{"as_of":"2026-08-09T12:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1b83d56baebd106b80103daf43eb0b69a4c169e9230bb1a67f15b3f85d782460","coverage":[{"denominator":180,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-23T01:03:26.037233Z","state":"measured"},{"denominator":103,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":103,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T22:58:28.347994Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-05-19T05:42:06.116850Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"cited_work":{"arxiv_id":"2503.08223","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.08223","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","venue":"cs.DC","work_id":"91cf844b-3fa0-4af6-a6ff-0f40288abf4d","year":2025},"citing_paper":{"arxiv_id":"2507.06542","last_updated":"2026-04-27T10:34:05Z","snapshot_observed_at":"2026-08-06T23:52:48.965163Z","submitted_at":"2025-07-09T04:56:56Z","title":"On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning","version":4},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-19T05:39:53.088948Z"},"links":{"cited_paper":"/paper/2503.08223","citing_paper":"/paper/2507.06542"},"observation_digest":"sha256:95e2120b5ef10c1198140fcb3da72565b55ac8dadf2f3613d5b0743d545af81a","observation_id":"8a4f4d3f-77a7-46aa-ba11-d03793a4a4d5","resolution":{"observed_at":"2026-05-19T05:42:06.118989Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.08223","snapshot_observed_at":"2026-08-05T22:58:28.347994Z","title":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2508.09194","last_updated":"2025-08-08T09:53:53Z","snapshot_observed_at":"2026-08-07T17:54:38.232851Z","submitted_at":"2025-08-08T09:53:53Z","title":"Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T22:58:28.347994Z"},"links":{"cited_paper":"/paper/2503.08223","citing_paper":"/paper/2508.09194"},"observation_digest":"sha256:a6ff521251fe898c137c54784085385da89d34eabfb44059815ee0b64fa7973d","observation_id":"a1af5989-bc41-4591-8e70-9b1c4dc583ed","resolution":{"observed_at":"2026-08-05T22:58:28.347994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"cited_work":{"arxiv_id":"2503.08223","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.08223","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","venue":"cs.DC","work_id":"91cf844b-3fa0-4af6-a6ff-0f40288abf4d","year":2025},"citing_paper":{"arxiv_id":"2601.14053","last_updated":"2026-04-16T15:26:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-01-20T15:06:19Z","title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","version":2},"reference_index":168,"source":"pdf_text","source_observed_at":"2026-05-16T12:47:28.248540Z"},"links":{"cited_paper":"/paper/2503.08223","citing_paper":"/paper/2601.14053"},"observation_digest":"sha256:cda8a7d8b980e779e0907ac283af9681d806ea29568b0db812cc2b1383bf6402","observation_id":"460fe8cb-bd17-451d-8e03-ed24a3e7e857","resolution":{"observed_at":"2026-05-16T12:47:53.693658Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.08223/citation-record","integrity":"/paper/2503.08223/integrity","json":"/paper/2503.08223/citation-record.json","paper":"/paper/2503.08223"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":"2001.08361","doi":"10.1145/3616855.3635845","metadata_source":"pith","pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling Laws for Neural Language Models","venue":"cs.LG","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","year":2020},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:e20c5471c345681c5e4c87365f1e631ad3a3fce8689677fbdd8036d75705f29b","observation_id":"b5fba773-4515-49ae-8fab-4bca1155f151","resolution":{"observed_at":"2026-05-23T01:05:16.460975Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.15556","last_updated":"2022-03-29T13:38:03Z","snapshot_observed_at":"2026-07-06T12:54:11.616335Z","submitted_at":"2022-03-29T13:38:03Z","title":"Training Compute-Optimal Large Language Models","version":1},"cited_work":{"arxiv_id":"2203.15556","doi":"10.1098/rsta.2024.0522","metadata_source":"pith","pith_arxiv_id":"2203.15556","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Training Compute-Optimal Large Language Models","venue":"cs.CL","work_id":"b2faf28d-86b7-429c-bc42-469458efc246","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2203.15556","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:0e5260e2153ae51ddeafe4da441f28a476c6994cfa2c0ac2519d07b91b478963","observation_id":"94999a6e-dad0-46d3-8871-95e63684b8b0","resolution":{"observed_at":"2026-05-23T01:05:16.456726Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":"2303.08774","doi":"10.1002/tea.20265","metadata_source":"pith","pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GPT-4 Technical Report","venue":"cs.CL","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:b093c57f17729718ed72ba74bc98dbd8dffa7c7fc52e3bb97703cc9f619226c8","observation_id":"422a34e9-4906-40a6-8bba-1df54979dc48","resolution":{"observed_at":"2026-05-23T01:05:16.465038Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Language models are few-shot learners","venue":null,"work_id":"0a857984-9fef-4b46-aedc-522ba38946fd","year":1901},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:8d843dfd30169901e63b6c9fffaeee3996a7dbde69e587256d89195cf395bcf3","observation_id":"889deac4-d20d-41b2-9a99-b5203d687f27","resolution":{"observed_at":"2026-05-23T01:05:17.263553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02311","last_updated":"2022-10-05T06:02:24Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-05T16:11:45Z","title":"PaLM: Scaling Language Modeling with Pathways","version":5},"cited_work":{"arxiv_id":"2204.02311","doi":"10.48550/arxiv.2204.02311","metadata_source":"pith","pith_arxiv_id":"2204.02311","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"PaLM: Scaling Language Modeling with Pathways","venue":"cs.CL","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2204.02311","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:86fa04aae47a2f789f38d907d1110f9f96df8ec9a88c3a9a4de069d4798b4eb0","observation_id":"c332d663-49ae-4d54-8c96-eac3068689e6","resolution":{"observed_at":"2026-05-23T01:05:16.452546Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-21T12:25:21.411055+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T12:25:21.411055+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10350","last_updated":"2021-04-23T14:26:29Z","snapshot_observed_at":"2026-07-06T11:02:18.405330Z","submitted_at":"2021-04-21T04:44:25Z","title":"Carbon Emissions and Large Neural Network Training","version":3},"cited_work":{"arxiv_id":"2104.10350","doi":"10.48550/arxiv.2104.10350","metadata_source":"pith","pith_arxiv_id":"2104.10350","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Carbon Emissions and Large Neural Network Training","venue":"cs.LG","work_id":"5cd5f484-8e24-440f-8bed-e8a801f4ac40","year":2021},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2104.10350","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d2119e1526b55c78fc3a3b60fa201511c7f4781fc015243da600f30cde9fc5f0","observation_id":"9e67cc35-395a-4347-ade3-f2c8d65de660","resolution":{"observed_at":"2026-05-23T01:05:16.500759Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:19.119642+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:19.119642+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":"02747c8a-0ffd-440b-a050-cd89702b880e","year":2009},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:88a037d67769c03929c8743dcffa2272ad362adb0d2fd8a711af2a0240a343be","observation_id":"74470511-edd3-417b-b487-5522f7280b44","resolution":{"observed_at":"2026-05-23T01:05:17.093664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":"2302.13971","doi":"10.48550/arxiv.2302.13971","metadata_source":"pith","pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"LLaMA: Open and Efficient Foundation Language Models","venue":"cs.CL","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d05d3eb659ee00e5d8c0082308d7c432c32d18872b11acf2600429797bfd6f5e","observation_id":"54483555-024f-4cdd-bc3c-0581056f79b6","resolution":{"observed_at":"2026-05-23T01:05:16.425244Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-08T16:08:17.350515+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-08T16:08:17.350515+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:10f14db3016182215b0fbbe2dcc2a3533166aa8b3b6114b71560e0c054f992ea","observation_id":"89a19af0-78c5-4e72-b99f-e10f9686cab3","resolution":{"observed_at":"2026-05-23T01:05:16.447706Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Introducing llama 3.1: Our most capable models to date","venue":null,"work_id":"f9738521-99ad-4140-bf6e-0264dd140b55","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:84967d002786107b8554472bea348c85649ea8c360c047163f993450d820c97d","observation_id":"fce5a582-6ca3-494d-9281-283869b8319f","resolution":{"observed_at":"2026-05-23T01:05:17.321978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":"2307.09288","doi":"10.24963/ijcai.2025/706","metadata_source":"pith","pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","venue":"cs.CL","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:4dc11d441e68bf69469b7615f3f27cf25f4ad210f5c99d9542480accf913decb","observation_id":"35450742-f973-4dd2-b2e3-c14e48b8a076","resolution":{"observed_at":"2026-05-23T01:05:16.496833Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","venue":null,"work_id":"0865b639-bf57-4b44-9c8e-9a34380430a9","year":2020},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:36e24eecc7bc476da5f27ac2dd4aadcd856d755ab28e11bc1746ffb6c738acde","observation_id":"7d1ecab9-7280-467c-9f31-f9d3ce0dde50","resolution":{"observed_at":"2026-05-23T01:05:17.324954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Introduction to federated learning","venue":null,"work_id":"7636775c-77bd-4a18-9df0-132d525c4f21","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:30a9016a7c4e42d2669635f3442ab236e1d7cd40c4550c12fc915fe44b82c215","observation_id":"7b1056e2-d47b-4bec-8605-bb65f50141cd","resolution":{"observed_at":"2026-05-23T01:05:17.313232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.06499","last_updated":"2022-03-24T19:29:45Z","snapshot_observed_at":"2026-08-05T18:30:13.997811Z","submitted_at":"2021-07-14T06:06:52Z","title":"Deduplicating Training Data Makes Language Models Better","version":2},"cited_work":{"arxiv_id":"2107.06499","doi":null,"metadata_source":"pith","pith_arxiv_id":"2107.06499","snapshot_observed_at":"2026-07-09T03:05:54.907820Z","title":"Deduplicating Training Data Makes Language Models Better","venue":"cs.CL","work_id":"7b9b24f2-6013-4e4a-be6b-ce3aeef64aa8","year":2021},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2107.06499","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:50abc51a26ba5389f75ba7be4334d08136f0573496e07645d375fee33a587e66","observation_id":"8deab416-dafc-4838-9351-f49889595cd6","resolution":{"observed_at":"2026-05-23T01:05:16.219164Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09911","last_updated":"2024-03-12T12:42:28Z","snapshot_observed_at":"2026-08-05T08:40:24.349401Z","submitted_at":"2022-11-17T21:58:17Z","title":"Short-range order and compositional phase stability in refractory high-entropy alloys via first principles theory and atomistic modelling: NbMoTa, NbMoTaW and VNbMoTaW","version":3},"cited_work":{"arxiv_id":"2211.09911","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.09911","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Data governance in the age of large language models","venue":null,"work_id":"d133a4a9-5e6f-4a00-a936-92d96a7ddfc7","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2211.09911","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d8b1b0a256347f7a99fa7487cb7f3188a7ee5e36f601db1b8bb66076a8a85f6d","observation_id":"ff74ee56-9be4-431b-a30c-423054776439","resolution":{"observed_at":"2026-05-23T01:05:16.395309Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Position: Will we run out of data? limits of llm scaling based on human-generated data","venue":null,"work_id":"5a71486b-8c1e-4fdd-b4e4-e4d25591c8a7","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:daecb853f7643072e2805c5f56d78cd8c2b1c03513f1f32b5989ac990bed474d","observation_id":"1a1a64c1-3270-46dd-906a-b98130b33fd4","resolution":{"observed_at":"2026-05-23T01:05:17.316396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15226","last_updated":"2024-10-22T18:54:23Z","snapshot_observed_at":"2026-07-06T19:36:32.581033Z","submitted_at":"2024-10-19T22:14:07Z","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","version":2},"cited_work":{"arxiv_id":"2410.15226","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.15226","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On the diversity of synthetic data and its impact on training large language models","venue":null,"work_id":"ddea9b76-0744-46d6-b090-e64b0a9f32d6","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2410.15226","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:1fed421a5e79f570985bb99020c46401372439459cab54b7834ff5ece44a9046","observation_id":"de6d5b97-cada-44eb-b0e1-02327be1b867","resolution":{"observed_at":"2026-05-23T01:05:16.443483Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Ai produces gibberish when trained on too much ai-generated data","venue":null,"work_id":"9029c656-2239-447d-b3d2-a2ed38a63811","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:25629062bb1dfc548c7287c98923a210eadb6a280e4b9b690d17ddce716307ae","observation_id":"48330d8b-63b3-432b-900c-6e4e56a51f87","resolution":{"observed_at":"2026-05-23T01:05:17.292259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Bias of ai-generated content: an examination of news produced by large language models","venue":null,"work_id":"53d838b2-1039-4136-89be-b4d0db3d3e87","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:771540d8ad3a759693fddce4e1aecb2bfd58c4161ae77adeed2a4e3e9ff5cf79","observation_id":"e43a6c45-28b9-477b-89b5-5c9742ebb637","resolution":{"observed_at":"2026-05-23T01:05:17.310654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"General data protection regulation","venue":null,"work_id":"2b808832-e201-49a0-b599-26111527e3e3","year":2018},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:45008f28da42a4e1e0cfb045e99018d687a2dcba99bd4fe5e48e360773db48c1","observation_id":"700df413-c57d-4b6f-87c5-3f7cf5dc0db1","resolution":{"observed_at":"2026-05-23T01:05:17.283589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Are ai scaling laws hitting a wall? https://www.linkedin.com/ pulse/ai-scaling-laws-hitting-wall-dean-hardy-white-xchfe/","venue":null,"work_id":"9f67878d-1f8a-40c0-8f0b-97ee71950787","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:17e40742db47d5171c0fc5f25f3566a25bf2a24ed96829f691e273f2954f9d96","observation_id":"29b91d36-60d7-42c7-ba43-413e7feed8d0","resolution":{"observed_at":"2026-05-23T01:05:17.286516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Introducing grok-3","venue":null,"work_id":"daee3d3b-6980-47a5-912f-1ee815658992","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:7cbb0829e73224b0f753b8b74e000a54917512b81199f39220251bd191d28eba","observation_id":"6c3fe473-7f22-4334-b396-fd617c4515a5","resolution":{"observed_at":"2026-05-23T01:05:17.289139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Deep