{"as_of":"2026-08-04T23:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:17843a0d66c2f0c33392b01665bf88b19d4d476b159c070c3cb155f5ec56bed5","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-12T03:29:00.463046Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.09365/citation-record","integrity":"/paper/2605.09365/integrity","json":"/paper/2605.09365/citation-record.json","paper":"/paper/2605.09365"},"outbound":[{"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":"Reducing hallucination in structured outputs via retrieval-augmented generation","venue":null,"work_id":"6e37bf74-220f-4cba-9cb1-c83c4071871a","year":2024},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:710f46242aecab9102c3a03c4d610b118444d2b96b8ab3b564e433c163d3ee0e","observation_id":"315db7cb-ff2d-47b6-a2ea-e491ba38b4c8","resolution":{"observed_at":"2026-05-12T19:36:48.153669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-08T15:05:03.918057Z","title":"Separations in the representational capabilities of transformers and recurrent architectures","venue":null,"work_id":"85fe6af2-e9df-4ca9-8776-0139a63a07c7","year":2024},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:14133389c3e572dcfec593b5d986c968b4215422e3d0496dc8654c8d119daa9d","observation_id":"a3070595-a474-4128-9c0e-e1a560e356ff","resolution":{"observed_at":"2026-05-12T19:36:48.182994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Enterprise ai adoption: Balancing innovation and roi in 2026","venue":null,"work_id":"9a67bb12-0669-4243-8030-56ae52ff4e61","year":2026},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:f50f5bb55a997b9505ca69c12c6b663f0a86fa3e518f882b95ec05223c7f0a42","observation_id":"30946eba-f215-415b-8583-76aa4eeeef0d","resolution":{"observed_at":"2026-05-12T19:36:48.233653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"ef399a6e-b7d0-4c06-8146-cfb9256b5940","year":2026},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:1340cd2c7b83d236fe0242fc297ba87527d92e0dbb4abe2e9eb27f74587f723e","observation_id":"502fd679-0870-4ad3-83de-6c897d68ef2b","resolution":{"observed_at":"2026-05-12T19:36:48.134856Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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 trends 2025: Adoption barriers and updated predictions","venue":null,"work_id":"cc9e7fe4-745c-4b54-a791-b91960abcef7","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:6ece5362eca6888e6a973d35081112d2c9ae830bd70f4f85e9f3fcae101efd25","observation_id":"77bfc7ab-8e49-439a-a194-eb2ace4568ab","resolution":{"observed_at":"2026-05-12T19:36:48.188576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"State of ai in the enterprise 2026","venue":null,"work_id":"c200536b-8e4d-4f16-8a6c-e21703bb47fb","year":2026},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:34cd7257cc3f0ad5a3231da6e16f6ae7fa76a60e3e08ec7b936e9237f31417c7","observation_id":"708797fc-a985-4780-8189-0c5fb8f8168b","resolution":{"observed_at":"2026-05-12T19:36:48.130408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Fixing it in post: A comparative study of llm post-training data quality and model performance","venue":null,"work_id":"8485179f-c60b-4ee2-978d-885c25990c8a","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:46cacc5bc147431329a09302527a36efdd8490502d9863b7f9d745e6bd70f9bc","observation_id":"524565ea-da3c-4e74-961b-6c9cb8621eb6","resolution":{"observed_at":"2026-05-12T19:36:48.077352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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 adoption outpaces governance: Responsible ai pulse survey","venue":null,"work_id":"fc29d85c-e08d-43c6-8758-adf5a2099c18","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:5e1163a525689ceb219915ca30958ff8089433ef25bf1532e0ab697c96b7aa80","observation_id":"fbf4c70d-6136-49dd-976f-6bba3932467c","resolution":{"observed_at":"2026-05-12T19:36:48.223812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Gartner predicts over 40% of agentic ai projects will be canceled by end of 