{"as_of":"2026-08-14T18:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c75c1bd2128653b5717c6a6dd8ed25dec3ac7f8415f65ad59b7342883149d4ff","coverage":[{"denominator":16,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T20:53:30.040384Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.01806/citation-record","integrity":"/paper/2507.01806/integrity","json":"/paper/2507.01806/citation-record.json","paper":"/paper/2507.01806"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:31.951299Z","title":null,"venue":null,"work_id":"362cdd8d-f592-4f18-b986-b7799953dfe1","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.269447Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:1ae7b4ef75194835e96476966b516b3358ca77d205d0bcdc9bba039161dc3bb6","observation_id":"5e524735-6763-44de-85c8-3fc4b97d08e1","resolution":{"observed_at":"2026-08-06T20:53:32.071309Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:31.744716Z","title":null,"venue":null,"work_id":"cf56222d-a210-4f13-9e0a-c448fc6f6633","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.350974Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:c0dedaeb7af4991a02325b4aff4dc5b9d66f8e82bfd97d82fc6c94ca83556143","observation_id":"0bb92516-8d41-4492-83d5-c5268134d127","resolution":{"observed_at":"2026-08-06T20:53:31.853600Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:31.457737Z","title":"Table 2 reports the time elapsed at each stage of our LoRA generation pipeline, measured on a Dell XPS15 (Intel i7-13700H, 14 cores, 64 GB RAM)","venue":null,"work_id":"819b0699-b49d-4529-86d5-49ac0d9bb016","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.429079Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:12dc72f430341daebe982ef16e73bef191c05d85b55e26e67fe21f49f156908f","observation_id":"2a76d948-1307-4ca7-b022-c0dc7e660e54","resolution":{"observed_at":"2026-08-06T20:53:31.617369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:30.512031Z","title":null,"venue":null,"work_id":"12c475a6-f15e-4b58-b4cb-2aab76301439","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.873779Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:c1101c0e997f1d8f3130b544a22c833f0a7cdfd026173534045d73640f4c3cfa","observation_id":"3ec061e2-af84-449a-8e14-65fd3695a15d","resolution":{"observed_at":"2026-08-06T20:53:30.620387Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:30.283796Z","title":"Expected Answer:","venue":null,"work_id":"d34b72ff-cbcb-4150-b3a8-6ebe6f7607be","year":2001},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:30.040384Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:5f219f189631a1094be22788dbfb0cf2fd49605b07d36215def3e603fe69f358","observation_id":"74803aef-1d6b-4b9d-8ed7-cceae4d72263","resolution":{"observed_at":"2026-08-06T20:53:30.366741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:32.523772Z","title":null,"venue":null,"work_id":"5111b0ee-ce8c-49c1-872c-38ec9b56b2d3","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.001816Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:da9c20b6b89f4621f4dc8e9a8d5a5cefefc99aba50ccd3865ea67e37d7914456","observation_id":"5426550e-568e-484e-bcc5-132c9ecf6edb","resolution":{"observed_at":"2026-08-06T20:53:32.661214Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:29.093799Z","title":"URL https: //doi.org/10.1007/978-3-030-56402-5","venue":null,"work_id":null,"year":1951},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.093799Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:9f4337b1b60279fba1d58b558e496ad21760403f094017baef0e1056fdbf0042","observation_id":"3f1efa76-fa9b-43c9-ad2e-8aa4959e660e","resolution":{"observed_at":"2026-08-06T20:53:29.093799Z","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":"2026-08-06T20:53:31.212390Z","title":null,"venue":null,"work_id":"e60aaae6-b264-4ebf-ba19-4882add234ca","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.522326Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:174f951932afc39e51ef8454becf0f1ae602b8b5e6957b92eaefeb97e575f72d","observation_id":"2c4ae8f2-ff1e-4c9e-b206-6e191f34e009","resolution":{"observed_at":"2026-08-06T20:53:31.334895Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:30.937613Z","title":null,"venue":null,"work_id":"d29d337d-8a80-42c4-a32d-c0d5d48707f6","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.598399Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:5067a410187dd18f4d43c9f1a181b7bebd9ef1e1dff8eef6f959781cc2a7ff7b","observation_id":"4f97af6a-aced-4721-99b9-8dd869d1cd25","resolution":{"observed_at":"2026-08-06T20:53:31.069823Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:30.735551Z","title":null,"venue":null,"work_id":"097b987a-8642-4e14-9b1b-067e8cf93399","year":null},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.759056Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:1c404b3d5e7adb4bc2c298a2248284a945200ee5dd9884dcf215d1d90d0e7dba","observation_id":"eec41203-6178-449d-bdc8-513b22a1982b","resolution":{"observed_at":"2026-08-06T20:53:30.851551Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:28.894826Z","title":"A