learning’s diminishing returns","venue":null,"work_id":"b25d12f1-675f-4451-aade-87c68d37fd9f","year":2021},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:6deda63a2460f6f81a8c1f608d385b402781d977e73aad60780c9121e0280b07","observation_id":"cd716e03-3edd-47ad-92be-6c87851e3d29","resolution":{"observed_at":"2026-05-23T01:05:17.274530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.08900","last_updated":"2020-04-19T16:28:35Z","snapshot_observed_at":"2026-08-08T11:44:54.578934Z","submitted_at":"2020-04-19T16:28:35Z","title":"The Cost of Training NLP Models: A Concise Overview","version":1},"cited_work":{"arxiv_id":"2004.08900","doi":"10.48550/arxiv.2004.08900","metadata_source":"arxiv_reference","pith_arxiv_id":"2004.08900","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Sharir, B","venue":"arXiv (Cornell University)","work_id":"49a44ad2-3337-48ea-ac20-5ee1f30ac458","year":2020},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2004.08900","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:212f6a83c47d58e481abcaabe395fa0ec6bb9c2b37b8146c942d24ec0ac9c358","observation_id":"32becdb3-cf51-4728-8ae6-718acd5704bc","resolution":{"observed_at":"2026-05-23T01:05:16.516916Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Green ai","venue":null,"work_id":"53450095-5a14-4bb0-8a6d-bba05d11a53e","year":2020},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:8b7be2e983fd98317cef6ad8319ce0734b3d65b22cb65a4999b4200471fb8823","observation_id":"823ad7c0-507b-4d2e-9055-37578fb0aa59","resolution":{"observed_at":"2026-05-23T01:05:17.277207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Artificial intelligence and competition policy","venue":null,"work_id":"542f82db-ecf9-4685-a8ff-9c11adb26741","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:f657a2da94ec2b4d5ded0a64beb52a9da331d54732a89cfed223f9c4589a9e29","observation_id":"1ff45ea2-8592-4430-bc23-2ed33ee31e34","resolution":{"observed_at":"2026-05-23T01:05:17.280237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05257","last_updated":"2022-11-13T21:53:48Z","snapshot_observed_at":"2026-08-06T00:14:29.431479Z","submitted_at":"2022-07-12T02:00:08Z","title":"Accelerating Certifiable Estimation with Preconditioned Eigensolvers","version":2},"cited_work":{"arxiv_id":"2207.05257","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2207.05257","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Frontier ai regulation: Managing emerging risks to public safety","venue":null,"work_id":"deb101d2-5d08-4ec9-907a-52501901cb29","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2207.05257","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:63a9d02a8d2d0524e9e9b66747dfaabae810fee229354c2b676a419d4b9a70f8","observation_id":"1085fe9b-9e4e-4996-bb0f-63486783077c","resolution":{"observed_at":"2026-05-23T01:05:16.525471Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Trends in training dataset sizes","venue":null,"work_id":"b06c7651-9a49-4aa2-ac4b-93195fca1da4","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:b7e1506a8044760d83038be6914eb9d365183510a3da4fc25b8fdf32f2f94e5c","observation_id":"cae01baf-5aea-411f-9904-4d12ab66498d","resolution":{"observed_at":"2026-05-23T01:05:17.307596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.04325","last_updated":"2024-06-04T22:09:46Z","snapshot_observed_at":"2026-08-07T22:09:30.469726Z","submitted_at":"2022-10-26T00:28:40Z","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","version":2},"cited_work":{"arxiv_id":"2211.04325","doi":"10.48550/arxiv.2211.04325","metadata_source":"arxiv_reference","pith_arxiv_id":"2211.04325","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Will we run out of data? limits of llm scaling based on human-generated data","venue":"arXiv (Cornell University)","work_id":"e9ffc77d-3e81-4a7f-9861-704f9accb1db","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2211.04325","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:14a8ba21639158beacd0b73f50b830c5c3e0c21a9f92e7b51508a197a9858c9e","observation_id":"a01342c8-52f5-49ce-9c6e-f7f9a1e75a02","resolution":{"observed_at":"2026-05-23T01:05:16.560310Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Compute trends across three eras of machine learning","venue":null,"work_id":"f6a83d9e-750b-4c8c-b075-131f5c927072","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:9733954d95d590986f4b7915de6579ad8d2ae310eb0ea10684945e2aceaac668","observation_id":"4757fd18-3724-429f-9b72-e56c10ca8dae","resolution":{"observed_at":"2026-05-23T01:05:17.295335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09237","last_updated":"2023-12-14T18:57:58Z","snapshot_observed_at":"2026-08-07T03:57:50.124362Z","submitted_at":"2023-12-14T18:57:58Z","title":"Pixel Aligned Language Models","version":1},"cited_work":{"arxiv_id":"2312.09237","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.09237","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tinygsm: Achieving 80% on gsm8k with small models","venue":null,"work_id":"57901864-9565-414e-8d85-e4cf0d3a6897","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2312.09237","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:8b4b5308ad403f67814344b13b0cf3599490f39a5ef06443349aec229f39cadd","observation_id":"5bbdd053-50ee-4d60-be4e-ecfcd4802608","resolution":{"observed_at":"2026-05-23T01:05:16.461164Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.17493","last_updated":"2024-04-14T05:20:10Z","snapshot_observed_at":"2026-08-05T16:03:40.517679Z","submitted_at":"2023-05-27T15:10:41Z","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","version":3},"cited_work":{"arxiv_id":"2305.17493","doi":"10.48550/arxiv.2305.17493","metadata_source":"pith","pith_arxiv_id":"2305.17493","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","venue":"cs.LG","work_id":"14bc9b3b-d8dd-4c25-a0be-6c178d31be0e","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2305.17493","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:ad0d5632ce3718900a412d3b1ff2dae31b1ee264f90f7fd7d5cea2300da1031d","observation_id":"cd3ce785-9a80-48c3-b774-60383cc2f983","resolution":{"observed_at":"2026-05-23T01:05:16.448204Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-20T14:22:09.312587+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T14:22:09.312587+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04840","last_updated":"2024-10-08T16:14:43Z","snapshot_observed_at":"2026-07-06T19:28:52.383175Z","submitted_at":"2024-10-07T08:54:23Z","title":"Strong Model Collapse","version":2},"cited_work":{"arxiv_id":"2410.04840","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.04840","snapshot_observed_at":"2026-07-01T00:15:09.312708Z","title":"Strong model collapse","venue":null,"work_id":"20e92589-bef1-46f4-aba8-9be1db5eef24","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2410.04840","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:6288cf2c8727b2b3db01f994ff8ecc3f2abb70ab6d55f7e57db89680ba536291","observation_id":"96c6db6c-dc2c-49ec-aaf2-2097805ff81e","resolution":{"observed_at":"2026-05-23T01:05:16.331326Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01850","last_updated":"2023-07-04T17:59:31Z","snapshot_observed_at":"2026-07-06T15:50:14.857449Z","submitted_at":"2023-07-04T17:59:31Z","title":"Self-Consuming Generative Models Go MAD","version":1},"cited_work":{"arxiv_id":"2307.01850","doi":"10.48550/arxiv.2307.01850","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.01850","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Self-consuming generative models go mad","venue":"arXiv (Cornell