{"as_of":"2026-08-10T14:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:454697500e691ace07404b3414e0d9ca094678079bca1f9965f513ed077eb05e","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":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":35,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T12:35:02.200490Z","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":"2026-07-04T18:00:01.488346Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-05-11T16:34:04.488351Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2104.08691"},"observation_digest":"sha256:e1975e3b9962ebb6659ed46d4c9cd3509f5e5b45d525b28257f24a6719c21f4a","observation_id":"278d1412-9c50-403a-b232-b2412d795d7d","resolution":{"observed_at":"2026-05-11T16:34:05.315601Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2104.08773","last_updated":"2022-03-14T09:15:08Z","snapshot_observed_at":"2026-08-05T18:13:22.401467Z","submitted_at":"2021-04-18T08:44:56Z","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","version":4},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-05-18T01:57:29.380571Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2104.08773"},"observation_digest":"sha256:da928ec0f14b5e6dd519ed42fa0c8a6fe3d0fcce1705881b3c687e7ecaacda99","observation_id":"8543792e-2e95-4428-b62b-32b9bc96da80","resolution":{"observed_at":"2026-05-18T01:57:29.423919Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_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},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-09T05:01:39.906340Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2106.09685"},"observation_digest":"sha256:091243756b47e053e3e89b10d13ea9aafb4cd119f678cad1faf7879b1d0da02f","observation_id":"994a3588-df0a-47c3-bad9-0bbdf31393a5","resolution":{"observed_at":"2026-05-09T05:01:40.853496Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2202.12837","last_updated":"2022-10-20T14:04:10Z","snapshot_observed_at":"2026-08-01T15:23:39.998892Z","submitted_at":"2022-02-25T17:25:19Z","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","version":2},"reference_index":119,"source":"arxiv_source","source_observed_at":"2026-05-15T09:51:46.701149Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2202.12837"},"observation_digest":"sha256:fbe8166ff0d18506be27fc004a7a52f6be05388859f9054c85eb6f40bf95af27","observation_id":"35a825f4-5f8b-4bf9-bcae-a1341999a07d","resolution":{"observed_at":"2026-05-15T09:51:46.812580Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"reference_index":133,"source":"arxiv_source","source_observed_at":"2026-05-10T20:53:16.720145Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2205.01068"},"observation_digest":"sha256:8a00678aea347f1c44e41a81eb6be802941baee3e50f5dd3e336dd43982472c3","observation_id":"14715225-a925-46c1-82f9-336b1970bf3d","resolution":{"observed_at":"2026-05-10T20:53:17.511748Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2211.16327","last_updated":"2026-04-24T13:45:07Z","snapshot_observed_at":"2026-08-08T11:08:14.507971Z","submitted_at":"2022-11-29T16:10:11Z","title":"On the Power of Foundation Models","version":6},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-24T10:46:59.388165Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2211.16327"},"observation_digest":"sha256:f9313d9b5d3047892a55bf8771dc78f01ed02d7d1760004da7a26f2d32a4455f","observation_id":"5b546b10-9fa6-4563-b150-591bb119f591","resolution":{"observed_at":"2026-05-24T10:49:21.367677Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2303.16199","last_updated":"2024-09-18T23:54:36Z","snapshot_observed_at":"2026-08-06T06:36:02.994951Z","submitted_at":"2023-03-28T17:59:12Z","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-05-14T23:07:42.245641Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2303.16199"},"observation_digest":"sha256:6840ca6eea2ba9cd168c0cc73d2deb3645fff4a5eef3e7236115e7e3fb03c8a5","observation_id":"acc6c81f-25a2-4da5-9070-8e02225d61ca","resolution":{"observed_at":"2026-05-14T23:07:42.957216Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2305.07922","last_updated":"2023-05-20T07:27:15Z","snapshot_observed_at":"2026-08-08T01:28:05.271964Z","submitted_at":"2023-05-13T14:23:07Z","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-19T05:26:57.440959Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2305.07922"},"observation_digest":"sha256:68c3b73b8d21e8733cf1265f5828ffe59fb147bb39916e57427878faa9eb30df","observation_id":"02374def-aefd-4bb4-81d3-7a66ea08e631","resolution":{"observed_at":"2026-05-19T05:26:57.553242Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2305.09617","last_updated":"2023-05-16T17:11:29Z","snapshot_observed_at":"2026-08-03T08:52:05.725675Z","submitted_at":"2023-05-16T17:11:29Z","title":"Towards