{"as_of":"2026-08-10T14:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bbea4788699fb901c655fa3adf69400fbe4317b74c9d6750d3445ce9cf788533","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:27:11.054872Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.21835/citation-record","integrity":"/paper/2505.21835/integrity","json":"/paper/2505.21835/citation-record.json","paper":"/paper/2505.21835"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:27:17.257184Z","title":"Sparsellm: Towards global pruning of pre-trained lan- guage models","venue":null,"work_id":"6e32415a-8707-4038-b3ae-b880c55f54fd","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:07.563586Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:8b93b9d5289c231a92d7b4bd51645692238b779e8c51add1c2b2f0bd2809b65f","observation_id":"2136e17d-f7b2-4e88-91dc-a8aee51b6b5e","resolution":{"observed_at":"2026-08-07T13:27:17.301812Z","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":"2026-08-07T13:27:17.148947Z","title":"Post train- ing 4-bit quantization of convolutional networks for rapid- deployment","venue":null,"work_id":"9268572f-2c30-43c6-92b2-87dc994bb37d","year":2019},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:07.663678Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:ac5f1b3c9f0590822b83e409989cb233088756886a0fe2511ce33c8af821baba","observation_id":"50240113-56b8-40ce-a9b4-415f891df18a","resolution":{"observed_at":"2026-08-07T13:27:17.182578Z","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":"2026-08-07T13:27:16.828109Z","title":"Zeroq: A novel zero shot quantization framework","venue":null,"work_id":"a17d6c3b-ec50-4df6-a259-4730583131f3","year":2020},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:07.796259Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:dfd4f0caca7a2dca62d46abebafb28b444b17ad4839258f03c941a5891195a50","observation_id":"e872eb5b-87b9-450c-b3dc-a17cea93ea1a","resolution":{"observed_at":"2026-08-07T13:27:17.003824Z","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":"2026-08-07T13:27:16.578473Z","title":"Scatterbrain: Unifying sparse and low- rank attention","venue":null,"work_id":"20514347-9a37-4e54-98a6-20b06072db18","year":2021},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:07.923907Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:234cdd292fab1c44553ab2caced184be93bd06478b553223d5fe419b8ba788f6","observation_id":"798f4191-50b1-42c0-8432-0e3ff70663ff","resolution":{"observed_at":"2026-08-07T13:27:16.683251Z","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":"2026-08-07T13:27:16.434072Z","title":"Comprehensive survey of model compression and speed up for vision transformers.Journal of Information, Technology and Policy, pages 1–12, 2024","venue":null,"work_id":"51757c05-9948-4493-bd72-699035ede4fe","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.047062Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:da9eea7de1a1c23c81468e5aba1805d30763fed27903b21ede484cacaac0ec71","observation_id":"6b6c9809-c391-4a57-93d8-38764195f81b","resolution":{"observed_at":"2026-08-07T13:27:16.490975Z","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":"2026-08-07T13:27:16.204412Z","title":"Super- LoRA: Parameter-efficient unified adaptation for large vi- sion models","venue":null,"work_id":"59f5a83d-1164-4fa8-a195-49a2cf24ec70","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.077715Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:6643b9bcdf8393c41882e000f96e65ad10c7997cb14170de1e514a621337df86","observation_id":"7da13ec5-e43d-4ddf-b3d1-d83ad8ff2376","resolution":{"observed_at":"2026-08-07T13:27:16.327213Z","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":"2026-08-07T13:27:15.958911Z","title":"Slaying the hydra: Parameter-efficient hyper networks with low-displacement rank adaptation","venue":null,"work_id":"a03e2a8e-439d-43b2-a784-e545c7ae0549","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.205671Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:327b00e519504951f368095065f43579d183d75d0419c1ddb69724ec99657289","observation_id":"3ad0ca8d-894c-48d0-8c40-e52cb3ccf083","resolution":{"observed_at":"2026-08-07T13:27:16.044216Z","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":"2026-08-07T13:27:15.790457Z","title":"A survey on deep neural network pruning: Taxonomy, compar- ison, analysis, and recommendations","venue":null,"work_id":"755f22cb-291f-4354-9748-07eebafaf6c0","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.435669Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:93aacb3360768615cbae392439e90d8febad0301ba327a6565abf01f38cfc71b","observation_id":"3340848f-345e-4bd1-8d2b-aa2702bdf93c","resolution":{"observed_at":"2026-08-07T13:27:15.864540Z","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":"2026-08-07T13:27:15.636720Z","title":"Rethinking attention with performers","venue":null,"work_id":"bd1c589b-2987-4da0-b1da-c9c73d6ef04d","year":null},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.536882Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:22a9b6713ce6b4208bd8b66c84f42965e1c1521a05ba37bd75a5e45b56335d9c","observation_id":"83a98a25-848a-4532-9c21-8bd371858cf0","resolution":{"observed_at":"2026-08-07T13:27:15.726792Z","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":"2026-08-07T13:27:15.449231Z","title":null,"venue":null,"work_id":"c222c1d7-936b-475a-83c5-6d651a2f2716","year":2022},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.627117Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:218186fed067a28ddfa3143017fa4bc752b5e1f7a2d5f539f3970c89ba2746fd","observation_id":"9e4473d6-68fb-45f4-8056-19b68514901b","resolution":{"observed_at":"2026-08-07T13:27:15.541106Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:27:08.733767Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.733767Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:78a575a031c3a006c23f71c75963b6a3799130b9a02861447b848d3a1454f8ed","observation_id":"d7d7e1f4-f05a-4c83-87de-ba582b997024","resolution":{"observed_at":"2026-08-07T13:27:08.733767Z","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":"2026-08-07T13:27:15.269473Z","title":"KronA: Parameter efficient tuning with Kronecker adapter","venue":null,"work_id":"5880e9ff-735d-4aa6-a644-bee18253b815","year":2023},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.828401Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:981d8f4bcbe096dbff39b47dbcb4e53505cc740f6ad0fa6c9ce47727262d6dbf","observation_id":"12627876-5727-414e-954f-79423a6bfe0a","resolution":{"observed_at":"2026-08-07T13:27:15.335885Z","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":"2026-08-07T13:27:15.114387Z","title":"Sparsegpt: massive language models can be accurately pruned in one-shot","venue":null,"work_id":"b0a3b3f9-3cb9-4e4c-ad22-571156c83539","year":2023},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.904987Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:325897470053f3a2ae5d162451b28ec0466e31c8b6ebc8f7896c253c8b5873fd","observation_id":"0c6f5d1a-9081-48d5-831d-6a109dad8a09","resolution":{"observed_at":"2026-08-07T13:27:15.196928Z","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":"2406.08447","last_updated":"2024-06-12T17:38:20Z","snapshot_observed_at":"2026-08-10T00:59:34.981882Z","submitted_at":"2024-06-12T17:38:20Z","title":"The Impact of Initialization on LoRA Finetuning Dynamics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08447","snapshot_observed_at":"2026-08-07T13:27:08.973188Z","title":"The impact of initialization on lora finetuning dynamics","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:08.973188Z"},"links":{"cited_paper":"/paper/2406.08447","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:ba2db61c4558b9a2316e521d221864d88488efc1842d8ff0ca02a8ae199c73cc","observation_id":"a438a6a2-4a9c-4447-8d20-c814ef2d242d","resolution":{"observed_at":"2026-08-07T13:27:08.973188Z","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":"2026-08-07T13:27:14.969805Z","title":"Language model compression with weighted low-rank factorization","venue":null,"work_id":"1c4f5f90-4c63-47b7-9335-aa05919a08c8","year":2022},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.018629Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:f66bf3bb8cf98d9aa9b71e66825daf286d91f5a6d0888968b3a919e9378efd01","observation_id":"0e4fab44-f78f-40f0-b9f7-2a951a0ad48c","resolution":{"observed_at":"2026-08-07T13:27:15.031749Z","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":"2026-08-07T13:27:14.820340Z","title":"Lora: Low- rank adaptation of large language