University)","work_id":"2f0f1aa2-5a4b-4d76-98be-034497b3b5ff","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2307.01850","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:145442f645e30fc1fe90d2a8705c02e7b56fed042d8dba8d2c0d3bf60e58d47e","observation_id":"14d144f6-84dc-42bd-bb9d-f609f2e577db","resolution":{"observed_at":"2026-05-23T01:05:16.243082Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T16:24:51.02723+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T16:24:51.02723+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09387","last_updated":"2023-06-15T15:13:45Z","snapshot_observed_at":"2026-07-06T15:43:07.989730Z","submitted_at":"2023-06-15T15:13:45Z","title":"Quintessences Universe in $f(R, L_m)$ gravity with special form of deceleration parameter","version":1},"cited_work":{"arxiv_id":"2306.09387","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.09387","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling laws of synthetic images for model training","venue":null,"work_id":"b98734b2-4ca8-48c5-8d63-be32b147ae27","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2306.09387","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:853445048b3af259e7bf887f3ac10bd4b9ea1837b7434576acf2394861e7d408","observation_id":"d39135e0-bb4f-4eb1-8cae-ba16845ab1db","resolution":{"observed_at":"2026-05-23T01:05:16.304469Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Trends in machine learning hardware","venue":null,"work_id":"795f717e-4114-4f6a-bf16-04cff580b258","year":null},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:6251ad03f1c829d5e5c402661d72b938fe4b4567500a156958dcdf95a7824a7a","observation_id":"175bddad-d779-4996-aa47-df4a7a781899","resolution":{"observed_at":"2026-05-23T01:05:17.240678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5a510498-0dd1-4695-b6cd-023b23a435f1","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:690adb50746513b84e5680e223ea08e65659739a4b81d0204b4cd02b463202f2","observation_id":"af69e408-0917-488f-8a82-aa533b821d68","resolution":{"observed_at":"2026-05-23T01:05:17.198714Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Attention is all you need","venue":null,"work_id":"ac9d72e5-eb60-417e-963d-25671207074e","year":2017},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:6bd303f16588c175f40ea97310e42858a1ad9d007d99ba89ab775cd6c8b0b7a9","observation_id":"740acc98-f9bd-459f-b098-2a1565ce0f17","resolution":{"observed_at":"2026-05-23T01:05:17.178358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"The end of moore’s law? innovation in computer systems continues","venue":null,"work_id":"6c11a66c-28fa-4237-a6dd-55ff1d9beac7","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:a98f12540e95c1d8857c7c1247ba66cc71749c748887ba1e564d5c6f257ab7a9","observation_id":"32a5f4b0-65f6-46a3-b5ff-9a25b57017b1","resolution":{"observed_at":"2026-05-23T01:05:17.223910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Apple, nvidia secure future with taiwan semi’s advanced chips as ai demand soars","venue":null,"work_id":"bfe252ea-d6e6-4f11-8f53-3a05d8a095bf","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:cb17d9783a4b833f2700132b02e9309290c1b0a5a1f71276797d24001392543f","observation_id":"ddd2f357-90be-46c4-b1e6-373f388e29d0","resolution":{"observed_at":"2026-05-23T01:05:17.334874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Ai’s hardware hunger: The global semiconductor supply chain under pressure","venue":null,"work_id":"8213f8bd-ceff-4b1f-99b1-afc34c3e0674","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:3373025eeec2f658977c7a941c1898a17d545e5fa2b02a3ad9c699c18d658abf","observation_id":"c2f9071b-670e-4b5f-a303-2b61efe5f09d","resolution":{"observed_at":"2026-05-23T01:05:17.121996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"V olume of data/information created, captured, copied, and consumed worldwide from 2010 to 2025","venue":null,"work_id":"68816bef-9e0f-4553-8d34-dd8b786c4ba4","year":2010},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:024fe1682784b47f87567ad21b3b5c1cb03ae2fd9a5c356219ceb6ee52a15570","observation_id":"fbd6b4a9-c453-4877-948c-cb55bac37680","resolution":{"observed_at":"2026-05-23T01:05:17.188847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Internet of things (iot) connected devices data size worldwide from 2019 to 2025","venue":null,"work_id":"69300c30-818e-4320-b920-b4f15fcdfb6c","year":2019},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d5c6eac8fd037314427054d28ac591ccba62dc0b2b8b81b2c024b2906b3de9fd","observation_id":"cff3a0d3-65b2-49f5-be69-5df570d9aac7","resolution":{"observed_at":"2026-05-23T01:05:17.069641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Edge computing market size & share analysis report, 2023-2030","venue":null,"work_id":"121ad289-00af-421f-821f-bbbaba8225ec","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:392bb5d411a40e0fda273707c53611b9d3563edee95186177552f49df90fb3d3","observation_id":"31396446-4051-4e60-8186-bd6788fe4b61","resolution":{"observed_at":"2026-05-23T01:05:17.075375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"How many smartphones are in the world?","venue":null,"work_id":"464fa19b-0d48-4e4c-ab2b-a74d0d9b1d9e","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:143aad24e0d278c1ab7387648ee8c183e4b3c231caa32c63280fda4eee4d907a","observation_id":"117cf150-55a1-41fa-ba10-986c512e95d9","resolution":{"observed_at":"2026-05-23T01:05:17.257282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Dataage white paper: The digitization of the world – from edge to core","venue":null,"work_id":"617b8fe1-1643-4cc4-bec5-e0c5e4c23e37","year":2019},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:eb3656166324104e15d21e6e10687c1a09fb413984f137a2f1602c7547d3593d","observation_id":"4ebaaf3c-c174-4b01-aceb-376799dca47b","resolution":{"observed_at":"2026-05-23T01:05:17.168860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Rethink data report 2020","venue":null,"work_id":"4681b32b-23f3-4e23-ba76-2911e6351eed","year":2020},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:475db76ab38926949598803a3e6e3bf1ed6fd7a13c7a84881f990bdb2a818ef1","observation_id":"4bf32d7e-4fb5-4d43-a6d8-031fdccf0b40","resolution":{"observed_at":"2026-05-23T01:05:17.232590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"A review on edge analytics: Issues, challenges, opportunities, promises, future directions, and applications","venue":null,"work_id":"9cdb1bad-bc05-45c6-9227-5c8b4eb39aae","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:996d08616bf051c8d01f89aea3e565b2f074b4034cf88ad377f587177e597170","observation_id":"674e92d8-8d4d-46b6-b270-0f9246b0a504","resolution":{"observed_at":"2026-05-23T01:05:17.175207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Edge Computing for IoT, Real-Time Data and Low Latency Processing","venue":null,"work_id":"db16a350-2c76-4e2a-ba0e-9007b8577a7f","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:f434b6e29c8f4efac63d9b2166038ae10ae7f5a2369a9d93ff5f35f9e9628beb","observation_id":"c9742289-426b-463b-b326-0d604da2d917","resolution":{"observed_at":"2026-05-23T01:05:17.195639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09990","last_updated":"2024-12-13T09:23:58Z","snapshot_observed_at":"2026-07-06T20:06:26.221438Z","submitted_at":"2024-12-13T09:23:58Z","title":"Small Language Model as Data Prospector for Large Language Model","version":1},"cited_work":{"arxiv_id":"2412.09990","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.09990","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Small language model as data prospector for large language