hitchhiker’s guide","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:28.894826Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:8de2e6584a27c60d74ac5439e2ad0cc67e97f8302c6e92aa62205a41a95926aa","observation_id":"a9e8ba4a-892b-4025-ac4f-ef500716d49d","resolution":{"observed_at":"2026-08-06T20:53:28.894826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.06904","last_updated":"2022-03-15T01:22:04Z","snapshot_observed_at":"2026-08-14T04:13:11.821456Z","submitted_at":"2022-03-14T07:56:32Z","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.06904","snapshot_observed_at":"2026-08-06T20:53:28.445295Z","title":"doi: 10.18653/v1/2020.emnlp-demos.7","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:28.445295Z"},"links":{"cited_paper":"/paper/2203.06904","citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:5c3b2c440c80a27abf9b1ed2ee6097fa425541be0437c7babfe49cc5dd9fc4ec","observation_id":"67e36b4f-4bfb-4796-94a9-3423ad939ee1","resolution":{"observed_at":"2026-08-06T20:53:28.445295Z","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":"2026-08-06T20:53:32.244607Z","title":"copy” of S in “distance domain","venue":null,"work_id":"54b0c155-8c44-4eb4-bad4-d13038912ab1","year":2020},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:29.194089Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:05e914a78d0824f767799ecdfa993b434c2c339268082640bac1c8b5a9eefd0b","observation_id":"d4af1f95-1c90-4b2e-8194-888929e98ca8","resolution":{"observed_at":"2026-08-06T20:53:32.364385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:53:32.822643Z","title":"Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath, Ivan Vuli´c, Sebastian Ruder, Kyunghyun Cho, and Iryna Gurevych","venue":null,"work_id":"1c787368-b622-49ef-a4da-253584173c53","year":2020},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:28.342804Z"},"links":{"citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:991517050bb8c0b0ec7889f2e92c932c72551d4399a76b6862ff8e7f3828c5fd","observation_id":"5d781889-c3e9-47a4-ad91-8cd4cc408c68","resolution":{"observed_at":"2026-08-06T20:53:32.928779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10752","last_updated":"2022-04-13T11:38:44Z","snapshot_observed_at":"2026-07-06T12:20:47.369918Z","submitted_at":"2021-12-20T18:55:25Z","title":"High-Resolution Image Synthesis with Latent Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10752","snapshot_observed_at":"2026-08-06T20:53:28.617124Z","title":"Xin Li, Dongze Lian, Zhihe Lu, Jiawang Bai, Zhibo Chen, and Xinchao Wang","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:28.617124Z"},"links":{"cited_paper":"/paper/2112.10752","citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:d9a48cd3fcd0fb4bb2cd92fff5c639b4f62360ac6991f2239383b8b2826208a3","observation_id":"461fffb6-3e5d-4d2f-91ee-61c23dff2ad3","resolution":{"observed_at":"2026-08-06T20:53:28.617124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14314","last_updated":"2023-05-23T17:50:33Z","snapshot_observed_at":"2026-08-13T23:56:42.354755Z","submitted_at":"2023-05-23T17:50:33Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14314","snapshot_observed_at":"2026-08-06T20:53:28.773451Z","title":"Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:28.773451Z"},"links":{"cited_paper":"/paper/2305.14314","citing_paper":"/paper/2507.01806"},"observation_digest":"sha256:23b8159f3337922e2a48553ddfb78bb8d78e3030c3d0412db97183c7ddd296a0","observation_id":"7e44a120-e246-4620-b9dd-d876daa9179c","resolution":{"observed_at":"2026-08-06T20:53:28.773451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.01806","last_updated":"2025-07-02T15:24:47Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T13:00:29.277080Z","submitted_at":"2025-07-02T15:24:47Z","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs"},"reference_resolution":{"displayed":16,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":16},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2507.01806."}