{"as_of":"2026-08-08T01:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:99fbf313e4f27cab7b2913ecbde582603b7945ef46647909f1c0f8edc6dce866","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:50:50.204155Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T22:18:45.189576Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T14:05:46.733789Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"cited_work":{"arxiv_id":"2506.04172","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.04172","snapshot_observed_at":"2026-07-01T14:05:46.733789Z","title":null,"venue":null,"work_id":"dcd02387-b9b5-4358-b06c-68d55fdb81e6","year":2025},"citing_paper":{"arxiv_id":"2605.12376","last_updated":"2026-06-04T17:58:18Z","snapshot_observed_at":"2026-08-07T20:29:26.287618Z","submitted_at":"2026-05-12T16:42:38Z","title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-13T05:56:36.312877Z"},"links":{"cited_paper":"/paper/2506.04172","citing_paper":"/paper/2605.12376"},"observation_digest":"sha256:3245e2e148fe80e009198573b4d64d53502f044385b3f28d7f1609915385b6e8","observation_id":"adc26130-5916-4e95-8611-86ee7d5a1a6c","resolution":{"observed_at":"2026-05-13T05:57:22.517689Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"cited_work":{"arxiv_id":"2506.04172","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.04172","snapshot_observed_at":"2026-07-01T14:05:46.733789Z","title":null,"venue":null,"work_id":"dcd02387-b9b5-4358-b06c-68d55fdb81e6","year":2025},"citing_paper":{"arxiv_id":"2605.12376","last_updated":"2026-06-04T17:58:18Z","snapshot_observed_at":"2026-08-07T20:29:26.287618Z","submitted_at":"2026-05-12T16:42:38Z","title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-30T22:18:45.189576Z"},"links":{"cited_paper":"/paper/2506.04172","citing_paper":"/paper/2605.12376"},"observation_digest":"sha256:e76661708f5cb7eefd498b603809b9cdd9f5295bd9a441c201f45bb2b863783c","observation_id":"f33e58be-df65-42af-999e-ff20d7f3f35e","resolution":{"observed_at":"2026-07-01T14:05:46.735213Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.04172/citation-record","integrity":"/paper/2506.04172/integrity","json":"/paper/2506.04172/citation-record.json","paper":"/paper/2506.04172"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.032299Z","title":", \" * write output.state after.block = add.period write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.032299Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:93afa92a248cc3d7c09fc95bc28f717b377b86b84127d6fbacbca29b361fa403","observation_id":"ec0a6069-a38e-4454-a795-aae377807103","resolution":{"observed_at":"2026-08-07T10:50:50.032299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.047629Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.047629Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:08beabf0ab05bdd2adba62ceaddff30b99a96f361f25a106a5a19089874ef14e","observation_id":"70bb04c9-6eea-48cf-8d04-3593f84d9148","resolution":{"observed_at":"2026-08-07T10:50:50.047629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:51.040454Z","title":null,"venue":null,"work_id":"e70c89f3-4d7c-416c-980b-258fc4a9062b","year":2020},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.063823Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:f488cf14f69fff47e6712c4516b541693c9e880f0868a050376b4ff165fc28d9","observation_id":"4d3c0fca-f2b6-42fc-a739-0c4b66ab7241","resolution":{"observed_at":"2026-08-07T10:50:51.044304Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.06280","last_updated":"2023-04-22T10:03:23Z","snapshot_observed_at":"2026-08-04T17:31:19.505383Z","submitted_at":"2022-10-12T15:03:28Z","title":"Language Models are Realistic Tabular Data Generators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.06280","snapshot_observed_at":"2026-08-07T10:50:50.077250Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.077250Z"},"links":{"cited_paper":"/paper/2210.06280","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:59be04f4cb1bb6e8d7ce6a125d7a3360863add1d70811e011bf2401378bd0818","observation_id":"45d5f491-44c9-43cf-a3fa-5123bf39a4ca","resolution":{"observed_at":"2026-08-07T10:50:50.077250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:51.030146Z","title":"D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al","venue":null,"work_id":"260b25fd-70ab-402a-9891-c2e810eff78f","year":2020},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.092402Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:4acd6faca0fcddfe9029654bdb2dab7578a2bbe54439c34828edd117288604a7","