model","venue":null,"work_id":"79383629-4611-45ec-a0a1-0e6dc9a8822c","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2412.09990","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:b622d3ed796dfce82696180f36bc708e4f62d596d67d0eaf091bf3eebddd1caf","observation_id":"ccdda23a-90e3-4cc8-ba52-d2b53fc1f73d","resolution":{"observed_at":"2026-05-23T01:05:16.529736Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"iphone 16 pro and 16 pro max - technical specifications","venue":null,"work_id":"7070cd5f-1511-49cd-b566-5d5b2180f0f5","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:3060db9239270ce7281e47a792d4a14942e1b535c8012384abbc41f9f86acc23","observation_id":"7e1edec9-9ebe-4085-9a7b-eee2bc226a28","resolution":{"observed_at":"2026-05-23T01:05:17.247608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Nvidia jetson agx orin tflops specifications","venue":null,"work_id":"09c5e49e-e781-4f7f-886f-b84f7afa8eb6","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:0a7010977948c999797f86d9f2dd9e2e5dc219951cb330658e1322b6ff0b7e9f","observation_id":"4424cd73-ff75-4f72-8221-7c03ea25715a","resolution":{"observed_at":"2026-05-23T01:05:17.254275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"NanoReview.net - Gadget Specifications and Comparisons","venue":null,"work_id":"97fbc143-67d0-44c3-a2a7-2a77e713fde5","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:ef918b78ba24d20878ae6cfd75dbdb23389245141036ff97308a5097f8f6ef4e","observation_id":"e2385bf5-d4d2-47ff-9468-94467cf36f75","resolution":{"observed_at":"2026-05-23T01:05:17.234004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Canalys Newsroom - Market Analysis and Research","venue":null,"work_id":"ccc4257c-d32c-4528-bd93-322f4f991fe1","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:8675f77b1c63ff201d3fcb74ac195833f3b15000894f4fc0247c54af31cf075e","observation_id":"9f4d2774-68d9-41b6-a9b5-613aaf58c3b7","resolution":{"observed_at":"2026-05-23T01:05:17.210714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.15790","last_updated":"2025-02-26T06:34:55Z","snapshot_observed_at":"2026-08-04T07:43:40.230682Z","submitted_at":"2024-09-24T06:36:56Z","title":"Small Language Models: Survey, Measurements, and Insights","version":3},"cited_work":{"arxiv_id":"2409.15790","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.15790","snapshot_observed_at":"2026-07-04T18:40:02.350725Z","title":"Small language models: Survey, measurements, and insights","venue":null,"work_id":"d47b62d8-fbc2-4285-8e86-9845f68619e3","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2409.15790","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:bc2ed18f1721c57d18dfd2e6d6b168c29a894481156d2b394fd06d46c65d80ca","observation_id":"56aa619b-4f94-4e3d-8582-05cd8a2843bb","resolution":{"observed_at":"2026-05-23T01:05:16.508630Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.03350","last_updated":"2024-12-28T09:18:36Z","snapshot_observed_at":"2026-08-04T03:34:32.259687Z","submitted_at":"2024-11-04T04:43:01Z","title":"A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness","version":2},"cited_work":{"arxiv_id":"2411.03350","doi":"10.48550/arxiv.2411.03350","metadata_source":"arxiv_reference","pith_arxiv_id":"2411.03350","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A comprehensive survey of small language mod- els in the era of large language models: Techniques, enhancements, applications, collaboration with llms, and trustworthiness","venue":"arXiv (Cornell University)","work_id":"a803a323-a63f-4f02-a480-340b3ea3fe73","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2411.03350","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:18850a6579a81e5b0a522871eda3df645a1935de49c4362bc31cecc723117ea0","observation_id":"a3008e07-0a3c-4090-bb95-9321f52ad1f8","resolution":{"observed_at":"2026-05-23T01:05:16.135665Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20011","last_updated":"2024-10-25T23:52:28Z","snapshot_observed_at":"2026-08-01T23:27:59.038399Z","submitted_at":"2024-10-25T23:52:28Z","title":"A Survey of Small Language Models","version":1},"cited_work":{"arxiv_id":"2410.20011","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.20011","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A survey of small language models","venue":null,"work_id":"719e1bb0-601f-48a8-968c-8a9d85de7d36","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2410.20011","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:caa0b90a93509f69407c1a95a42d450550af2f0a5e51e4b6a13d2a7ccd091d45","observation_id":"7c425754-3f15-41ed-8bc9-5ae62daaf1ac","resolution":{"observed_at":"2026-05-23T01:05:16.488678Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.10351","last_updated":"2020-10-16T02:12:46Z","snapshot_observed_at":"2026-08-07T22:21:53.513424Z","submitted_at":"2019-09-23T13:05:35Z","title":"TinyBERT: Distilling BERT for Natural Language Understanding","version":5},"cited_work":{"arxiv_id":"1909.10351","doi":"10.48550/arxiv.1909.10351","metadata_source":"arxiv_reference","pith_arxiv_id":"1909.10351","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Tinybert: Distilling bert for natural language understanding","venue":"arXiv (Cornell University)","work_id":"40d9fbb8-3c66-44bf-955c-5b5560f1e2f8","year":1909},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/1909.10351","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:b13561816a0b17851a7f99970bcd6c36fb0e9ad91e9ab0e6a237e7ea6876dcad","observation_id":"bc7090e6-5def-4587-8ef1-73c17f19c09e","resolution":{"observed_at":"2026-05-23T01:05:16.228134Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11942","last_updated":"2020-02-09T03:00:18Z","snapshot_observed_at":"2026-07-06T08:24:44.631342Z","submitted_at":"2019-09-26T07:06:13Z","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","version":6},"cited_work":{"arxiv_id":"1909.11942","doi":"10.48550/arxiv.1909.11942","metadata_source":"pith","pith_arxiv_id":"1909.11942","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","venue":"cs.CL","work_id":"aedf7950-7c35-4e28-a32d-bec290f51669","year":2019},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/1909.11942","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:95e2ad0ca7563eafb8fd70bd8955b8ffa4f3a3ad03bcd613e56d37cbdd3bf38b","observation_id":"a7afe8d8-bded-4296-af6c-f402c080a3ff","resolution":{"observed_at":"2026-05-23T01:05:16.551221Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":"2312.00752","doi":"10.48550/arxiv.2312.00752","metadata_source":"pith","pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","venue":"cs.LG","work_id":"4ee75248-1199-492c-a52f-6661e0f4adff","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:5a9c25dd17274a87a3171fb7b54b999e2d44729315983102aff62a12c567db3a","observation_id":"f50da84b-53ac-42d2-a2f5-4d9a43121564","resolution":{"observed_at":"2026-05-23T01:05:16.538409Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-30T19:25:31.081761+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-30T19:25:31.081761+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15242","last_updated":"2024-11-22T02:55:20Z","snapshot_observed_at":"2026-08-02T17:22:58.179617Z","submitted_at":"2024-11-22T02:55:20Z","title":"The Zamba2 Suite: Technical Report","version":1},"cited_work":{"arxiv_id":"2411.15242","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.15242","snapshot_observed_at":"2026-07-04T18:40:03.205634Z","title":"The zamba2 suite: Technical