Expert-Level Medical Question Answering with Large Language Models","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-05-24T04:32:33.271634Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2305.09617"},"observation_digest":"sha256:2dc98ab05d9be271e8347bb828ba01634c91e7ad4859fae743115d25f58f6ba6","observation_id":"68e2ee75-b0cb-4699-ab88-3c9e81e585b5","resolution":{"observed_at":"2026-05-24T04:32:33.574956Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2305.14233","last_updated":"2023-05-23T16:49:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-23T16:49:14Z","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","version":1},"reference_index":165,"source":"arxiv_source","source_observed_at":"2026-05-15T17:25:07.730933Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2305.14233"},"observation_digest":"sha256:b2b77e52f4dc586fac2cd9f947da7b0fe697571207c6d28145f1f2398fe717f5","observation_id":"332b6033-3bb5-44ad-a446-1926af15c99a","resolution":{"observed_at":"2026-05-15T17:25:08.125832Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2307.06435","last_updated":"2024-10-17T01:10:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-12T20:01:52Z","title":"A Comprehensive Overview of Large Language Models","version":10},"reference_index":247,"source":"pdf_text","source_observed_at":"2026-05-19T20:28:38.900026Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2307.06435"},"observation_digest":"sha256:84e277dc1f055dc993e9292d60990a8f2011397afed151cf3df4e39481029e99","observation_id":"614fa362-09f2-4eb7-8048-f9da50b1d6dc","resolution":{"observed_at":"2026-05-19T20:28:39.111826Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2309.03409","last_updated":"2024-04-15T07:50:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-07T00:07:15Z","title":"Large Language Models as Optimizers","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-15T00:04:31.212102Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2309.03409"},"observation_digest":"sha256:fdb40c029a67dd24afb0dcb6cf0ab54c60346c9d0b0e4a9c00c043e4c46c9226","observation_id":"ea55b48a-bd5f-4686-83f8-c8c6059f6665","resolution":{"observed_at":"2026-05-15T00:04:31.289275Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2309.08532","last_updated":"2025-05-01T11:56:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-15T16:50:09Z","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","version":3},"reference_index":110,"source":"arxiv_source","source_observed_at":"2026-05-16T06:11:49.475825Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2309.08532"},"observation_digest":"sha256:aa62b178bface1e7eaf4a366fea1b5dbde11d8eeab11a482dc50014f41e38b48","observation_id":"4e89dd82-88f9-467a-aba7-05298eb67f0f","resolution":{"observed_at":"2026-05-16T06:11:49.596632Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-13T11:32:36.738536Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2403.14608"},"observation_digest":"sha256:bd8ae35449e47249bebdab9e122357c423c4501bc7ce7d06db4b5441d5e3a681","observation_id":"be038804-055f-4b3e-85ae-9776aeb4c6fa","resolution":{"observed_at":"2026-05-13T11:32:37.170459Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-10T12:35:02.200490Z","title":"Gpt understands, too,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.16542","last_updated":"2025-01-27T22:26:37Z","snapshot_observed_at":"2026-08-10T12:26:45.272390Z","submitted_at":"2025-01-27T22:26:37Z","title":"UniPET-SPK: A Unified Framework for Parameter-Efficient Tuning of Pre-trained Speech Models for Robust Speaker Verification","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T12:35:02.200490Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2501.16542"},"observation_digest":"sha256:05d555cdb0b9fda33e10a8ce73cadf1cfdc5d7f75c35f8e54d20574d5f5d5829","observation_id":"a16ea2ac-c48d-4d2a-a2aa-21317d93527e","resolution":{"observed_at":"2026-08-10T12:35:02.200490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-10T10:43:49.230377Z","title":"Preprint, arXiv:2103.10385","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.16794","last_updated":"2025-01-28T08:52:33Z","snapshot_observed_at":"2026-08-10T10:37:28.057108Z","submitted_at":"2025-01-28T08:52:33Z","title":"Algorithm for Automatic Legislative Text