:39:22Z","snapshot_observed_at":"2026-08-08T05:41:22.421788Z","submitted_at":"2025-06-09T17:00:38Z","title":"Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:27:33.435879Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2506.07940"},"observation_digest":"sha256:bea531478f2cfb23c8340df4eee2b5262d3547ccc6d9e356b459c062a8ee645a","observation_id":"0d9beb9d-d86f-4265-902d-382070cf6e09","resolution":{"observed_at":"2026-08-07T05:27:33.435879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2506.11563","last_updated":"2026-05-06T22:11:53Z","snapshot_observed_at":"2026-08-07T18:17:24.844242Z","submitted_at":"2025-06-13T08:17:07Z","title":"A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-19T09:28:32.185398Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2506.11563"},"observation_digest":"sha256:ccc7b7e412b360c3852d76d9a8bd6598fabf3ce5952cb56e537c0d2d9c5fab7e","observation_id":"2a4aae37-78b6-4252-b9ca-173ed32a0b5f","resolution":{"observed_at":"2026-05-19T09:32:16.544087Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T00:40:36.690386Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13045","last_updated":"2025-08-24T10:01:04Z","snapshot_observed_at":"2026-08-08T06:33:39.031465Z","submitted_at":"2025-06-16T02:27:25Z","title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","version":4},"reference_index":246,"source":"pdf_text","source_observed_at":"2026-08-07T00:40:36.690386Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2506.13045"},"observation_digest":"sha256:6f07c1810546c58078aa36cd20f30e34ba4bff4546e6adea29a7989fc4e77205","observation_id":"876146e2-2f24-4fdf-8937-203e3db08918","resolution":{"observed_at":"2026-08-07T00:40:36.690386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T00:24:12.965494Z","title":"When scal- ing meets llm finetuning: The effect of data, model and finetuning method.arXiv preprint arXiv:2402.17193,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.14146","last_updated":"2025-06-17T03:20:41Z","snapshot_observed_at":"2026-08-07T22:13:26.061718Z","submitted_at":"2025-06-17T03:20:41Z","title":"Collaborative Editable Model","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:24:12.965494Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2506.14146"},"observation_digest":"sha256:3c3b51f533933fc869509123a2929d0b60a7b9bd62a75c671c3938048a7e3d38","observation_id":"c951fbed-399d-4aea-9353-023fb92de5e1","resolution":{"observed_at":"2026-08-07T00:24:12.965494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T12:40:25.565467Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method.arXiv preprint arXiv:2402.17193 , 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.15702","last_updated":"2025-05-30T01:54:12Z","snapshot_observed_at":"2026-08-08T01:32:10.806688Z","submitted_at":"2025-05-30T01:54:12Z","title":"Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-Distillation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:40:25.565467Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2506.15702"},"observation_digest":"sha256:4dbe708aac6346d419570c30c39b2487f69458d91a478a5fe7dc369fc0d95af3","observation_id":"0caa0043-5f84-482e-b6ae-cc4d4164c229","resolution":{"observed_at":"2026-08-07T12:40:25.565467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-06T22:44:00.581983Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20963","last_updated":"2025-07-04T01:31:36Z","snapshot_observed_at":"2026-08-06T22:34:35.092667Z","submitted_at":"2025-06-26T03:01:33Z","title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:44:00.581983Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2506.20963"},"observation_digest":"sha256:4e2a8e3c533bc22a7cfc85a7f963f0da48c880b0c1d1061e744eddaa34e434c2","observation_id":"29f86ffd-cb2c-43b0-badf-3f835637a52e","resolution":{"observed_at":"2026-08-06T22:44:00.581983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-06T12:18:39.305805Z","title":"& Firat, O","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21919","last_updated":"2025-07-30T10:11:59Z","snapshot_observed_at":"2026-08-06T12:18:32.619773Z","submitted_at":"2025-07-29T15:33:20Z","title":"Training language models to be warm and empathetic makes them less reliable and more sycophantic","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T12:18:39.305805Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2507.21919"},"observation_digest":"sha256:fa64910b7df1bab8ac5088ea5aff9ab94adb152c6a04bebc95d455a6eb8743d3","observation_id":"f94e2fab-c2ad-48f9-94ec-1794aed310c2","resolution":{"observed_at":"2026-08-06T12:18:39.305805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T19:21:54.052630Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.12800","last_updated":"2025-08-29T10:05:13Z","snapshot_observed_at":"2026-08-07T12:27:09.576328Z","submitted_at":"2025-08-18T10:23:10Z","title":"Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-05T19:21:54.052630Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2508.12800"},"observation_digest":"sha256:15b73903f637a9d102a4c450e9ea433bd83866b90b459edfda0280adbc183ec8","observation_id":"4d497f33-5882-4898-a173-b1973938d212","resolution":{"observed_at":"2026-08-05T19:21:54.052630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T11:25:23.698181Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.04512","last_updated":"2025-09-02T20:53:03Z","snapshot_observed_at":"2026-08-07T10:36:58.496060Z","submitted_at":"2025-09-02T20:53:03Z","title":"Scaling