report","venue":null,"work_id":"306995de-58e3-4848-a8c6-12087f56bf36","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2411.15242","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d04c976b87217d81d89c5f5e66774e66ba333658ec6c87f5d110498dc5ab16f2","observation_id":"511592ce-da80-49e7-a645-db5cee068e8c","resolution":{"observed_at":"2026-05-23T01:05:16.204147Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.13676","last_updated":"2024-11-20T19:51:25Z","snapshot_observed_at":"2026-08-02T12:55:25.835610Z","submitted_at":"2024-11-20T19:51:25Z","title":"Hymba: A Hybrid-head Architecture for Small Language Models","version":1},"cited_work":{"arxiv_id":"2411.13676","doi":"10.48550/arxiv.2411.13676","metadata_source":"pith","pith_arxiv_id":"2411.13676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Hymba: A hybrid-head architecture for small language models","venue":"cs.CL","work_id":"283d6d50-8219-44e7-94e7-eb6b8673dec7","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2411.13676","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:8a0f323e1a2473f072dbddfac1c10ce791fe15f39175f1fcbe7a4509d18eee24","observation_id":"fea57a3b-6a94-4969-a6af-02e7ca4a10e0","resolution":{"observed_at":"2026-05-23T01:05:16.456536Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-07-10T18:19:58.783393+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-10T18:19:58.783393+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04517","last_updated":"2024-12-06T15:42:07Z","snapshot_observed_at":"2026-08-07T15:21:45.322877Z","submitted_at":"2024-05-07T17:50:21Z","title":"xLSTM: Extended Long Short-Term Memory","version":2},"cited_work":{"arxiv_id":"2405.04517","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.04517","snapshot_observed_at":"2026-07-10T01:36:43.972832Z","title":"xlstm: Extended long short-term memory","venue":"cs.LG","work_id":"cd8ee2fb-957f-4f9d-bdf9-e168fba4c2b8","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2405.04517","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:971377532be78bc6c5cd4ca44df8ff7655e24c4c74c6a22691abb790d4e14adf","observation_id":"164b05c7-3d3e-4213-9b50-620852b97f5c","resolution":{"observed_at":"2026-05-23T01:05:16.418223Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"SlimPajama: A 627B token cleaned and deduplicated version of RedPajama","venue":null,"work_id":"3e76b531-0d70-437b-aa19-4e8e1b988abb","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d1a2aa7788c44bb981c2ee81166c6ee285294ea2767f47ea58324b66a7dc1be1","observation_id":"d5727db1-3e34-4449-9a74-80799caeed74","resolution":{"observed_at":"2026-05-23T01:05:17.061828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13048","last_updated":"2023-12-11T03:58:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-22T13:57:41Z","title":"RWKV: Reinventing RNNs for the Transformer Era","version":2},"cited_work":{"arxiv_id":"2305.13048","doi":"10.48550/arxiv.2305.13048","metadata_source":"pith","pith_arxiv_id":"2305.13048","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"RWKV: Reinventing RNNs for the Transformer Era","venue":"cs.CL","work_id":"524dc80d-f4ef-4f89-bf1a-9a8c1e4b6a81","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2305.13048","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:b29f3ba5a2c064dd019e7730857c88286072ae85cb527aa305f501bf6bd363af","observation_id":"4152cc87-d6b7-437b-b092-7fd1eb9cce9f","resolution":{"observed_at":"2026-05-23T01:05:16.543067Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Paloma: A benchmark for evaluating language model fit","venue":null,"work_id":"0a9f97ba-ba4d-42bc-a757-f8f886b87197","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:05c1ce9ab9d170807567691916f7888848e74cc646630c353b6abf19c9b97d52","observation_id":"b863800d-b895-4d19-aa95-fd42e1b867b3","resolution":{"observed_at":"2026-05-23T01:05:17.072261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":"1810.04805","doi":"10.1111/jofi.12885","metadata_source":"pith","pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","venue":"cs.CL","work_id":"ed240a10-5b19-406c-baa5-30803f465785","year":2018},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:028c52ce8bd7f7dbda5691041666e5a2b74233264cfe911eedb96290538341e1","observation_id":"42cec4f7-def9-4c99-bcb5-3749eece08c3","resolution":{"observed_at":"2026-05-23T01:05:16.326854Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":"1910.01108","doi":"10.48550/arxiv.1910.01108","metadata_source":"pith","pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-07-11T02:57:46.620845Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","venue":"cs.CL","work_id":"756f9764-ecd6-4672-8043-b37c698c7ad2","year":2019},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:0b985b58ddc65db9d03d51ec5dc8c721dfb0378c0a675c081df80281ab3cc836","observation_id":"64d70a58-5540-4113-888c-f645288487f2","resolution":{"observed_at":"2026-05-23T01:05:16.512513Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","venue":null,"work_id":"551e69fc-b169-43a0-825f-aa05a1654eea","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:5d31da81c758dbd4f85938fbddae2506cdaab3c38e956446847c6b51ed3a1283","observation_id":"8ff78982-9271-40c2-9c89-a619c2b5bc01","resolution":{"observed_at":"2026-05-23T01:05:17.115400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12726","last_updated":"2023-01-30T08:51:19Z","snapshot_observed_at":"2026-07-06T14:45:55.345502Z","submitted_at":"2023-01-30T08:51:19Z","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","version":1},"cited_work":{"arxiv_id":"2301.12726","doi":"10.48550/arxiv.2301.12726","metadata_source":"arxiv_reference","pith_arxiv_id":"2301.12726","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Specializing smaller language models towards multi-step reasoning","venue":"arXiv (Cornell University)","work_id":"349d1339-23c4-4611-8834-3221afbdcb91","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2301.12726","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:04099f8ee6d410920ba2cbd63aa1ffbdb5cab28efffc364d9b5e3bd0e60fcc34","observation_id":"c85c56d4-a652-44f8-b8b2-077205e1c253","resolution":{"observed_at":"2026-05-23T01:05:16.391216Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.02301","last_updated":"2023-07-05T16:59:31Z","snapshot_observed_at":"2026-07-06T15:22:55.122322Z","submitted_at":"2023-05-03T17:50:56Z","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","version":2},"cited_work":{"arxiv_id":"2305.02301","doi":"10.48550/arxiv.2305.02301","metadata_source":"pith","pith_arxiv_id":"2305.02301","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","venue":"cs.CL","work_id":"5aa5f825-0529-4a20-a69d-9ecab4c8290c","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2305.02301","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:c963bec415db6b16cafbaff9ce0ef13a32b493ab34571d056af27391ad4f7530","observation_id":"723feb34-f13a-46d0-b677-c476282b2e99","resolution":{"observed_at":"2026-05-23T01:05:16.167661Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-20T14:22:04.795988+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T14:22:04.795988+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Exo: Run your own ai cluster at home with everyday devices","venue":null,"work_id":"17a279eb-d8bb-4f71-b915-e253ad1bf636","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:bbe4da0842f83aa16017192fc711f06dba0ed4fd557b46049ade4d061f735426","observation_id":"58d9afbd-154c-4c4a-9236-afea97ba7a17","resolution":{"observed_at":"2026-05-23T01:05:17.118361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Rovinski, Trevor Mudge, Jason Mars, and Lingjia