{"as_of":"2026-08-10T16:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:018bc6733c3623cd4682560fcbfd2c8d075baeef9c27624530c2a765bca607f0","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T23:25:54.763519Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T19:10:58.845006Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T21:06:14.418560Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"cited_work":{"arxiv_id":"2501.18475","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.18475","snapshot_observed_at":"2026-07-01T21:06:14.418560Z","title":"arXiv preprint arXiv:2501.18475 , year=","venue":null,"work_id":"9b9492d5-3996-4b06-a088-a12749844bd7","year":2025},"citing_paper":{"arxiv_id":"2606.00494","last_updated":"2026-06-02T02:20:42Z","snapshot_observed_at":"2026-08-06T11:18:56.095781Z","submitted_at":"2026-05-30T02:54:40Z","title":"ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-06-28T19:10:58.845006Z"},"links":{"cited_paper":"/paper/2501.18475","citing_paper":"/paper/2606.00494"},"observation_digest":"sha256:b34fbae35f89aa2367ce3263b468595c35c616e20a7125fabe560ed8b265adc2","observation_id":"cc3c6953-16bf-4112-ac22-bfdcd6b34373","resolution":{"observed_at":"2026-06-28T19:12:34.514520Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"cited_work":{"arxiv_id":"2501.18475","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.18475","snapshot_observed_at":"2026-07-01T21:06:14.418560Z","title":"arXiv preprint arXiv:2501.18475 , year=","venue":null,"work_id":"9b9492d5-3996-4b06-a088-a12749844bd7","year":2025},"citing_paper":{"arxiv_id":"2606.01412","last_updated":"2026-05-31T19:17:39Z","snapshot_observed_at":"2026-08-05T23:04:35.966323Z","submitted_at":"2026-05-31T19:17:39Z","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T17:28:14.160341Z"},"links":{"cited_paper":"/paper/2501.18475","citing_paper":"/paper/2606.01412"},"observation_digest":"sha256:23832dcf90a147ec6176d69dc9691255c3dcceb71b2eea064913a3439e51980d","observation_id":"06f4f22b-a193-4b9f-9bdf-d5a6f42a51d4","resolution":{"observed_at":"2026-07-01T21:06:14.420621Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.18475/citation-record","integrity":"/paper/2501.18475/integrity","json":"/paper/2501.18475/citation-record.json","paper":"/paper/2501.18475"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.01885","last_updated":"2023-12-01T07:04:05Z","snapshot_observed_at":"2026-07-06T16:14:17.621050Z","submitted_at":"2023-09-05T01:39:09Z","title":"QuantEase: Optimization-based Quantization for Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01885","snapshot_observed_at":"2026-08-09T23:25:54.600693Z","title":"Quantease: Optimization-based quantization for language models–an efficient and intuitive algorithm.arXiv preprint arXiv:2309.01885,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.600693Z"},"links":{"cited_paper":"/paper/2309.01885","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:db5035a54af4cd335873e3a33cde3596ba8bb0b4208d2fa1c6bfd965bf2d2050","observation_id":"885e6a86-93df-4c1f-bdfb-3e81b0923770","resolution":{"observed_at":"2026-08-09T23:25:54.600693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06085","last_updated":"2018-07-17T07:33:19Z","snapshot_observed_at":"2026-07-06T06:39:21.688392Z","submitted_at":"2018-05-16T01:19:43Z","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06085","snapshot_observed_at":"2026-08-09T23:25:54.611967Z","title":"Pact: Parameterized clipping activation for quantized neural networks.arXiv preprint arXiv:1805.06085,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.611967Z"},"links":{"cited_paper":"/paper/1805.06085","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:7309773143ee45397cdb0d3d26c8a10c0d8fa85b3c52d4f74a4043dd76f782da","observation_id":"d9e48516-a85a-4377-8732-60bb2b9eb9b4","resolution":{"observed_at":"2026-08-09T23:25:54.611967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-09T23:25:54.628098Z","title":"Training verifiers to solve math word problems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.628098Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:736660e02f796f327c019f7867a0bf792515065b18a761203f926ea97ca4715a","observation_id":"b99beb5f-de6c-474e-9efe-ec9e43ddcf1c","resolution":{"observed_at":"2026-08-09T23:25:54.628098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-09T23:25:54.649320Z","title":"Lora: Low-rank adaptation of large language models.arXiv preprint