{"as_of":"2026-08-08T18:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dd7edd446922f1549911443cabc152dc951998f2877be0fdf4cedb49c24082c0","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":17,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":17,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":17,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T11:11:42.731430Z","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":"2026-07-04T11:09:46.495658Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2211.05100","last_updated":"2023-06-27T09:57:58Z","snapshot_observed_at":"2026-08-04T18:56:03.233715Z","submitted_at":"2022-11-09T18:48:09Z","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","version":4},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-05-12T00:51:10.919818Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2211.05100"},"observation_digest":"sha256:0c09b236c9292da73033d908ee0ecf849b4d291ab6fe62cd7f5b68ccf272f655","observation_id":"0183dc41-e8f0-44ae-af56-2cc866c6845e","resolution":{"observed_at":"2026-05-12T00:51:11.419681Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2303.09014","last_updated":"2023-03-16T01:04:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-03-16T01:04:45Z","title":"ART: Automatic multi-step reasoning and tool-use for large language models","version":1},"reference_index":168,"source":"arxiv_source","source_observed_at":"2026-05-16T19:03:05.597295Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2303.09014"},"observation_digest":"sha256:5aaafd3814180dcd1c35a5c0087b5e74809b5259099767d51b9c2705e039b3b1","observation_id":"517eab86-cc0e-441a-96fa-00b5aeaf9587","resolution":{"observed_at":"2026-05-16T19:03:06.318529Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2402.19088","last_updated":"2026-04-27T09:42:01Z","snapshot_observed_at":"2026-07-06T17:37:21.849767Z","submitted_at":"2024-02-29T12:13:50Z","title":"Survey in Characterizing Semantic Change","version":5},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-05-24T03:49:31.880798Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2402.19088"},"observation_digest":"sha256:d2cd710730e9223c77c35751f87773c582b854a7a625d67a8a7cc5370e2de8e2","observation_id":"914c1f4b-09f8-4735-a256-554bf54367e4","resolution":{"observed_at":"2026-05-24T03:53:55.583672Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-08T11:11:42.731430Z","title":"Preprint, arXiv:2205.05638","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08009","last_updated":"2025-02-11T23:09:50Z","snapshot_observed_at":"2026-08-08T11:05:56.571435Z","submitted_at":"2025-02-11T23:09:50Z","title":"The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T11:11:42.731430Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2502.08009"},"observation_digest":"sha256:f7161341bb996815012735e2dd324abeafc8ba008288239ee33e46795dda176b","observation_id":"a0b866db-a1c4-4d77-b002-8242eb92c05f","resolution":{"observed_at":"2026-08-08T11:11:42.731430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-07T12:24:05.649864Z","title":"Transactions of the Association for Computational Linguistics, 12:950–978","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.24525","last_updated":"2025-05-30T12:34:28Z","snapshot_observed_at":"2026-08-07T12:16:48.432752Z","submitted_at":"2025-05-30T12:34:28Z","title":"Limited-Resource Adapters Are Regularizers, Not Linguists","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T12:24:05.649864Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2505.24525"},"observation_digest":"sha256:9741a0a918f40f24c98efaf2d8bfc47e95c478cfe05839ace31d8741fabc588d","observation_id":"ac76dc4c-03f5-4367-99ea-c1bbee681e41","resolution":{"observed_at":"2026-08-07T12:24:05.649864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-07T05:41:31.055832Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning.CoRR, abs/2205.05638, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07280","last_updated":"2025-06-10T11:37:10Z","snapshot_observed_at":"2026-08-07T10:25:31.097897Z","submitted_at":"2025-06-08T20:52:34Z","title":"From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:41:31.055832Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2506.07280"},"observation_digest":"sha256:b882d7522215aa3b374e283bdb7cb1aff8c1cb72a8c22ea8316ef5136cdd0ec9","observation_id":"441411b7-2850-41a3-b225-e8d301fcf21f","resolution":{"observed_at":"2026-08-07T05:41:31.055832Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-07T15:11:29.961290Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.11049","last_updated":"2025-08-14T14:50:40Z","snapshot_observed_at":"2026-08-07T15:05:47.466041Z","submitted_at":"2025-05-21T21:53:19Z","title":"15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:11:29.961290Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2506.11049"},"observation_digest":"sha256:30d1b33099804fa9069e700675a04847155466510700844420d3165abbccd7e3","observation_id":"1fd94bda-3dc6-41a6-8efe-f443d0c10139","resolution":{"observed_at":"2026-08-07T15:11:29.961290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-06T22:41:50.987020Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20989","last_updated":"2025-06-26T04:06:20Z","snapshot_observed_at":"2026-08-08T09:37:17.501553Z","submitted_at":"2025-06-26T04:06:20Z","title":"Can Gradient Descent Simulate