2027","venue":null,"work_id":"db535aa5-e8e8-43fb-9b47-2e5cf30df0bf","year":2027},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:60ff97631f8f933655defc6305ca8c554797c5e3c8949cc238229bec5b2b4640","observation_id":"0f7a7144-a581-494a-b451-7dc8b2025758","resolution":{"observed_at":"2026-05-12T19:36:48.193922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Hána and B","venue":null,"work_id":"d97264c7-3778-445b-99e0-3c1bdc4c49e3","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:528738c52c0680275438cb784ef08a9d0103689d7098be47fd75380a28d0ffa2","observation_id":"fbb28a29-9828-48ec-bc58-59db6193c1d5","resolution":{"observed_at":"2026-05-12T19:36:48.202920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Overcoming the organizational barriers to ai adoption","venue":null,"work_id":"fe4f243d-7f37-4705-b82b-0af3eba81627","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:4d46be028b23ca8f3f68101a1de36274c6efff8e6077f4fa7f3e031a49381dd0","observation_id":"79620e82-9a8b-4670-a8e3-cf00badc0ce8","resolution":{"observed_at":"2026-05-12T19:36:48.229104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"State of enterprise ai adoption report 2025","venue":null,"work_id":"1928a205-bbe0-4158-9ee7-dee881992488","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:37cd85fbf371dfdca63debcb62ad208e3f273c73a32d16704c7aa5cb5398b7b8","observation_id":"3d7f0d29-08e1-4907-81b3-836ea9792362","resolution":{"observed_at":"2026-05-12T19:36:48.072039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"88d921e7-323f-4f9b-9e1c-681f42bd557a","year":null},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:0c33371e61a20f59519ff28b5d5bbfd6c6bcab1a68557ef5da5ee782c69edddf","observation_id":"e4b9fb3b-c4ca-465d-9cf9-ac537c3c4201","resolution":{"observed_at":"2026-05-12T19:36:48.112535Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Karakurt and A","venue":null,"work_id":"2f7c3671-794b-4e87-b505-0e3adb850910","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:a42142eb6fe588dab2ee1eeea0cfe9b19ad40a6993f787ed8cfa59bb9fad0bc3","observation_id":"f9053b29-c36a-468e-bfc2-0682225d5a06","resolution":{"observed_at":"2026-05-12T19:36:48.083988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Foundation models for tabular data within systemic contexts need grounding","venue":null,"work_id":"0acc2677-5ddd-4bff-8c5a-18ad32a84907","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:ca3d2a09960fd4dd1f652f1fc1728ec8435b326ccfb7368fd5c1d2b00201c33d","observation_id":"6d4477ba-18fd-411d-b463-d78b3f3c3453","resolution":{"observed_at":"2026-05-12T19:36:48.101057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Retrieval-augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":"241f802f-d0cd-43ec-991e-a2807e6802f2","year":2021},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:d8a5213adfebf22448574251eb30c38aee4e9119d26015bfe894021feb1d1ecb","observation_id":"d815b2af-12f0-48ce-80d8-055d15b86ee0","resolution":{"observed_at":"2026-05-12T19:36:48.091193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"End-to-end ontology learning with large language models.Advances in Neural Information Processing Systems, 37:87184–87225","venue":null,"work_id":"aa1c10df-0fe6-4319-8917-74dcb9aeee8d","year":2024},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:bc5eb4de34e26476de3204e29717eb93ee31fbbf2acef5a8a1676372b33930d5","observation_id":"b4898e5e-25f0-4bd3-9e94-dafb6f31e721","resolution":{"observed_at":"2026-05-12T19:36:48.148627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.02029","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T04:56:39.129673Z","title":"Canonical intermediate representation for llm-based optimization problem formulation and code generation","venue":null,"work_id":"6344f90f-e75d-4635-9f2a-085b0e7624e9","year":2026},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:5db06778316c065e10e61671d8bb78a5e2f7a67a6af49018ebeb3a5d97f26be5","observation_id":"82866899-e590-4ebe-81b0-bf04abf562d7","resolution":{"observed_at":"2026-05-12T07:21:23.719766Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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 state of ai: Global survey 2025","venue":null,"work_id":"7c8e96ab-eb77-4ae1-9231-da4d7c696e03","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:91ed35e96e1183f72331adddc1e7e47472091894eeca8bf438395ca39a4a541a","observation_id":"af51d9ce-3661-4b5b-b149-375ba82a29b7","resolution":{"observed_at":"2026-05-12T19:36:48.173535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2025: The state of ai in healthcare","venue":null,"work_id":"13c7944e-7e39-451c-ade4-fa3a60779fdd","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:4e01840a3d4f63a9bd6f82628e808e374fbe458c67876034d5f3af34ce4e7307","observation_id":"41f36176-30cb-4ae8-972a-497e88755a9c","resolution":{"observed_at":"2026-05-12T19:36:48.218208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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 state of enterprise ai","venue":null,"work_id":"201dbf50-97c5-473a-85b7-3932a1b314b6","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:6c01d27586c7b6ff480a281bd28ace50b65b687f4fdcf58bb06f9d93c8d503a5","observation_id":"4dc473a1-f1f4-4a1d-97f7-6be48570f750","resolution":{"observed_at":"2026-05-12T19:36:48.126276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"merging worlds","venue":null,"work_id":"2c10b5ab-d826-45ae-a9de-1f5c2cc37cab","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:5c32e1b8922967d319c67ef728ed7b679eb0f7daf464930f6f43a06ff6377507","observation_id":"2f0f2af6-7c12-45cd-b643-847eb58f5f56","resolution":{"observed_at":"2026-05-12T19:36:48.213640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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 GenAI Divide: State of AI in Business 2025","venue":null,"work_id":"c6d7b0b1-477e-421a-ac14-b62f23e0214c","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:42702c42c142f920aa9431bc0b3d0b13f7f31f57dc1aaeea354d3657db77b81f","observation_id":"e353ad5f-f67a-4224-80e1-5d4464104cbc","resolution":{"observed_at":"2026-05-12T19:36:48.059661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Romeo and J","venue":null,"work_id":"f0414156-d570-4429-a33e-bda85685a700","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:8ac80a730e075ed4e45db9d5acef01c965c426da7330f4cdf57484e30a4b9fe7","observation_id":"fca5bcd8-bba0-4ae8-a615-bad633a79785","resolution":{"observed_at":"2026-05-12T19:36:48.096589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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 adoption is soaring, but few companies are measuring its impact","venue":null,"work_id":"553f6ba8-8e73-49c1-8978-eae50bd0f216","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:802c009e6529d93b35fccf25d946e70c1c47877f06c319514af7320d3db7c4a4","observation_id":"6340b9f6-05ee-432d-9c32-ff098df187cb","resolution":{"observed_at":"2026-05-12T19:36:48.158672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"What formal lan- guages can transformers express? a survey.Transactions of the Association for Computational Linguistics","venue":null,"work_id":"53e312ae-c04b-4474-8e9c-1926dbc8deff","year":2024},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:dc27a88113b57246e1d096c8184fb9515553234a91f6eb9bd35a6fb03d0ce5af","observation_id":"97b7cebc-03fd-4502-9952-8ecd2a0fa4e5","resolution":{"observed_at":"2026-05-12T19:36:48.208623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Claude ai agent deletes firm database in seconds.The Guardian, April 2026","venue":null,"work_id":"3b6183be-8f37-412e-9889-ba0f4e9d8688","year":2026},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:3527ea19232050df6ad5ea3778c284ac4aec204373056d07fb5f8d202862b7be","observation_id":"8c8cf7d7-2ddf-4e08-ae5d-1414f249fe03","resolution":{"observed_at":"2026-05-12T19:36:48.117453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Enterprise ai adoption and roi: Three-year executive study","venue":null,"work_id":"e6fcb98b-ed37-4d8d-9cdc-009ac562f725","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:0105f8530baa7b2787e13ba95deac308c0a4c1c60bc9f4594b3d0e899933eae7","observation_id":"a7125268-32dc-434a-a82f-be2a0ff13c20","resolution":{"observed_at":"2026-05-12T19:36:48.163495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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 