arXiv:2106.09685,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.649320Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:8bcca454d5aa7593db65cbebe4802f3ea30801d9c3e4dac62fbd3d195cb7c340","observation_id":"6a55fa05-375f-4956-8652-549af3ebbc2f","resolution":{"observed_at":"2026-08-09T23:25:54.649320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.01933","last_updated":"2023-10-09T15:38:46Z","snapshot_observed_at":"2026-08-09T04:45:14.956800Z","submitted_at":"2023-04-04T16:31:37Z","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.01933","snapshot_observed_at":"2026-08-09T23:25:54.654512Z","title":"Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.654512Z"},"links":{"cited_paper":"/paper/2304.01933","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:17155fca79d96dfc09ad18e751ff7f90c0f320001af99baa5357db09247e1eda","observation_id":"d26bfd13-05ca-4ee6-a4f3-1cd29fdbc1ea","resolution":{"observed_at":"2026-08-09T23:25:54.654512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-09T23:25:54.659609Z","title":"Mistral 7b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.659609Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:3fd6cabf6be56fea9e40041885b862ef8ae5cba655b95013d9c343f9efbcaae5","observation_id":"3223d2ca-3414-498b-b0f7-80b96282dcb5","resolution":{"observed_at":"2026-08-09T23:25:54.659609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T23:25:54.664544Z","title":"Mawps: A math word problem repository","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.664544Z"},"links":{"citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:b63132b72ca029f17eabb17f25459014d958a050998ef2551680ed06cf43f31e","observation_id":"abbb87e5-cbc8-409c-b783-6f0485598551","resolution":{"observed_at":"2026-08-09T23:25:54.664544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08659","last_updated":"2023-11-28T16:06:59Z","snapshot_observed_at":"2026-08-10T01:10:20.500227Z","submitted_at":"2023-10-12T18:34:08Z","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08659","snapshot_observed_at":"2026-08-09T23:25:54.674492Z","title":"Loftq: Lora-fine-tuning-aware quantization for large language models.arXiv preprint arXiv:2310.08659, 2023a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.674492Z"},"links":{"cited_paper":"/paper/2310.08659","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:49dad1aec849a28f7058f8eb799f7beefb0408afba87c3cac64b69f6a1a2332c","observation_id":"3a7dc95f-8886-4098-b396-fb5cc10540bb","resolution":{"observed_at":"2026-08-09T23:25:54.674492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.04146","last_updated":"2017-10-23T16:45:03Z","snapshot_observed_at":"2026-08-02T16:52:38.363314Z","submitted_at":"2017-05-11T13:04:47Z","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.04146","snapshot_observed_at":"2026-08-09T23:25:54.679881Z","title":"Program induction by rationale generation: Learning to solve and explain algebraic word problems.arXiv preprint arXiv:1705.04146,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.679881Z"},"links":{"cited_paper":"/paper/1705.04146","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:8ecc0f204c9c7dde4b6133fe319a72fb91bc78d11b9cbff8db76c536411d9145","observation_id":"561f9e6f-29ca-478c-8bca-35f14510a27d","resolution":{"observed_at":"2026-08-09T23:25:54.679881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-09T23:25:54.689805Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.689805Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:a9c6e9c39f9f136a4675b36e9c1e93aea4f8faa164b277d7886882dde54fa432","observation_id":"ad512f46-2136-4a7f-8be7-210d0e2234b3","resolution":{"observed_at":"2026-08-09T23:25:54.689805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07843","last_updated":"2016-09-26T04:06:13Z","snapshot_observed_at":"2026-07-06T05:12:10.387914Z","submitted_at":"2016-09-26T04:06:13Z","title":"Pointer Sentinel Mixture Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07843","snapshot_observed_at":"2026-08-09T23:25:54.694842Z","title":"Pointer sentinel mixture models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.694842Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:d73934adb3c43bcfa09f484ac85c0d19831094fa9bb7d075e8604ee273960a9f","observation_id":"4422294a-dcf1-4c9c-bfae-3ba4d3e4d092","resolution":{"observed_at":"2026-08-09T23:25:54.694842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02789","last_updated":"2018-09-08T11:47:16Z","snapshot_observed_at":"2026-08-08T02:19:52.596062Z","submitted_at":"2018-09-08T11:47:16Z","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02789","snapshot_observed_at":"2026-08-09T23:25:54.700012Z","title":"Can a suit of armor conduct electricity? a new dataset for open book question answering.arXiv preprint arXiv:1809.02789,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.700012Z"},"links":{"cited_paper":"/paper/1809.02789","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:cf141c8299729932efff6e50ef3b37408b7e4be1260b10607d0afc7bfa427b93","observation_id":"f2cf3bd9-12ea-4ea3-8a4b-afafa3ef4b90","resolution":{"observed_at":"2026-08-09T23:25:54.700012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.07191","last_updated":"2021-04-15T06:11:12Z","snapshot_observed_at":"2026-08-07T13:11:17.300265Z","submitted_at":"2021-03-12T10:23:47Z","title":"Are NLP Models really able to Solve Simple Math Word Problems?