observation_id":"ae07147a-c580-479b-8290-b20f3d232e5d","resolution":{"observed_at":"2026-08-07T10:50:51.034483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:51.019633Z","title":"V.; Bowyer, K","venue":null,"work_id":"a2a8586e-0f52-4caa-9074-56ec3bb0c99f","year":2002},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.096496Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:aa13d1bd719653d60021b87a1991be15705a5e6283bc09f8d5c8668c8177aa3f","observation_id":"3aa2da86-37f4-4309-a26f-01818562f8dc","resolution":{"observed_at":"2026-08-07T10:50:51.024544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:51.009349Z","title":null,"venue":null,"work_id":"559f03bd-a2ad-4700-9bcd-281eb95ba955","year":2023},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.100300Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:2e23de41defd66fbb2a6b274b1fd1fa16ed10f56634865a91f188742e45a3eb9","observation_id":"9bf39cd0-0b27-49cc-810e-b9d0192ae613","resolution":{"observed_at":"2026-08-07T10:50:51.013332Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.998147Z","title":null,"venue":null,"work_id":"d28d6958-6efc-4b2f-b628-8a1e75e7dead","year":2014},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.104090Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:71479beedb013699f7295fa133a44926cbb7960e06706134f33c232a411edd7e","observation_id":"9af770bd-b95f-4e9c-8262-fc4b0685bab7","resolution":{"observed_at":"2026-08-07T10:50:51.003185Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.988378Z","title":null,"venue":null,"work_id":"1a6a281e-2371-4b61-9e84-8bffb4e06aec","year":2025},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.109706Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:6cb92b5e970482fe4b2a8ee0ceae4f3919982c749021153d5c49bb1dac71d413","observation_id":"50ac4fec-efb6-4007-bb58-ff71a980fa52","resolution":{"observed_at":"2026-08-07T10:50:50.991877Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.977303Z","title":null,"venue":null,"work_id":"fdbe2ae8-205e-41f3-bf01-6b5e8c77b1f0","year":2023},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.113075Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:df3fa45558215adaa6f5bba72378cf68d1b82086718d1afceae7ed19d3043c8a","observation_id":"129ef3b9-68a8-4fee-b771-bc6ddc92269d","resolution":{"observed_at":"2026-08-07T10:50:50.982718Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.965058Z","title":null,"venue":null,"work_id":"cbd34f68-c917-4463-a675-0af78dab85b9","year":2023},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.117430Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:0e47f57717541871a3de4ee6a7762a4d3390964c7ff6827959e91a369cbacb65","observation_id":"bd74eb56-5e7d-4031-bf7a-3a93ccf39aff","resolution":{"observed_at":"2026-08-07T10:50:50.969812Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10615","last_updated":"2025-05-23T03:23:26Z","snapshot_observed_at":"2026-08-08T00:03:49.992038Z","submitted_at":"2024-08-20T07:49:38Z","title":"Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10615","snapshot_observed_at":"2026-08-07T10:50:50.123055Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.123055Z"},"links":{"cited_paper":"/paper/2408.10615","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:b97956e831b53a54e0ad27e76d77cd0eb95e56e71c96584a9d9aa14e295c1768","observation_id":"ff266c60-fd7f-4f17-be12-b9326f88f34a","resolution":{"observed_at":"2026-08-07T10:50:50.123055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.951860Z","title":"B.; Girard, P.; and Terranova, N","venue":null,"work_id":"080f70a0-c972-48b5-9020-a1f5880bff99","year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.126599Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:118f8e5cb06b1eb1aaba9b4727a9a39f38f6f4c4eb8facf1cd8050aa9ce6232e","observation_id":"28bd1275-bfa1-4d66-957c-8d336f77f2c1","resolution":{"observed_at":"2026-08-07T10:50:50.957109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18915","last_updated":"2026-05-20T07:04:38Z","snapshot_observed_at":"2026-07-06T20:42:55.911327Z","submitted_at":"2025-02-26T08:07:17Z","title":"END: Early Noise Dropping for Efficient and Effective Context Denoising","version":3},"cited_work":{"arxiv_id":"2502.18915","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.18915","snapshot_observed_at":"2026-08-07T10:50:50.563477Z","title":"END: Early Noise Dropping for Efficient and Effective Context