Tang","venue":null,"work_id":"1abb8f6a-48c6-4582-8808-475268c78d54","year":2017},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d4084de80241a7b9d638e00963ae00b46a4718831c8b1a3205f2ee8de2636939","observation_id":"30c4ca6f-ba83-40ff-a201-b2af170c4911","resolution":{"observed_at":"2026-05-23T01:05:17.148433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09410","last_updated":"2025-01-16T09:36:32Z","snapshot_observed_at":"2026-07-06T20:21:50.886212Z","submitted_at":"2025-01-16T09:36:32Z","title":"MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models","version":1},"cited_work":{"arxiv_id":"2501.09410","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.09410","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Yang, Jian Wu, and Meng Zhang","venue":null,"work_id":"9f1bd2a7-ad91-462e-87e4-92501061a29f","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2501.09410","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d9fc7275e508d661ea75a346dcdda994654e022f12453d66e7f86ce561490594","observation_id":"b1aebb35-e76a-415e-8470-1548c2eb8a77","resolution":{"observed_at":"2026-05-23T01:05:16.479630Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Edge intelligence: On-demand deep learning model co- inference with device-edge synergy","venue":null,"work_id":"048cb8c2-f3b1-422c-9810-7318664051cc","year":2018},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:153269ee1ae52a5437bd60e6a809c9ea2186c05e03a0c1fee431dbd41b33561c","observation_id":"9842a0ef-b64f-411c-b811-792a7b37caf5","resolution":{"observed_at":"2026-05-23T01:05:17.133341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17245","last_updated":"2024-05-27T15:01:04Z","snapshot_observed_at":"2026-08-04T21:01:51.439514Z","submitted_at":"2024-05-27T15:01:04Z","title":"Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference","version":1},"cited_work":{"arxiv_id":"2405.17245","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17245","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Galaxy: A resource-efficient collaborative edge ai system for in-situ transformer inference","venue":null,"work_id":"483ffcb8-102f-4976-b490-0c4c916f9a4c","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2405.17245","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:331a20683b3b0f567bc141f57345ca0e22bb8d239278378a76468bd5ea7ca921","observation_id":"3b8c494d-9f11-4bc9-be15-6a21ced81128","resolution":{"observed_at":"2026-05-23T01:05:16.386504Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"On- device training under 256kb memory","venue":null,"work_id":"fa878c5a-e017-4df9-be8d-8a39f8880017","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:920259e051b42c42d7418f9648d81c3b7b981c884e4d3ee1becc1aeaa6256a44","observation_id":"c72c8aa9-2afc-4379-8e17-f1396604e6c6","resolution":{"observed_at":"2026-05-23T01:05:17.179508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Tinytl: Reduce memory, not parameters for efficient on-device learning","venue":null,"work_id":"4cf1dbd2-39c1-46cc-9231-256eef8adaa4","year":2020},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:1a79ba1d13c7775b0b1be06571e223f9ef72dacc97d802091c622e5b8b8df9c9","observation_id":"f3261c13-734b-405d-8e1a-88539111add5","resolution":{"observed_at":"2026-05-23T01:05:17.345860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Zerofl: Efficient on-device training for federated learning with local sparsity","venue":null,"work_id":"56b679ef-1ba8-4cdd-b79d-854024329b0b","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:ccf38e51695c6635eaa54d09ed28dd153dcd7a56d1e1718ad8ea1209b60a07cb","observation_id":"1af0f515-e4e2-4a5c-9959-069d37dabdb3","resolution":{"observed_at":"2026-05-23T01:05:17.353133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04287","last_updated":"2025-01-08T05:25:14Z","snapshot_observed_at":"2026-08-03T03:58:13.622039Z","submitted_at":"2025-01-08T05:25:14Z","title":"ElasticZO: A Memory-Efficient On-Device Learning with Combined Zeroth- and First-Order Optimization","version":1},"cited_work":{"arxiv_id":"2501.04287","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.04287","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Elasticzo: A memory-efficient on-device learning with combined zeroth- and first-order optimization","venue":null,"work_id":"4f0506ea-a9a2-4f72-8f27-ae44247d49d9","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2501.04287","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:8172e00d4c3786fc4a918681caff5159a2f24a656b06378d984b2a726347d4a1","observation_id":"11f74362-0a83-4a6d-bd22-c6e35afcf617","resolution":{"observed_at":"2026-05-23T01:05:16.547354Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"5dbadb2f-213d-4b5b-a2dc-b1704554a42b","year":2017},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:1df45f8100a611435220e2a1f0257298e62791ad3caae7c6b64696502bc717c4","observation_id":"12ecd87c-fcd7-4430-b268-776482ee5f35","resolution":{"observed_at":"2026-05-23T01:05:17.356545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Federated fine-tuning of large language models under heterogeneous language tasks and client resources","venue":null,"work_id":"4973c727-5b07-48b9-82d4-864fba46459c","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:72cbaa3123cbe1bdd740faa8f3fec25773f91b738bd7a97f4bae2c5376dc386f","observation_id":"8a8a6448-cd0c-477c-9fde-75ca35675280","resolution":{"observed_at":"2026-05-23T01:05:17.192346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01075","last_updated":"2025-05-02T07:33:00Z","snapshot_observed_at":"2026-08-07T15:57:09.124741Z","submitted_at":"2025-05-02T07:33:00Z","title":"Federated Adapter on Foundation Models: An Out-Of-Distribution Approach","version":1},"cited_work":{"arxiv_id":"2505.01075","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01075","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated adapter on foundation models: An out-of-distribution approach","venue":null,"work_id":"d257e2c0-786d-42db-8c24-d8b349f58d22","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2505.01075","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:235ac7f8e2b7c99fb34be8d8ab06d43adea287b35fe4d646fd264479c871ea03","observation_id":"e9afd0c6-6c89-4609-a7a4-8a2ca3f79bf5","resolution":{"observed_at":"2026-05-23T01:05:16.199014Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Fedpetuning: When federated learning meets the parameter-efficient tuning methods of pre- trained language models","venue":null,"work_id":"76f7b705-152f-458c-bf2d-264bb63dd09c","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:85800f9297b7fd3456430cc7b6736d82d8900bc0bd7230920c12ed31129e16df","observation_id":"16457c94-3ef9-455c-a1e4-e7c711026d63","resolution":{"observed_at":"2026-05-23T01:05:17.264537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Feddat: an approach for foundation model finetuning in multi-modal heterogeneous federated learning","venue":null,"work_id":"48fc6618-e99b-4077-8d0e-fd0272dcf473","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:40c842281ebaedb9c7694fb243f0a46c772ee78c1f334d1efa6dd4e7899d4b8b","observation_id":"d9f3d4d0-cc8b-4d5c-85d0-290a6747cf28","resolution":{"observed_at":"2026-05-23T01:05:17.106066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Fedmatch: Federated learning over heterogeneous question answering data","venue":null,"work_id":"87a07299-9261-4fdb-9908-c806dd8d5b2e","year":2021},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:0f48d47eda2685ff0427af738d44062f497bdae886e9809d7a7fbaf9cb2325ed","observation_id":"2b7b23ef-0de2-4533-8a6f-f89b8aa93781","resolution":{"observed_at":"2026-05-23T01:05:17.109711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Flower: A friendly federated ai