Prompting?","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T22:41:50.987020Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2506.20989"},"observation_digest":"sha256:c5ff53c7fcce6e5c8e8ce688e512763644d4a6aeb515ff5d4069cb89f90d4a23","observation_id":"0f65d03e-030e-4191-bd48-1320b3b7205e","resolution":{"observed_at":"2026-08-06T22:41:50.987020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-05T12:43:43.790522Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.01314","last_updated":"2025-09-01T09:58:52Z","snapshot_observed_at":"2026-08-08T18:45:32.376784Z","submitted_at":"2025-09-01T09:58:52Z","title":"Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-05T12:43:43.790522Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2509.01314"},"observation_digest":"sha256:df5bcd29139703f22a316f827d62bc7274bc645beab6ca5908dbcfaf9ca5a131","observation_id":"4ffc1ef9-af33-4190-97f3-ab1d7d0112e3","resolution":{"observed_at":"2026-08-05T12:43:43.790522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2512.04457","last_updated":"2026-05-14T19:49:24Z","snapshot_observed_at":"2026-08-08T09:44:23.060731Z","submitted_at":"2025-12-04T05:00:52Z","title":"RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-21T17:33:06.959574Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2512.04457"},"observation_digest":"sha256:c76bf9a1a21315aaa6b345e65efee8d8cbdac45c5ef9e3d8ee1277bca465e22e","observation_id":"91c86a9d-a97f-42bd-a87d-38b9bf2b9d71","resolution":{"observed_at":"2026-05-21T17:34:17.386509Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2604.02352","last_updated":"2026-03-03T12:36:15Z","snapshot_observed_at":"2026-08-08T03:59:10.266884Z","submitted_at":"2026-03-03T12:36:15Z","title":"An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-15T16:37:16.968173Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2604.02352"},"observation_digest":"sha256:b78d1ef313c14f39bf56110f23f5ae539fd7cee07b3402752ce53549c93d9ac3","observation_id":"5d42f028-50b9-4d66-ac81-b8581d8698d8","resolution":{"observed_at":"2026-05-15T16:40:10.543066Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2604.16400","last_updated":"2026-05-15T08:08:50Z","snapshot_observed_at":"2026-08-03T05:06:36.867183Z","submitted_at":"2026-03-31T09:49:47Z","title":"CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-21T10:33:00.445749Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2604.16400"},"observation_digest":"sha256:e9d31b4f1b8ea765eab7cabb67c742938fc48d7e469249a6d67063d125644e1c","observation_id":"993e34c6-12b1-4303-a6ee-487bc8fb2f64","resolution":{"observed_at":"2026-05-21T10:34:07.212972Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2604.22783","last_updated":"2026-04-03T17:05:33Z","snapshot_observed_at":"2026-08-06T23:37:29.735410Z","submitted_at":"2026-04-03T17:05:33Z","title":"Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM Adaptation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-13T20:34:34.666827Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2604.22783"},"observation_digest":"sha256:b5560f8c007150d9568eded5cd55d567ea4744690e8c38a4cc45001e9d414339","observation_id":"82169ca3-2bc5-4a50-b2c1-730984737b82","resolution":{"observed_at":"2026-05-13T20:38:15.051606Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2604.24678","last_updated":"2026-04-27T16:38:01Z","snapshot_observed_at":"2026-07-06T23:10:38.548416Z","submitted_at":"2026-04-27T16:38:01Z","title":"Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-08T02:49:14.533263Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2604.24678"},"observation_digest":"sha256:e19be3b8e9180569a8fe70ed44d3a7e9a3907bcaf2c91b1e7d9491a2d91c159f","observation_id":"26ee190a-ae74-475e-bdc8-1bc2c744f9fc","resolution":{"observed_at":"2026-05-11T22:26:13.319211Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":"2205.05638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-07-04T11:09:46.495658Z","title":"Tam, D","venue":null,"work_id":"7f74e8fa-f34c-4991-bc0f-322b7e519b85","year":2022},"citing_paper":{"arxiv_id":"2606.24937","last_updated":"2026-07-27T15:17:17Z","snapshot_observed_at":"2026-08-02T23:19:25.465662Z","submitted_at":"2026-06-22T17:48:54Z","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","version":1},"reference_index":113,"source":"pdf_text","source_observed_at":"2026-06-26T08:09:57.542558Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2606.24937"},"observation_digest":"sha256:355a9e3d399e9e96a1d1064f3aefd9f8b27013be3675088242117caa3c64ad7a","observation_id":"2f314c38-17c0-4c41-a2a3-aa4e580d291c","resolution":{"observed_at":"2026-07-04T11:09:46.497250Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-02T10:27:18.056768Z","title":"Few-Shot Parameter-Efficient Fine- Tuning Is Better and Cheaper Than in-Context Learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.24937","last_updated":"2026-07-27T15:17:17Z","snapshot_observed_at":"2026-08-02T23:19:25.465662Z","submitted_at":"2026-06-22T17:48:54Z","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","version":2},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-02T10:27:18.056768Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2606.24937"},"observation_digest":"sha256:3d44326c695d627b6ec15820db8e594acbb1d9598af74f69ec7baa4797176fd1","observation_id":"0c5b0788-e388-4715-8218-c076df57b63c","resolution":{"observed_at":"2026-08-02T10:27:18.056768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.05638","snapshot_observed_at":"2026-08-03T00:49:10.632805Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.28669","last_updated":"2026-07-25T11:04:42Z","snapshot_observed_at":"2026-08-07T09:01:11.638556Z","submitted_at":"2026-07-25T11:04:42Z","title":"LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T00:49:10.632805Z"},"links":{"cited_paper":"/paper/2205.05638","citing_paper":"/paper/2607.28669"},"observation_digest":"sha256:c7fb45b7bb7f94a78f645c56b7471d10ccfb2ff678e838c2db92e4740336b11b","observation_id":"b97e5972-d4b9-4283-8c72-3f256778053e","resolution":{"observed_at":"2026-08-03T00:49:10.632805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2205.05638/citation-record","integrity":"/paper/2205.05638/integrity","json":"/paper/2205.05638/citation-record.json","paper":"/paper/2205.05638"},"outbound":[],"paper":{"arxiv_id":"2205.05638","last_updated":"2022-08-26T16:23:29Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T13:08:59.614061Z","submitted_at":"2022-05-11T17:10:41Z","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 17 inbound Pith citation observations for arXiv:2205.05638."}