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.07191","snapshot_observed_at":"2026-08-09T23:25:54.704986Z","title":"Are nlp models really able to solve simple math word problems? arXiv preprint arXiv:2103.07191,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.704986Z"},"links":{"cited_paper":"/paper/2103.07191","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:3d10f6e7384b6aa58d61dbd7190be783835b2d55def115806a7831e8d13bb5c9","observation_id":"81b44fd4-26c9-499d-a434-7dac2eb6be13","resolution":{"observed_at":"2026-08-09T23:25:54.704986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.09728","last_updated":"2019-09-09T17:29:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-04-22T05:36:37Z","title":"SocialIQA: Commonsense Reasoning about Social Interactions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.09728","snapshot_observed_at":"2026-08-09T23:25:54.709780Z","title":"Socialiqa: Commonsense reasoning about social interactions.arXiv preprint arXiv:1904.09728,","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.709780Z"},"links":{"cited_paper":"/paper/1904.09728","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:91b6f53af15cbd81373fa30e99512a8807918c688f58c7146aa1b97d35b4c36c","observation_id":"699b2112-e378-464f-9b71-200ee91796c7","resolution":{"observed_at":"2026-08-09T23:25:54.709780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.13137","last_updated":"2024-03-18T05:33:22Z","snapshot_observed_at":"2026-07-06T16:10:15.694898Z","submitted_at":"2023-08-25T02:28:35Z","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.13137","snapshot_observed_at":"2026-08-09T23:25:54.715241Z","title":"Omniquant: Omnidirectionally calibrated quantization for large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.715241Z"},"links":{"cited_paper":"/paper/2308.13137","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:e40f597fe266e2f787579ea6f201688d220604b3551ac2f60f2611fe90ab7770","observation_id":"0c9d6478-6e43-446e-a317-3624827d4102","resolution":{"observed_at":"2026-08-09T23:25:54.715241Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-09T23:25:54.720016Z","title":"Llama 2: Open foundation and fine-tuned chat models.arXiv preprint arXiv:2307.09288,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.720016Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:019c94ff5ebff72228d7fa5d4eb403b586569a871bb705d2108097486381a3fb","observation_id":"ae3df061-f198-4be6-bcbd-fef63154ddbe","resolution":{"observed_at":"2026-08-09T23:25:54.720016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10777","last_updated":"2024-10-15T19:47:15Z","snapshot_observed_at":"2026-07-06T18:31:36.504766Z","submitted_at":"2024-06-16T02:08:49Z","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10777","snapshot_observed_at":"2026-08-09T23:25:54.724690Z","title":"Roselora: Row and column-wise sparse low-rank adaptation of pre-trained language model for knowledge editing and fine-tuning.arXiv preprint arXiv:2406.10777, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.724690Z"},"links":{"cited_paper":"/paper/2406.10777","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:a646ef22ab7e8370f591bc00462ffdeda96705789bbdbacfba0a03fbbd7fbea6","observation_id":"567223a1-6a0c-49e3-9e9b-e05fb30b36e5","resolution":{"observed_at":"2026-08-09T23:25:54.724690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05000","last_updated":"2024-07-16T07:32:23Z","snapshot_observed_at":"2026-07-06T18:42:18.289966Z","submitted_at":"2024-07-06T08:37:21Z","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05000","snapshot_observed_at":"2026-08-09T23:25:54.729617Z","title":"Lora-ga: Low-rank adaptation with gradient approximation.arXiv preprint arXiv:2407.05000, 2024b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.729617Z"},"links":{"cited_paper":"/paper/2407.05000","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:7a3dab08690ad129d3d6ecff55b8f4606de9ca5f81203d7be405ff8f65a1c24d","observation_id":"77b962e6-f603-4aa6-935c-5c150fe21e99","resolution":{"observed_at":"2026-08-09T23:25:54.729617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08302","last_updated":"2023-05-26T00:17:06Z","snapshot_observed_at":"2026-08-04T07:05:46.232759Z","submitted_at":"2023-03-15T01:27:15Z","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08302","snapshot_observed_at":"2026-08-09T23:25:54.734518Z","title":"Zeroquant-v2: Exploring post-training quantization in llms from comprehensive study to low rank compensation.arXiv preprint