Consolidation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T10:43:49.230377Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2501.16794"},"observation_digest":"sha256:934a359277053b4be0f665ec2a0a80c97228ef85e0f98e8e72bb9dea4e2ce998","observation_id":"0132b675-9373-4a42-b79f-ee839b5fd6de","resolution":{"observed_at":"2026-08-10T10:43:49.230377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-08T10:55:16.529693Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08092","last_updated":"2025-06-02T14:02:08Z","snapshot_observed_at":"2026-08-10T02:30:00.783514Z","submitted_at":"2025-02-12T03:33:06Z","title":"GCoT: Chain-of-Thought Prompt Learning for Graphs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T10:55:16.529693Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2502.08092"},"observation_digest":"sha256:ae4da67cd79baa88dc7f03a5f826b133f3d2e04e086a601687ff029f96d2cb8d","observation_id":"dd46e811-38e7-4e3c-94b8-0bd5234a3b44","resolution":{"observed_at":"2026-08-08T10:55:16.529693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2502.18864","last_updated":"2025-02-26T06:17:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-26T06:17:13Z","title":"Towards an AI co-scientist","version":1},"reference_index":158,"source":"arxiv_source","source_observed_at":"2026-05-11T13:02:43.571234Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2502.18864"},"observation_digest":"sha256:600eee3be9f287affe25756ac6fdb27ccf7efdcc46902714bebcd51edbe0063d","observation_id":"394283c3-de36-4340-982d-b8d5fecfc65a","resolution":{"observed_at":"2026-05-11T13:02:45.036698Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-07T15:21:54.160731Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15471","last_updated":"2025-05-21T12:46:42Z","snapshot_observed_at":"2026-08-09T00:27:47.622023Z","submitted_at":"2025-05-21T12:46:42Z","title":"CoLA: Collaborative Low-Rank Adaptation","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T15:21:54.160731Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2505.15471"},"observation_digest":"sha256:6545f2132a181e8033d2c3ac5eaf5cf19840bc9c6eb5d0d123a32817ca691556","observation_id":"df80b815-bd39-4edd-8217-e50882f428ed","resolution":{"observed_at":"2026-08-07T15:21:54.160731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-07T13:23:37.005934Z","title":"Gpt understands, too,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23822","last_updated":"2025-07-23T14:16:49Z","snapshot_observed_at":"2026-08-07T13:16:30.261603Z","submitted_at":"2025-05-28T04:07:17Z","title":"Speech as a Multimodal Digital Phenotype for Multi-Task LLM-based Mental Health Prediction","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:23:37.005934Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2505.23822"},"observation_digest":"sha256:d29035996e14521e8d4a3eeed96578585f0388b76b69a2c548a004067ece7534","observation_id":"7195ee69-06f0-40ae-b106-87e014d5e461","resolution":{"observed_at":"2026-08-07T13:23:37.005934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-07T12:37:47.221424Z","title":"GPT Understands, Too,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24224","last_updated":"2025-05-30T05:23:16Z","snapshot_observed_at":"2026-08-07T12:26:43.650226Z","submitted_at":"2025-05-30T05:23:16Z","title":"MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:47.221424Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2505.24224"},"observation_digest":"sha256:7454d5bbc4fa8e42a0c11a40286339814c904e41141125586b7364f5dcbb0796","observation_id":"b097ff4e-d7d2-4902-b52d-fa29e6c142cc","resolution":{"observed_at":"2026-08-07T12:37:47.221424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-07T10:17:23.562950Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05629","last_updated":"2025-06-05T23:13:22Z","snapshot_observed_at":"2026-08-07T10:11:26.556577Z","submitted_at":"2025-06-05T23:13:22Z","title":"Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T10:17:23.562950Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2506.05629"},"observation_digest":"sha256:c9b631bbb620d8684e131d3886c22e7d7b89bb5d6c07bf9d186238c674fcb4a6","observation_id":"59bd6dd2-3512-4fb5-9170-7e33a3bd086f","resolution":{"observed_at":"2026-08-07T10:17:23.562950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-06T22:44:44.258722Z","title":"Gpt understands, too.ArXiv preprint, abs/2103.10385, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20917","last_updated":"2025-06-26T00:49:35Z","snapshot_observed_at":"2026-08-07T05:17:23.851973Z","submitted_at":"2025-06-26T00:49:35Z","title":"Optimising Language Models for Downstream Tasks: A Post-Training