Denoising","venue":"cs.CL","work_id":"9e8b63e7-efcc-460d-b113-2d6f9107a4e3","year":2025},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.130803Z"},"links":{"cited_paper":"/paper/2502.18915","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:635e732991c4c7607655e0a4ba10beba93a9f680316d3a2bb9990e43d516e359","observation_id":"9871a274-0bc3-4a8f-87d5-97519f3cd386","resolution":{"observed_at":"2026-08-07T10:50:50.653326Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.941808Z","title":null,"venue":null,"work_id":"fa65d4cb-d96e-4972-b853-67e24dd0bfdf","year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.135352Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:c7f3007a08e04c9bc2bcfb39e4ca53941821f6747c1972732c2d2c9bda088f18","observation_id":"6d070720-1e26-4155-8f14-c2fe9abe2818","resolution":{"observed_at":"2026-08-07T10:50:50.946268Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.930313Z","title":null,"venue":null,"work_id":"34b2c33a-0fec-4159-a0ed-c8ff5615ca9f","year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.139718Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:315c742318d0e52b528612cdbe132cade7f967d76b5add543bd19479937ec351","observation_id":"be059cc8-cfd3-450f-9e58-5fa947c01a48","resolution":{"observed_at":"2026-08-07T10:50:50.934827Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-07T10:50:50.144350Z","title":"P.; and Welling, M","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.144350Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:a1c95c6603e0781e1d3ec560c111b4b5d94457b45ca8a755416bb894869e16ba","observation_id":"3396e394-2f40-44ee-987b-c6873c83bfa5","resolution":{"observed_at":"2026-08-07T10:50:50.144350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.919645Z","title":"S.; Reid, M.; Matsuo, Y.; and Iwasawa, Y","venue":null,"work_id":"20503228-4cb9-4ebe-8927-cac5a88b0b4b","year":2022},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.148149Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:d01740875b5faeee0198c360837a05e891a397c10025a7be38600fdf0e6242af","observation_id":"9b045b58-0332-4d04-af85-8e7d47de0eed","resolution":{"observed_at":"2026-08-07T10:50:50.922744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12813","last_updated":"2024-07-19T20:37:17Z","snapshot_observed_at":"2026-08-04T21:26:05.829484Z","submitted_at":"2024-06-27T21:41:43Z","title":"Data Generation Using Large Language Models for Text Classification: An Empirical Case Study","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.12813","snapshot_observed_at":"2026-08-07T10:50:50.153342Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.153342Z"},"links":{"cited_paper":"/paper/2407.12813","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:5cc19208c57681ea92ec419710b9bf94c0068d0970bcbea8e2ced3a6912adc4c","observation_id":"2fc26267-2a43-45f5-b813-776633838bc8","resolution":{"observed_at":"2026-08-07T10:50:50.153342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07503","last_updated":"2024-08-10T20:46:47Z","snapshot_observed_at":"2026-07-06T17:58:39.485508Z","submitted_at":"2024-04-11T06:34:17Z","title":"Best Practices and Lessons Learned on Synthetic Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07503","snapshot_observed_at":"2026-08-07T10:50:50.157269Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.157269Z"},"links":{"cited_paper":"/paper/2404.07503","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:a5b95bd355494364f04bee741c6b970bf380863d12617669f44361d71d2642ca","observation_id":"03d7a2d4-33e7-4be3-bc8f-9f1c87f87286","resolution":{"observed_at":"2026-08-07T10:50:50.157269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15126","last_updated":"2024-06-14T07:47:09Z","snapshot_observed_at":"2026-07-06T18:34:51.641949Z","submitted_at":"2024-06-14T07:47:09Z","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15126","snapshot_observed_at":"2026-08-07T10:50:50.163370Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.163370Z"},"links":{"cited_paper":"/paper/2406.15126","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:08ae0177c8449934608239fdac7f8d4fc7c3b2d6c33b21eded44938efb05bc64","observation_id":"bab40330-8c93-4715-950b-a85c840ea0ef","resolution":{"observed_at":"2026-08-07T10:50:50.163370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.168787Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.168787Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:46ff5d13f90a6c43207073273f2942d39be41d6579b0116de0d62f313068ed33","observation_id":"918a8530-ca52-4f34-97d8-d8973baa339b","resolution":{"observed_at":"2026-08-07T10:50:50.168787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.03384","last_updated":"2018-07-02T19:20:02Z","snapshot_observed_at":"2026-08-04T17:07:26.080555Z","submitted_at":"2018-06-09T00:23:15Z","title":"Data