arXiv:2303.08302,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.734518Z"},"links":{"cited_paper":"/paper/2303.08302","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:e998700eebdc1bc20d7e2e05c93dc538fa745f61cd5f854ffae15f6345584aa9","observation_id":"dae832e8-680d-4d9d-b77b-e0f4a1f3b475","resolution":{"observed_at":"2026-08-09T23:25:54.734518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.06052","last_updated":"2017-08-17T06:56:17Z","snapshot_observed_at":"2026-07-06T05:23:15.238465Z","submitted_at":"2016-12-19T05:54:18Z","title":"Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection","version":2},"cited_work":{"arxiv_id":"1612.06052","doi":null,"metadata_source":"pith","pith_arxiv_id":"1612.06052","snapshot_observed_at":"2026-08-09T23:25:54.832031Z","title":"Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection","venue":"cs.LG","work_id":"ea0ac32c-b9cd-472a-a334-b00c6751fed0","year":2016},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.739234Z"},"links":{"cited_paper":"/paper/1612.06052","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:7d14fa379f5b17d9eaad8cff97984af64c3ec6c2e6c3314f083179966e5cde69","observation_id":"5ee09635-d575-4d3c-8ecd-3ef489f995c9","resolution":{"observed_at":"2026-08-09T23:25:54.839680Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-07-31T00:09:56.948833Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-09T23:25:54.743907Z","title":"Understanding straight-through estimator in training activation quantized neural nets","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.743907Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:e71af9a2984ba05c10a80b44ec95224a9152e53fb1b08eea6591aeb4acb2d598","observation_id":"8dcd9155-3d1c-4108-a012-1a55e9d8140b","resolution":{"observed_at":"2026-08-09T23:25:54.743907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07134","last_updated":"2024-10-19T17:07:51Z","snapshot_observed_at":"2026-08-09T09:19:49.246962Z","submitted_at":"2024-03-11T20:04:03Z","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07134","snapshot_observed_at":"2026-08-09T23:25:54.749430Z","title":"Magr: Weight magnitude reduction for enhancing post-training quantization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.749430Z"},"links":{"cited_paper":"/paper/2403.07134","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:673200a0c55cf2a81debf2cbcecfd5aa549e994c858dd171176f013f041fd5ab","observation_id":"66848603-ace9-4f60-8543-f243625a1f1e","resolution":{"observed_at":"2026-08-09T23:25:54.749430Z","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":"2026-08-09T23:25:55.300750Z","title":"Multiple task Following the framework proposed by Hu et al","venue":null,"work_id":"53673106-f338-4503-9cd6-2c12a7af67a6","year":2023},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.754290Z"},"links":{"citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:f012137b91916cf0728b8a6e582d3f722852857d2201c89a6677649409d534d7","observation_id":"a0115d7a-e950-413f-810d-203a3114f72a","resolution":{"observed_at":"2026-08-09T23:25:55.305822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T23:25:55.284595Z","title":null,"venue":null,"work_id":"6a80153e-b727-48d2-a87a-a1e3855e4792","year":2023},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.758851Z"},"links":{"citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:1030a9d6fe35d40751205ce29bd824b68d0b8c63ea92720a59cfe9ee2ade7f82","observation_id":"c6a1093f-108d-4d69-9ba7-8d4f4b3a9e55","resolution":{"observed_at":"2026-08-09T23:25:55.289625Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T23:25:55.268066Z","title":"16 Published in Transactions on Machine Learning Research (08/2025) Table 11: Hyper-parameter for the finetuning of Llama2","venue":null,"work_id":"45159a0a-1b01-4108-8781-8a926f4bf752","year":2025},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.763519Z"},"links":{"citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:db3f0e73463d58e6f257cef943a5df5f99fdc8744717bd48ddc2e8d29c16a6e4","observation_id":"c7f5ddc8-ef34-4cbb-aba4-5999d39a584c","resolution":{"observed_at":"2026-08-09T23:25:55.273333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-07T08:38:54.025062Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-09T23:25:54.638946Z","title":"Gptq: Accurate post-training quantization for generative pre-trained transformers.arXiv preprint arXiv:2210.17323, 2022a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":1936,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.638946Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:717377d40dd6644c2cbcdac723209ca7082d18d3089a9a8624a7d1e63bf819d6","observation_id":"a054d16f-d625-4c90-b89c-24b86033cb49","resolution":{"observed_at":"2026-08-09T23:25:54.638946Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.18965","last_updated":"2024-12-12T19:54:41Z","snapshot_observed_at":"2026-07-06T19:39:15.025945Z","submitted_at":"2024-10-24T17:58:21Z","title":"On the Crucial Role of Initialization for Matrix Factorization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.18965","snapshot_observed_at":"2026-08-09T23:25:54.669559Z","title":"On the crucial role of initialization for matrix