models","venue":null,"work_id":"83178869-a3bb-428b-9235-1e6d796053c7","year":2022},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.077556Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:aad41a17f6762f50b6fd0e58f50645e0b9bb273e11eccf8b952ce5eccd1cfc9d","observation_id":"28e35ff2-89d7-43e3-a9a2-367b03e532d8","resolution":{"observed_at":"2026-08-07T13:27:14.903328Z","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":"2026-08-07T13:27:14.699145Z","title":"Com- pressing speaker extraction model with ultra-low precision quantization and knowledge distillation","venue":null,"work_id":"0b2c5a6e-a32f-4f37-8f3a-f7fdb6ec18dd","year":2022},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.156736Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:9e9cd6a4456344436ceb7e67ffab28e9b4567d0ac09342119775394662ba8247","observation_id":"6a5a103e-deb0-4096-850b-2e4080bb7985","resolution":{"observed_at":"2026-08-07T13:27:14.756114Z","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":"2406.09117","last_updated":"2024-06-13T13:44:31Z","snapshot_observed_at":"2026-07-06T18:30:19.486766Z","submitted_at":"2024-06-13T13:44:31Z","title":"PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09117","snapshot_observed_at":"2026-08-07T13:27:09.214105Z","title":"PC-loRA: Low-rank adaptation for progressive model compression with knowledge distilla- tion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.214105Z"},"links":{"cited_paper":"/paper/2406.09117","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:e4281e43946975077b8e8436c64b5bee0bcf6dc9bdb6dbd789047ec183b641e0","observation_id":"bd50a7e3-423e-44da-a64a-bcd1ed6c7cca","resolution":{"observed_at":"2026-08-07T13:27:09.214105Z","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":"2026-08-07T13:27:14.525890Z","title":"Gpt-zip: Deep compres- sion of finetuned large language models","venue":null,"work_id":"0b135577-f754-4c47-aaca-f89525dfd2ca","year":2023},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.296116Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:8525d90233402f8844868b92b9d0420d04dc66b7e968519ce666efdd30385b17","observation_id":"47e69711-42d8-424f-9072-2ab7f25081fc","resolution":{"observed_at":"2026-08-07T13:27:14.610831Z","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":"2026-08-07T13:27:14.342596Z","title":"A neural network com- pression method based on knowledge-distillation and param- eter quantization for the bearing fault diagnosis.Applied Soft Computing, 127:109331, 2022","venue":null,"work_id":"28cf37da-b14d-4680-ac06-9aed8f910593","year":2022},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.372078Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:cc2f503feae76a08b53e738d30340dbf91e535a814c6a954d244ba864c971cf1","observation_id":"728c7c8c-c5ff-4d14-81e7-b597eb1ac161","resolution":{"observed_at":"2026-08-07T13:27:14.413962Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:27:09.460156Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.460156Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:862378fce9175b1a69b604d2f8710804f43d08b907ed97e795b9dc7343d34a48","observation_id":"c89cf26d-c698-466f-ae2b-b93659449954","resolution":{"observed_at":"2026-08-07T13:27:09.460156Z","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":"2026-08-07T13:27:14.137804Z","title":"Reward design with language models","venue":null,"work_id":"98d21ad6-d921-49e9-8cfd-ea20eb9880b9","year":2023},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.503052Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:132ee0c145d9eb4c0dd89bdffaf5414ec5dd685a9eaebcad7952006df12a19d5","observation_id":"7bd84b27-84f0-49d9-9821-3523e01404da","resolution":{"observed_at":"2026-08-07T13:27:14.224375Z","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":"2026-08-07T13:27:13.935069Z","title":"A fast post- training pruning framework for transformers","venue":null,"work_id":"0ba9f6eb-5d4f-445e-bdb8-4522bfd1c7df","year":null},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.528525Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:b63755ef8a4e333c0c77f5ff17cc506fa7ed001ab89cd130034aeda6b8be4706","observation_id":"459a16c8-a939-480d-bfe5-c16df65d2569","resolution":{"observed_at":"2026-08-07T13:27:14.027390Z","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":"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":"2410.18965","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.18965","snapshot_observed_at":"2026-08-07T13:27:11.410957Z","title":"On