framework","venue":null,"work_id":"e62c9fef-d416-45ce-9260-26fc1e61e88a","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:53b7a14347c53a9961978a106335caebd13d54e3d7f8b817d780935be7f555b6","observation_id":"4f1d53c0-e029-4df3-bf44-f2d21e74ccdb","resolution":{"observed_at":"2026-05-23T01:05:17.136828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10049","last_updated":"2023-10-16T04:17:13Z","snapshot_observed_at":"2026-08-08T09:36:17.477554Z","submitted_at":"2023-10-16T04:17:13Z","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.10049","doi":"10.48550/arxiv.2310.10049","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.10049","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Fate-llm: An industrial grade federated learning framework for large language models","venue":"arXiv (Cornell University)","work_id":"40a2337e-74e2-4a29-ad9a-cfd068762ade","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2310.10049","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:6f0315d0e4848d708b7b8f3d3c585b6239f71ccd32dc4665d84ed892389bbc3f","observation_id":"ab2504b7-a1cd-4d62-99db-65d8d5b8c40c","resolution":{"observed_at":"2026-05-23T01:05:16.404733Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Opendiloco: An open-source framework for globally distributed low- communication training","venue":null,"work_id":"d2e62936-d3c2-4768-8a2e-2f7c57826a5a","year":2025},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:576c3c1c5ad2e04c5046c6a414be61f5ea7e7713eccc774e907436fe2c47a223","observation_id":"0fccb502-a642-4e4e-8f2a-5260e1a2e2f8","resolution":{"observed_at":"2026-05-23T01:05:17.261058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2411.02908","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Photon: Federated llm pre-training","venue":null,"work_id":"a8aa3202-48cb-4bd2-8b50-544bcc73a31a","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:ed1380792d80030263abe3dd5f05a0b753d798f3c97c6d84db967dae52d0553c","observation_id":"494d354e-4fa5-429d-8937-ec1e071be4d0","resolution":{"observed_at":"2026-05-23T01:05:16.399994Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18421","last_updated":"2024-03-27T10:18:21Z","snapshot_observed_at":"2026-08-07T07:50:55.679613Z","submitted_at":"2024-03-27T10:18:21Z","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","version":1},"cited_work":{"arxiv_id":"2403.18421","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18421","snapshot_observed_at":"2026-07-03T18:08:45.686200Z","title":"Biomedlm: A 2.7 b parameter language model trained on biomedical text","venue":null,"work_id":"eacb5aff-ebda-464d-a6fb-b9414866fd51","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2403.18421","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:52aa6968850b383aacb38c1552067f02255e6e35786c3801fc31ab7d51b3d390","observation_id":"d489b56c-99f3-4f88-8aed-6721e1e8cdc9","resolution":{"observed_at":"2026-05-23T01:05:16.214995Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Advances and open problems in federated learning.Foundations and Trends® in Machine Learning, 14(1–2):1–210","venue":null,"work_id":"ead1a730-b0a7-4047-83bb-7ec4e6ddd737","year":2021},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:b0bc9aef11471aa346af6c4a509c83abab0f324f67915f407f2b6250ad1cca56","observation_id":"f9f48c14-223a-4ee6-b2ad-568554700e42","resolution":{"observed_at":"2026-05-23T01:05:17.257809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout","venue":null,"work_id":"7d5c151d-2870-46b7-9c55-a86e92a51da8","year":2021},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:bdc535bfacca0433fbd8a080cc1285e3210307568d15a984578e84d54cea3458","observation_id":"e8bc9eeb-8dd4-4dd9-91e1-f21d9f88acbc","resolution":{"observed_at":"2026-05-23T01:05:17.271389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Fedrolex: Model-heterogeneous feder- ated learning with rolling sub-model extraction","venue":null,"work_id":"b3f1acb7-1436-4183-bc9f-59c1c149e333","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:a6754637c756f93ff0f7a9810b09779314687dee19c3e2fd02fb3b62b1e627c9","observation_id":"b44c15e5-013e-4998-bd8b-c7acf6268233","resolution":{"observed_at":"2026-05-23T01:05:17.253799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"On the effects of data heterogeneity on the convergence rates of distributed linear system solvers","venue":null,"work_id":"a1fbab5b-b476-4917-9c08-653a3dbe815a","year":2023},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:a558617704d90335d39f076a126cc081bad63fcd657b30a2725839045f6c891e","observation_id":"a3333694-ae15-4e41-87e3-cd28b54a892c","resolution":{"observed_at":"2026-05-23T01:05:17.247893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Azizan-Ruhi, F","venue":null,"work_id":"7a66394e-6837-4e0b-a80b-ea6e4d6b760f","year":2019},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:97a16e4919a8aea9384419dbccb07239f69b4e4bc78a98f501cb503836f99072","observation_id":"0283c3bd-ac59-406b-9e1e-5a946a85d576","resolution":{"observed_at":"2026-05-23T01:05:17.250227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16989","last_updated":"2024-07-16T05:59:06Z","snapshot_observed_at":"2026-08-07T11:02:42.163743Z","submitted_at":"2024-06-24T05:24:41Z","title":"Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning","version":2},"cited_work":{"arxiv_id":"2406.16989","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16989","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Retrieval-augmented mixture of lora experts for uploadable machine learning","venue":null,"work_id":"42203aab-6905-442c-83c8-23d0899a5959","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2406.16989","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:36608f89459e14e3c3126aecd0aff6a4e2a068e4e724960489f8f6fc6db550df","observation_id":"8f9c6e57-0471-428e-a657-bfd27d9f487b","resolution":{"observed_at":"2026-05-23T01:05:16.426768Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":"2108.07258","doi":"10.1016/j.specom.2008.12.003","metadata_source":"pith","pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"On the Opportunities and Risks of Foundation Models","venue":"cs.LG","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","year":2021},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:a7736182d9277bee91070e34a4084704a6cc05a1a0841e23c008078a6cc098dc","observation_id":"61e5d846-ffda-48ae-ac83-f2c97fa2b5cb","resolution":{"observed_at":"2026-05-23T01:05:16.381004Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T09:22:59.787075+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T09:22:59.787075+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Democratising artificial intelligence in healthcare: community-driven approaches for ethical solutions","venue":null,"work_id":"14fefa3e-2d42-4c82-b361-7e8b533dc709","year":2024},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:ca2f32cf60e3e0d641becfcf86a4ffa05408e16f31ccc83c5208c252031d8d0b","observation_id":"28f6685c-24bc-4575-9f0e-933bb699e1c2","resolution":{"observed_at":"2026-05-23T01:05:17.240875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Edge-cloud polarization and collaboration: A comprehensive survey for ai","venue":null,"work_id":"cfa5aad0-87a0-4ad4-87f3-7f5d8818ea05","year":2022},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:b150064bf5a81eb13eb2bc03180c7c5690b5e2246a8833db6372bf5e059a7e0d","observation_id":"d5a53b54-665c-4baa-9794-592e8b3af6d4","resolution":{"observed_at":"2026-05-23T01:05:17.237799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","latest_version":3,"primary_category":"cs.DC","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":1,"unresolved":0,"verified_exact":42,"verified_fuzzy":56},"total_outbound_references":180},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 100 of 180 outbound references and 3 inbound Pith citation observations for arXiv:2503.08223."}