Perspective","version":1},"reference_index":140,"source":"pdf_text","source_observed_at":"2026-08-06T22:44:44.258722Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2506.20917"},"observation_digest":"sha256:9545377cd39c69fdccea88b24b9f2e8374829663b04e723a30df71a159a16db9","observation_id":"1dc55529-a7b4-48d0-8678-a3fe1e5a9a97","resolution":{"observed_at":"2026-08-06T22:44:44.258722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-06T21:24:31.122601Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.00258","last_updated":"2025-06-30T20:52:15Z","snapshot_observed_at":"2026-08-10T10:37:46.435768Z","submitted_at":"2025-06-30T20:52:15Z","title":"Impact of Fine-Tuning Methods on Memorization in Large Language Models","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T21:24:31.122601Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2507.00258"},"observation_digest":"sha256:a14351c5d2588a58ba3e3b0d071e8243fe452ef2d262b66cab7c4f810ff9819a","observation_id":"15791386-02e7-4150-a7a5-9aff854c70b1","resolution":{"observed_at":"2026-08-06T21:24:31.122601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-06T20:57:40.940440Z","title":"Gpt understands, too","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.03003","last_updated":"2025-07-02T05:23:20Z","snapshot_observed_at":"2026-08-08T14:58:12.616619Z","submitted_at":"2025-07-02T05:23:20Z","title":"Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T20:57:40.940440Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2507.03003"},"observation_digest":"sha256:cc4a6421dd18a22cb6a4d82ff23a647a564331eda0625bbfe429af9a7c36b6c5","observation_id":"bc9ae2a2-42ec-4b22-92ff-fd4837ab230f","resolution":{"observed_at":"2026-08-06T20:57:40.940440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2507.03724","last_updated":"2025-12-03T03:19:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-04T17:21:46Z","title":"MemOS: A Memory OS for AI System","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-15T08:20:22.658329Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2507.03724"},"observation_digest":"sha256:fe610e268eb1488f65ef198a5d86bed7b0216c62739af74eeca3697c53eaf2f5","observation_id":"5db0fa5e-0b63-4470-8681-2683fa1e87b7","resolution":{"observed_at":"2026-05-15T08:20:22.920687Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-06T18:49:28.433587Z","title":"Available: https://arxiv.org/abs/2103.10385","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.07296","last_updated":"2025-07-09T21:43:06Z","snapshot_observed_at":"2026-08-09T14:58:57.469937Z","submitted_at":"2025-07-09T21:43:06Z","title":"Time Series Foundation Models for Multivariate Financial Time Series Forecasting","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:28.433587Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2507.07296"},"observation_digest":"sha256:c8f14677f20e6ad37d24b7418af5e06d926f18fdb3b13ad9556bfcc4132e5384","observation_id":"5fa119f3-bd7d-47df-b8bd-38490191b742","resolution":{"observed_at":"2026-08-06T18:49:28.433587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-06T17:11:49.012680Z","title":"Gpt understands, too, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.11467","last_updated":"2025-07-15T16:39:12Z","snapshot_observed_at":"2026-08-09T18:07:20.273240Z","submitted_at":"2025-07-15T16:39:12Z","title":"Modeling Code: Is Text All You Need?","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T17:11:49.012680Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2507.11467"},"observation_digest":"sha256:395edf65257150b1ebfbe6fdf040f759f5329d68980e84e71291add666f48b59","observation_id":"96365679-88f0-4b75-b214-5796262c7356","resolution":{"observed_at":"2026-08-06T17:11:49.012680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-06T18:01:28.027974Z","title":"Gpt understands, too","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.15864","last_updated":"2025-07-13T07:16:08Z","snapshot_observed_at":"2026-08-08T14:46:08.544466Z","submitted_at":"2025-07-13T07:16:08Z","title":"Adversarial Demonstration Learning for Low-resource NER Using Dual Similarity","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:01:28.027974Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2507.15864"},"observation_digest":"sha256:85e132355ab962b4e19d16a25aa496f19e15e3be82976340d7fe33990bcfb8cb","observation_id":"e02c1bdd-15f9-41cd-b6c8-5867938717e7","resolution":{"observed_at":"2026-08-06T18:01:28.027974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-05T15:27:29.299358Z","title":"GPT