the Crucial Role of Initialization for Matrix Factorization","venue":"cs.LG","work_id":"7be87982-7c8a-4b45-81b7-a236aff7161d","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.604506Z"},"links":{"cited_paper":"/paper/2410.18965","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:ba261e1f46d6f9e4395f32b68fc55668f663d87d962e4dcc03524b8ef2455d0f","observation_id":"dba9a3b0-07b2-42de-be6b-b5d84cf5d726","resolution":{"observed_at":"2026-08-07T13:27:11.467656Z","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:27:13.750209Z","title":"Yolo-based face mask detection on low-end devices using pruning and quantization","venue":null,"work_id":"29c4be78-57b6-4816-b179-03cd15743ddf","year":2022},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.682337Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:8f7e4a7e43f5af20c493fb7ab2f368392aeeccd387429e69d465fe56ac501e6a","observation_id":"3b3f448b-9084-4144-9a0b-181594f09b0f","resolution":{"observed_at":"2026-08-07T13:27:13.854642Z","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":"2026-08-07T13:27:13.554583Z","title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","venue":null,"work_id":"414c1db9-7e44-4d0f-89bc-e703fde682b6","year":null},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.791674Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:3edf3d8fae1da392d144f4acbb4c5446af66f3855028d6958ad386f92f27edb7","observation_id":"28c3630b-11a2-4bd7-b888-7977dfd0de5a","resolution":{"observed_at":"2026-08-07T13:27:13.606005Z","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":"2026-08-07T13:27:13.420037Z","title":"Loda: Low-dimensional adaptation of large language models","venue":null,"work_id":"cc18b334-e1b0-48c5-8657-dfcf47a49b14","year":2023},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.850632Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:9965ee5a46562c5a82e87e05c02c831a097ad36dc3fb057f14523c73e05c5e09","observation_id":"5b687bd2-61c0-41b6-ab63-e240b78a9d5c","resolution":{"observed_at":"2026-08-07T13:27:13.489565Z","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":"2026-08-07T13:27:13.249366Z","title":"Rethinking the value of network pruning","venue":null,"work_id":"6ecdd4c4-b31f-4dd3-b489-3053d5319e52","year":null},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.886583Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:b0f004b1d95a5da887b760d7d3a9f6770e69b80891915ba9c74c6f369884f5a2","observation_id":"962da8db-f74b-4445-8fca-d8c5d8d50619","resolution":{"observed_at":"2026-08-07T13:27:13.316518Z","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":"2026-08-07T13:27:13.079670Z","title":"Com- puter vision model compression techniques for embedded systems: A survey","venue":null,"work_id":"b8ba25fe-1df3-4010-bc36-b472edf991fb","year":null},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:09.928660Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:8c5e07009ca363d18984f14a77b7cd04648b51fd9f85546ce27a3b56309fc5e1","observation_id":"beab3b1b-cf2c-4330-bc5e-88af6f82d6f4","resolution":{"observed_at":"2026-08-07T13:27:13.188385Z","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":"2403.03853","last_updated":"2024-10-11T09:43:32Z","snapshot_observed_at":"2026-08-03T01:48:18.654934Z","submitted_at":"2024-03-06T17:04:18Z","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03853","snapshot_observed_at":"2026-08-07T13:27:10.007718Z","title":"Shortgpt: Layers in large language models are more redun- dant than you expect","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.007718Z"},"links":{"cited_paper":"/paper/2403.03853","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:7bc47327176021ad266d04062bca29f7546fa38a03e83121a0e604ce9ec733f9","observation_id":"8963f463-2cd5-4565-bb02-b4f148379ddd","resolution":{"observed_at":"2026-08-07T13:27:10.007718Z","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":"2026-08-07T13:27:12.951207Z","title":"PiSSA: Principal singular values and singular vectors adaptation of large language