Synthesis based on Generative Adversarial Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.03384","snapshot_observed_at":"2026-08-07T10:50:50.172662Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.172662Z"},"links":{"cited_paper":"/paper/1806.03384","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:8dbf506c33e32847d365da5299a8e5c3e31c29b9958b9d6c92435a1f398543af","observation_id":"d41c2700-d16f-4da0-8cea-b4c3faba6e49","resolution":{"observed_at":"2026-08-07T10:50:50.172662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.909066Z","title":"H.; Sch \\\"a rli, N.; and Zhou, D","venue":null,"work_id":"a33103ca-6c6a-449b-9697-462f04c9e106","year":2023},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.176667Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:ff973349ae9b33890dadcb54d81c7620cb5692e2343787a82095fe633dfc858a","observation_id":"40b31283-d2a8-471c-b342-ee72244dfc02","resolution":{"observed_at":"2026-08-07T10:50:50.912789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.180831Z","title":"V.; Zhou, D.; et al","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.180831Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:034a0d5de2ac8cccb012b73d19e72f053abd3ede78f717bbb44026881793a005","observation_id":"e77165e8-c892-4ae5-958a-f902cadf9198","resolution":{"observed_at":"2026-08-07T10:50:50.180831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.897186Z","title":null,"venue":null,"work_id":"b39991d0-db99-4aa4-b3fd-38b16e93b62d","year":2024},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.185107Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:a5b72fd8a10bb4e747da398a98abb2705915bbbbd7aef0fdc26dd6f80b9884cb","observation_id":"d396899b-b2c9-42e8-a9ef-14d72ae4ccbd","resolution":{"observed_at":"2026-08-07T10:50:50.900620Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:50.780679Z","title":"J.; Krishna, R.; Shen, J.; and Zhang, C","venue":null,"work_id":"cbf1f5b7-1c3b-4d1c-86ee-81635a088602","year":2023},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.190578Z"},"links":{"citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:beaf8136180369c75b327fa3089cc2e63d2be8066c29e65613bcc1174ed56559","observation_id":"d12b3dd1-1b1b-4904-9c6e-47d0db4b00c2","resolution":{"observed_at":"2026-08-07T10:50:50.867486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10703","last_updated":"2023-05-18T04:30:09Z","snapshot_observed_at":"2026-07-06T15:29:01.076710Z","submitted_at":"2023-05-18T04:30:09Z","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval","version":1},"cited_work":{"arxiv_id":"2305.10703","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.10703","snapshot_observed_at":"2026-08-07T10:50:50.234625Z","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval","venue":"cs.CL","work_id":"41429e62-95d6-4237-8bc8-e68fb03ed68a","year":2023},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.197955Z"},"links":{"cited_paper":"/paper/2305.10703","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:73d403bb27341518a2b7e58b4affd03af48fdaaf6adec66123b9c90c82c4e776","observation_id":"3cec156f-e529-41ae-98f2-827691a458ce","resolution":{"observed_at":"2026-08-07T10:50:50.345359Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.01910","last_updated":"2023-03-10T17:20:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-03T15:43:03Z","title":"Large Language Models Are Human-Level Prompt Engineers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01910","snapshot_observed_at":"2026-08-07T10:50:50.204155Z","title":"I.; Han, Z.; Paster, K.; Pitis, S.; Chan, H.-C.; and Ba, J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.204155Z"},"links":{"cited_paper":"/paper/2211.01910","citing_paper":"/paper/2506.04172"},"observation_digest":"sha256:b3dd1e983332c2aa9c0bb98738ff551ad851b7dea014ca566a46d0a40b0413bf","observation_id":"9cc7e790-e9b8-4b4e-a61e-8c0438af1583","resolution":{"observed_at":"2026-08-07T10:50:50.204155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.04172","last_updated":"2025-06-04T17:15:19Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T10:44:14.455669Z","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":2,"verified_fuzzy":6},"total_outbound_references":29},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 2 inbound Pith citation observations for arXiv:2506.04172."}