state of digital adoption 2025 (special ai edition)","venue":null,"work_id":"fbdc8a28-b40b-4b61-8611-1f54233c7db2","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:d60b87264cd0e141f8a3084770f4a21b40fff076fb458cca6685efc27a8da3a0","observation_id":"5b9724d1-edf7-4688-80e8-509c12b05ed4","resolution":{"observed_at":"2026-05-12T19:36:48.177958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Lumina: Detecting hallucinations in rag system with context–knowledge signals","venue":null,"work_id":"de6ef7a6-14cb-41a2-8242-3c8cd52a66bc","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:9e1667549e2f913603796f585802279f32c5c095166877fc2aa9a1400504b9f5","observation_id":"e76a89e3-638e-420a-993b-ffc474374a39","resolution":{"observed_at":"2026-05-12T19:36:48.052931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"textbook-quality","venue":null,"work_id":"988141df-1525-407b-9896-f5fbab3120e2","year":2025},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:e0558fa461134a5e8f7925c9786c1d86d11e56ac7cf253b61e4cdaa34c1ea420","observation_id":"9e223bf5-0c49-4245-a8ba-bd788c6abd53","resolution":{"observed_at":"2026-05-12T19:36:48.106902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"6SLM surveys document systematic OOD failures","venue":null,"work_id":"965e4ad3-b4bd-4ca7-bbfb-9c8ce4844653","year":null},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:db6af04fe53c4742a7f97f7392ac833387005827a4d837d109925081fd3fb5eb","observation_id":"764dce5c-09b4-4f6c-97a1-16df9571d0ae","resolution":{"observed_at":"2026-05-12T19:36:48.143410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2562eee1-f47b-447d-800a-7ad2d0cda68e","year":null},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:1029d39eaba18d850b4958cbf27225162037ed9e3807941df6e6a2993801bf9e","observation_id":"d947cd4d-56da-4a1c-a066-a397091b04db","resolution":{"observed_at":"2026-05-12T19:36:48.198338Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"10f13177-0627-44af-8052-2b58336df4d9","year":null},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:e57e166805a2b6980192b77988816be50bed8cfc3d1933fcf6039b969f80fdaa","observation_id":"7eb87691-2286-45ab-ad4d-d68263aa61ea","resolution":{"observed_at":"2026-05-12T19:36:48.139033Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"7f196054-bebe-4279-b675-cd756d19c9ec","year":null},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:1dc592081ccbf1fd3249c1378d6ece2b6295153767ea700e1ad5a9870a785b0d","observation_id":"cfdb63b7-b0c9-4704-9be2-c2d6f87adde2","resolution":{"observed_at":"2026-05-12T19:36:48.066812Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"a6c40fad-0501-437a-945d-3d3b6261cf29","year":null},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:19d11c05368f7aebdceeca1dea22c8ec77f779e7b12f64dc411a282d726956ac","observation_id":"e59cce97-8041-4878-acdf-f4ca881334b8","resolution":{"observed_at":"2026-05-12T19:36:48.121785Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"If the task requires high information complexity (e.g., many latent states or steps), this double compression tends to privilege superficial heuristics over algorithmic fidelity","venue":null,"work_id":"5ecd018b-106e-4f52-8721-f00f39e92ceb","year":null},"citing_paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:00.463046Z"},"links":{"citing_paper":"/paper/2605.09365"},"observation_digest":"sha256:56739f347d0903a5816efef1ca9ee937f6bc76e4da9532ada906183f666e63de","observation_id":"74906851-0442-4c0d-8ff2-b92c56832922","resolution":{"observed_at":"2026-05-12T19:36:48.169106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.09365","last_updated":"2026-05-10T06:29:34Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T06:29:34Z","title":"Position: Avoid Overstretching LLMs for every Enterprise Task"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":5,"verified_exact":1,"verified_fuzzy":30},"total_outbound_references":37},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2605.09365."}