models","venue":null,"work_id":"5b4365c7-d57a-4893-912d-8e3209dd6b1b","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.109430Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:782ca0cbc480cb9462005a0ee91358d120da92861c2ded11c65ea2230528a196","observation_id":"b80768bf-516a-4c59-9567-ac132bf8778d","resolution":{"observed_at":"2026-08-07T13:27:13.025869Z","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":"2026-08-07T13:27:12.815420Z","title":"Data-free quantization through weight equal- ization and bias correction","venue":null,"work_id":"1b800758-d2a0-4753-81b7-076eebfa9963","year":2019},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.181128Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:1df8c6d8b23be46ff9dec1578ff3f8055c943d59b61595480b2bea57b84c961c","observation_id":"dd3fa0d7-1ecc-4981-8bc7-531560141953","resolution":{"observed_at":"2026-08-07T13:27:12.859768Z","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":"2026-08-07T13:27:12.688417Z","title":"Structured unrestricted-rank matrices for parameter efficient finetuning","venue":null,"work_id":"4b28c29a-9439-4060-bb64-7f3124ca12b4","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.212515Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:c2c0008f18d670978b21037d3c39684f907b2f71f3eb1396c7ed54306528829d","observation_id":"1abad312-9419-45e0-aee5-e844a7675ae4","resolution":{"observed_at":"2026-08-07T13:27:12.754961Z","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":"2026-08-07T13:27:12.462369Z","title":"Sanity-checking prun- ing methods: Random tickets can win the jackpot","venue":null,"work_id":"2488378b-f38b-437e-a69c-7d2b3b251d92","year":null},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.273553Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:18fcf37372bfcf96640595604c2f0509db5131105ccf10ce784ecd1db88c177b","observation_id":"4afef119-3aca-4c14-92a3-0c76be11ce82","resolution":{"observed_at":"2026-08-07T13:27:12.571987Z","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":"1707.09102","last_updated":"2017-07-28T04:40:32Z","snapshot_observed_at":"2026-07-06T05:53:05.719791Z","submitted_at":"2017-07-28T04:40:32Z","title":"Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization","version":1},"cited_work":{"arxiv_id":"1707.09102","doi":null,"metadata_source":"pith","pith_arxiv_id":"1707.09102","snapshot_observed_at":"2026-08-07T13:27:11.195682Z","title":"Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization","venue":"cs.CV","work_id":"3224c19a-90ed-4345-8a47-0c66947839a9","year":2017},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.336365Z"},"links":{"cited_paper":"/paper/1707.09102","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:f00a6f2493d6fdbb07cd59b65e76cc67b82ced6f69045daf07e68f372da3fa9f","observation_id":"df4c8700-5461-4287-9bbf-68d47f7c8b5a","resolution":{"observed_at":"2026-08-07T13:27:11.252846Z","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:27:12.329792Z","title":"Gan slimming: All-in-one gan compres- sion by a unified optimization framework","venue":null,"work_id":"f43f2863-ca1f-42a0-9071-23d9ae14d275","year":2020},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.417438Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:cff2db112eb12de3e81deaf4a9809e9fd093ed4ccaea3c28119b140e6ab2a711","observation_id":"85810dff-2c11-443d-8c8c-505104d94ec4","resolution":{"observed_at":"2026-08-07T13:27:12.380482Z","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":"2026-08-07T13:27:12.242136Z","title":"Pufferfish: Communication-efficient models at no extra cost","venue":null,"work_id":"68177f21-ca4b-40b2-9010-789418bf9a0b","year":2021},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.468075Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:32a3948815ca844e2f897b50fb7b77a186831136331320cbe5f983aa3824853e","observation_id":"6ce94ae1-8776-4a69-a417-dbc03dc0484d","resolution":{"observed_at":"2026-08-07T13:27:12.277986Z","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":"2403.07378","last_updated":"2025-03-16T03:27:33Z","snapshot_observed_at":"2026-07-06T17:43:05.793351Z","submitted_at":"2024-03-12T07:31:18Z","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07378","snapshot_observed_at":"2026-08-07T13:27:10.525787Z","title":"SVD-LLM: Truncation-aware singular value decomposition for large language model