behavior of large language models in emotional safety classification across sizes and tasks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T11:25:23.698181Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2509.04512"},"observation_digest":"sha256:1022f3d1e043f25830a2a7e17822e1e51d4beac263804ec6242d2503b6fc5957","observation_id":"1f2c420c-3731-4453-acf6-e1ad4a8fa0fe","resolution":{"observed_at":"2026-08-05T11:25:23.698181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-04T13:46:16.378471Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method.arXiv preprint arXiv:2402.17193, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.25522","last_updated":"2026-06-04T23:14:09Z","snapshot_observed_at":"2026-08-05T11:58:53.582807Z","submitted_at":"2025-09-29T21:24:17Z","title":"Understanding Generative Recommendation with Semantic IDs from a Model-scaling View","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T13:46:16.378471Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2509.25522"},"observation_digest":"sha256:4d42bed9c32e415d03c7b5f3b329e5e58521fcd5e91151e1750c25544698a78b","observation_id":"273a9bd2-18d5-4fb3-881d-65896d093983","resolution":{"observed_at":"2026-08-04T13:46:16.378471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2512.05929","last_updated":"2026-06-29T18:18:24Z","snapshot_observed_at":"2026-08-03T18:19:06.255338Z","submitted_at":"2025-12-05T18:12:21Z","title":"LLM Harms: A Taxonomy and Discussion","version":2},"reference_index":212,"source":"pdf_text","source_observed_at":"2026-05-17T00:29:07.951709Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2512.05929"},"observation_digest":"sha256:168e49cf5e21803d2662d5691511af9004fe148168154ed6c14488ee54c10ff6","observation_id":"684a0b87-1f6b-484e-b0cf-109664cb90b1","resolution":{"observed_at":"2026-05-17T00:31:24.761092Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-03T18:19:30.200157Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.05929","last_updated":"2026-06-29T18:18:24Z","snapshot_observed_at":"2026-08-03T18:19:06.255338Z","submitted_at":"2025-12-05T18:12:21Z","title":"LLM Harms: A Taxonomy and Discussion","version":4},"reference_index":212,"source":"pdf_text","source_observed_at":"2026-08-03T18:19:30.200157Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2512.05929"},"observation_digest":"sha256:81dc0e8549e09d18073030e949ab29b701ad75dee5d1a9fbf63ac34f735e4409","observation_id":"0c3f770d-e2a9-4d52-9c99-4da5c185d371","resolution":{"observed_at":"2026-08-03T18:19:30.200157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2603.00989","last_updated":"2026-04-13T21:30:35Z","snapshot_observed_at":"2026-07-06T22:47:24.369805Z","submitted_at":"2026-03-01T08:32:36Z","title":"Sustainable Code Generation Using Large Language Models: A Systematic Literature Review","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-15T18:49:01.097179Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2603.00989"},"observation_digest":"sha256:e465b01732fd3167bb6a499e84bcb273f0802a43e3033fad5a2d007bafb02d0f","observation_id":"03428e5c-038a-483a-819f-a5e9c5e8a868","resolution":{"observed_at":"2026-05-15T18:50:16.541781Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2604.06202","last_updated":"2026-03-13T21:47:50Z","snapshot_observed_at":"2026-07-31T17:44:41.986774Z","submitted_at":"2026-03-13T21:47:50Z","title":"Cross-Lingual Transfer and Parameter-Efficient Adaptation in the Turkic Language Family: A Theoretical Framework for Low-Resource Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-15T11:07:44.497336Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2604.06202"},"observation_digest":"sha256:7fa08d2bcb16002037b38cf223ed0926eb5d0d4dc0dcc30441ce24faf2e2ce91","observation_id":"22144df3-e8fd-4fe4-87ad-d9e600eb5019","resolution":{"observed_at":"2026-05-15T11:09:57.864007Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2604.15270","last_updated":"2026-04-16T17:41:49Z","snapshot_observed_at":"2026-08-02T08:53:29.929171Z","submitted_at":"2026-04-16T17:41:49Z","title":"Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T10:40:30.734804Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2604.15270"},"observation_digest":"sha256:04d11723bf2a813d7c583cd45165530599cef585f1056770630946b9ef51c803","observation_id":"57fdf641-9e70-4ef6-af82-bcf1f6898954","resolution":{"observed_at":"2026-05-10T10:44:37.961327Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2604.17267","last_updated":"2026-07-09T19:09:07Z","snapshot_observed_at":"2026-08-02T10:35:57.850745Z","submitted_at":"2026-04-19T05:45:37Z","title":"Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-05-10T06:38:29.248538Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2604.17267"},"observation_digest":"sha256:da8994a9681e2fc925a765c70b7f12eae07af35bfb63f50e42a3cac6ae64ce87","observation_id":"54106b31-3a65-4f25-9807-760488a0d7ed","resolution":{"observed_at":"2026-05-10T06:41:36.670394Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2604.17778","last_updated":"2026-04-20T04:00:13Z","snapshot_observed_at":"2026-08-03T02:01:58.695602Z","submitted_at":"2026-04-20T04:00:13Z","title":"TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T06:03:50.054105Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2604.17778"},"observation_digest":"sha256:b3edda214abcaccea804776e53bbc14b65614f55d9196bc5993eff73e3abaafb","observation_id":"89ec2e04-7f40-42f3-90e3-ea99147d3eeb","resolution":{"observed_at":"2026-05-10T06:06:18.870039Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2604.18381","last_updated":"2026-04-20T15:04:57Z","snapshot_observed_at":"2026-08-02T10:52:14.752020Z","submitted_at":"2026-04-20T15:04:57Z","title":"Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T04:55:18.468593Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2604.18381"},"observation_digest":"sha256:3b1f28d27bd6aa856902ad86743554e13c56339560ee37f46659479b3e5d2e6a","observation_id":"65eec70c-7920-4546-ba76-ac031f6ac6f4","resolution":{"observed_at":"2026-05-10T11:10:09.622862Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2604.20924","last_updated":"2026-04-22T06:30:54Z","snapshot_observed_at":"2026-08-03T00:58:50.646005Z","submitted_at":"2026-04-22T06:30:54Z","title":"Clinically Interpretable Sepsis Early Warning via LLM-Guided Simulation of Temporal Physiological Dynamics","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-10T01:17:38.596865Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2604.20924"},"observation_digest":"sha256:08eb4432e3eef781da9577c9b1f1afda2484ec50649fe738cb4eeaecd48c0974","observation_id":"b6b8785f-2467-4613-8957-8c38e5a410db","resolution":{"observed_at":"2026-05-10T01:20:37.231815Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2605.21127","last_updated":"2026-05-20T12:58:01Z","snapshot_observed_at":"2026-08-06T19:06:47.472110Z","submitted_at":"2026-05-20T12:58:01Z","title":"Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-21T06:04:41.398736Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2605.21127"},"observation_digest":"sha256:eb186ca1d13958ceac72d162f916425613b308f366065fb6e870a5c2ebbbc7ab","observation_id":"455e431d-c49b-4bb3-8c8a-4c6c6675fd0e","resolution":{"observed_at":"2026-05-21T06:09:41.202991Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2606.24119","last_updated":"2026-06-23T04:09:58Z","snapshot_observed_at":"2026-07-06T23:58:44.541819Z","submitted_at":"2026-06-23T04:09:58Z","title":"When Top-1 Fails: Calibrating LoRA Monitors for Masked Diffusion LMs","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-06-26T00:49:34.365193Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2606.24119"},"observation_digest":"sha256:6458aa555498434cf3a4881ee867b461ccbae17280b492096ad6f37d2956fba1","observation_id":"db3b11df-0022-416b-bd59-f64784d43b2b","resolution":{"observed_at":"2026-07-04T16:19:56.325146Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":"2402.17193","doi":"10.48550/arxiv.2402.17193","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhang, Z","venue":"arXiv (Cornell University)","work_id":"3f7258e9-0c0f-498b-b941-8eb4c52e5b15","year":2024},"citing_paper":{"arxiv_id":"2606.30360","last_updated":"2026-06-29T14:26:13Z","snapshot_observed_at":"2026-08-02T18:18:55.136020Z","submitted_at":"2026-06-29T14:26:13Z","title":"On the Vulnerability of Parameter-Level Defenses to Model Merging","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-30T07:14:32.902738Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2606.30360"},"observation_digest":"sha256:0b41feeab6737a938b03db672b3d96134813d64aa6cfb792b2fa6665bdef95c1","observation_id":"10f96673-d50f-449a-9585-0b9a6916c0a4","resolution":{"observed_at":"2026-06-30T07:24:22.508587Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:22:16.356993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-07-11T08:20:49.438388Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05131","last_updated":"2026-07-06T14:17:44Z","snapshot_observed_at":"2026-08-08T03:58:49.160758Z","submitted_at":"2026-07-06T14:17:44Z","title":"TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-11T08:20:49.438388Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2607.05131"},"observation_digest":"sha256:c2ed298c22a35b2583f94702877f31a43da053ab2096d9e5a9a864d8c579b0e0","observation_id":"a6b17bc3-4a2c-486d-8ad8-8cf713f0d35a","resolution":{"observed_at":"2026-07-11T08:20:49.438388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.17193/citation-record","integrity":"/paper/2402.17193/integrity","json":"/paper/2402.17193/citation-record.json","paper":"/paper/2402.17193"},"outbound":[],"paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 29 inbound Pith citation observations for arXiv:2402.17193."}