factorization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.669559Z"},"links":{"cited_paper":"/paper/2410.18965","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:88382d6cc3e4bd19f56a3aada0f60ba5c71dffa61afe4ddec422bd78eb5a6eca","observation_id":"0bfc115f-2319-4bef-93ed-2ddbc5b2e46f","resolution":{"observed_at":"2026-08-09T23:25:54.669559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09353","last_updated":"2024-07-09T05:59:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-14T17:59:34Z","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09353","snapshot_observed_at":"2026-08-09T23:25:54.685028Z","title":"Dora: Weight-decomposed low-rank adaptation.arXiv preprint arXiv:2402.09353,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.685028Z"},"links":{"cited_paper":"/paper/2402.09353","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:f7a0006e45ab271a2edb33603cea7bee87dad329667c81ab28dedb65850c2671","observation_id":"f1eac84f-ef7c-4762-9ded-a8aabe35e62a","resolution":{"observed_at":"2026-08-09T23:25:54.685028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10044","last_updated":"2019-05-24T05:48:49Z","snapshot_observed_at":"2026-07-06T07:55:12.121264Z","submitted_at":"2019-05-24T05:48:49Z","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10044","snapshot_observed_at":"2026-08-09T23:25:54.617311Z","title":"Boolq: Exploring the surprising difficulty of natural yes/no questions.arXiv preprint arXiv:1905.10044,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.617311Z"},"links":{"cited_paper":"/paper/1905.10044","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:bdcc1b5a5355dcfa24a99cc89c598f3320ae2fe6f356c2eef5f55a0a7a125ee1","observation_id":"e0d968b9-c366-46cc-9bc5-5ba728df7430","resolution":{"observed_at":"2026-08-09T23:25:54.617311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-09T23:25:54.622902Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge.arXiv preprint arXiv:1803.05457,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.622902Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:15871bfacb352aca1858ae4c888fdef669cefec08ddef99650a90c0f813f05e3","observation_id":"91ae33e6-8d75-46fb-949a-84ca7b7b57c9","resolution":{"observed_at":"2026-08-09T23:25:54.622902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01775","last_updated":"2024-11-25T12:45:19Z","snapshot_observed_at":"2026-08-09T04:52:08.104539Z","submitted_at":"2024-06-03T20:37:27Z","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01775","snapshot_observed_at":"2026-08-09T23:25:54.606104Z","title":"Olora: Orthonormal low-rank adaptation of large language models.arXiv preprint arXiv:2406.01775,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.606104Z"},"links":{"cited_paper":"/paper/2406.01775","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:b8620b3e2095a98c510780778104ee7869ede65771330d7c253759b840457ca4","observation_id":"9e104309-e2c0-4707-8e22-21abd23b6db3","resolution":{"observed_at":"2026-08-09T23:25:54.606104Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-08-09T23:25:54.633860Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.633860Z"},"links":{"cited_paper":"/paper/2305.14314","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:1717944e0ade55856f2bae29e0d109f962cd88acd4fe70ec8be92c28d8d34718","observation_id":"bdf64f87-139a-4a4d-b0f3-1fe4e7269b0f","resolution":{"observed_at":"2026-08-09T23:25:54.633860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-09T23:25:54.594753Z","title":"com/qwopqwop200/gptqlora","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.594753Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:e853d534d37a0f20cce5a06b3f086400c1e52f861e362f0d82b302b170d38b80","observation_id":"eaa54dd3-4829-4916-bb43-238c76bb5230","resolution":{"observed_at":"2026-08-09T23:25:54.594753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14196","last_updated":"2024-01-26T09:23:11Z","snapshot_observed_at":"2026-08-06T22:40:28.707813Z","submitted_at":"2024-01-25T14:17:53Z","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14196","snapshot_observed_at":"2026-08-09T23:25:54.643828Z","title":"Deepseek-coder: When the large language model meets programming–the rise of code intelligence","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T23:25:54.643828Z"},"links":{"cited_paper":"/paper/2401.14196","citing_paper":"/paper/2501.18475"},"observation_digest":"sha256:747ce8defd072b13de25f90504f0355d5540a7aa6afea840917d0dc324f879d2","observation_id":"7f997571-ba7c-45c3-ac2e-a42b34c81b1d","resolution":{"observed_at":"2026-08-09T23:25:54.643828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.18475","last_updated":"2025-08-14T03:12:42Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T01:10:45.458704Z","submitted_at":"2025-01-30T16:48:15Z","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":1,"verified_fuzzy":2},"total_outbound_references":34},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2501.18475."}