compression","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.525787Z"},"links":{"cited_paper":"/paper/2403.07378","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:80d0472617fa4951fd7c664b3f0078c07225a7019f54c97e4fffea27e0464400","observation_id":"46b6a569-7155-4d36-9e62-c123388e4c4d","resolution":{"observed_at":"2026-08-07T13:27:10.525787Z","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":"2026-08-07T13:27:12.086296Z","title":"Nystr¨omformer: A nystr¨om-based algorithm for approximat- ing self-attention","venue":null,"work_id":"d3c77507-3aee-4b47-8d7b-bae84bfbd0ba","year":2021},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.607102Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:d38b3a3945d93cdcabf9ae3824bc91c58ab3386562b83d6455f2e96660a25e09","observation_id":"acb47ce2-d9d5-4612-ab10-b9452038e4f6","resolution":{"observed_at":"2026-08-07T13:27:12.169278Z","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":"2026-08-07T13:27:11.892459Z","title":"CorDA: Context-oriented decomposition adaptation of large language models for task-aware parameter-efficient fine- tuning","venue":null,"work_id":"2c321e9b-118c-439d-b4f0-d8f5d8c6f679","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.707348Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:f242f1520af848f2b9f9ac18af3f8e361867a9aeecada22d9130c5271d20fcb3","observation_id":"da3faa53-5715-459d-aa10-a821087a47ba","resolution":{"observed_at":"2026-08-07T13:27:11.985340Z","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":"2026-08-07T13:27:11.743895Z","title":"Joint-detnas: Upgrade your detector with nas, pruning and dynamic distillation","venue":null,"work_id":"56a5c3b5-6f64-4db4-a00e-b408ae363b37","year":2021},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.793181Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:12f4276ba2f4202e0807220e403ff5a50fef388e94470f813bcff420d0ead16b","observation_id":"b0abe06a-c59a-41d4-bb0b-551bcc15481c","resolution":{"observed_at":"2026-08-07T13:27:11.814204Z","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":"2026-08-07T13:27:11.575481Z","title":"Navigating text-to- image customization: From LyCORIS fine-tuning to model evaluation","venue":null,"work_id":"9f7185b3-62ac-4c45-9a7a-601ea0124f07","year":2024},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.851569Z"},"links":{"citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:5abfe6c506760287b84f35522605deebb3b82279d68a273f0dfe3cc6690334b8","observation_id":"31b33a42-4c11-4ff7-932a-855b9c58ca98","resolution":{"observed_at":"2026-08-07T13:27:11.669401Z","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":"2304.01089","last_updated":"2023-05-17T10:07:33Z","snapshot_observed_at":"2026-07-06T15:11:32.429514Z","submitted_at":"2023-04-03T15:46:15Z","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.01089","snapshot_observed_at":"2026-08-07T13:27:10.956921Z","title":"Rptq: Reorder-based post-training quantization for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:10.956921Z"},"links":{"cited_paper":"/paper/2304.01089","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:86a3e7ca0ee6ac4bf9a7a529d023001cec3b36c96d390bbdd188a6314d325b6a","observation_id":"bc21011f-198d-4ce5-9c00-4842c0696f96","resolution":{"observed_at":"2026-08-07T13:27:10.956921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.05821","last_updated":"2025-08-28T03:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-10T08:41:24Z","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.05821","snapshot_observed_at":"2026-08-07T13:27:11.054872Z","title":"ASVD: Activation-aware singular value decomposition for compressing large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:27:11.054872Z"},"links":{"cited_paper":"/paper/2312.05821","citing_paper":"/paper/2505.21835"},"observation_digest":"sha256:1064cf61cebab6d1af19b4297793f5d5602c318765ce2323024626b982ea391d","observation_id":"b83ea1fb-458f-4318-9c9a-8156c12db32f","resolution":{"observed_at":"2026-08-07T13:27:11.054872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.21835","last_updated":"2025-05-27T23:49:35Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T12:32:55.355186Z","submitted_at":"2025-05-27T23:49:35Z","title":"TuneComp: Joint Fine-tuning and Compression for Large Foundation Models"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":2,"verified_fuzzy":33},"total_outbound_references":44},"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 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2505.21835."}