Understands, Too,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.19856","last_updated":"2025-08-27T13:16:31Z","snapshot_observed_at":"2026-08-09T19:44:31.906970Z","submitted_at":"2025-08-27T13:16:31Z","title":"TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T15:27:29.299358Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2508.19856"},"observation_digest":"sha256:9d72f76f18edd2123ee4feef0ce22daa80c5bcf1053ef924b48a96f9576c97e2","observation_id":"bdba9e19-1253-4ff5-b5f6-95e1e8b71720","resolution":{"observed_at":"2026-08-05T15:27:29.299358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-08-03T03:48:09.556542Z","title":"ISBN 9781713829546","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.06883","last_updated":"2026-06-03T15:54:18Z","snapshot_observed_at":"2026-08-08T06:35:16.823754Z","submitted_at":"2026-02-06T17:12:22Z","title":"Vision Transformer Finetuning Benefits from Non-Smooth Components","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T03:48:09.556542Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2602.06883"},"observation_digest":"sha256:5ce454f331b6cfac96a0d0c76eac8a0e8a7d3349b8b1a733b36de1ffbc5a2723","observation_id":"f7b612f1-0977-4874-b6e2-3d079af1127f","resolution":{"observed_at":"2026-08-03T03:48:09.556542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2604.05732","last_updated":"2026-04-07T11:35:45Z","snapshot_observed_at":"2026-07-06T22:54:21.571606Z","submitted_at":"2026-04-07T11:35:45Z","title":"Graph Topology Information Enhanced Heterogeneous Graph Representation Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T19:27:45.961277Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2604.05732"},"observation_digest":"sha256:0f8f9241138d3af205fb83f1bcf13eb82095d9e3b21c4ce52d3c03ccae175135","observation_id":"c958bf84-36f6-4c3d-89c1-3eca06e5411b","resolution":{"observed_at":"2026-05-10T22:55:51.368900Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2605.04058","last_updated":"2026-04-10T08:00:28Z","snapshot_observed_at":"2026-07-06T23:16:54.673178Z","submitted_at":"2026-04-10T08:00:28Z","title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-10T17:19:59.247074Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2605.04058"},"observation_digest":"sha256:aa88e80615e4b924778cb968d83a11fa79b94335cbb5199bef393d7b9e87e394","observation_id":"9d33cd1b-6416-43dc-b2c4-0d6841d6a381","resolution":{"observed_at":"2026-05-11T07:01:10.815971Z","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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2605.31246","last_updated":"2026-05-29T12:46:15Z","snapshot_observed_at":"2026-07-06T23:40:27.543522Z","submitted_at":"2026-05-29T12:46:15Z","title":"BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-28T21:52:23.150188Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2605.31246"},"observation_digest":"sha256:7eee8a6bc5438af25d49ebec5b3a99a6a680a0b29a9b52f1e0619b14d7983b49","observation_id":"845761d5-237d-4441-a7df-118cf7345b6b","resolution":{"observed_at":"2026-07-01T19:56:11.280281Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2103.10385","last_updated":"2023-10-25T06:15:58Z","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too","version":2},"cited_work":{"arxiv_id":"2103.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10385","snapshot_observed_at":"2026-07-04T18:00:01.488346Z","title":"arXiv preprint arXiv:2103.10385 , year=","venue":null,"work_id":"016ac77d-966a-44e3-bbed-2dcfaac73b73","year":2021},"citing_paper":{"arxiv_id":"2606.24841","last_updated":"2026-06-23T17:21:03Z","snapshot_observed_at":"2026-08-09T07:56:18.360447Z","submitted_at":"2026-06-23T17:21:03Z","title":"Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-25T23:06:47.559340Z"},"links":{"cited_paper":"/paper/2103.10385","citing_paper":"/paper/2606.24841"},"observation_digest":"sha256:a7ef5b44269926c1fd67b72570d2927541a6827d675e0e1abef0c598e67b0a8c","observation_id":"b81959d3-9742-4fb4-8b8f-bc5fb2b280ee","resolution":{"observed_at":"2026-07-04T18:00:01.489800Z","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/2103.10385/citation-record","integrity":"/paper/2103.10385/integrity","json":"/paper/2103.10385/citation-record.json","paper":"/paper/2103.10385"},"outbound":[],"paper":{"arxiv_id":"2103.10385","last_updated":"2023-10-25T06:15:58Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T10:51:16.166605Z","submitted_at":"2021-03-18T17:13:50Z","title":"GPT Understands, Too"},"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":"2026-08-10T06:31:04.303077+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 0 of 0 outbound references and 35 inbound Pith citation observations for arXiv:2103.10385."}