{"as_of":"2026-08-16T14:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:024d0596564ad35504896f67d224a976b654a9fbb5ae7b91688bd2dfe9898913","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:28:47.163457Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-03T14:54:36.915852Z","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":"2026-07-03T14:58:32.445072Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"cited_work":{"arxiv_id":"2506.19773","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.19773","snapshot_observed_at":"2026-07-03T14:58:32.445072Z","title":"Automatic prompt optimization for knowledge graph construction: Insights from an empirical study,","venue":null,"work_id":"28824387-1e91-4574-b33e-6c0e806e4544","year":2025},"citing_paper":{"arxiv_id":"2607.01972","last_updated":"2026-07-02T10:07:34Z","snapshot_observed_at":"2026-08-14T05:13:37.101578Z","submitted_at":"2026-07-02T10:07:34Z","title":"Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-03T14:54:36.915852Z"},"links":{"cited_paper":"/paper/2506.19773","citing_paper":"/paper/2607.01972"},"observation_digest":"sha256:d0ae87f2c715d22d6bcd84851e20563abcdd57f80818fbcc8a41533d8f307ea8","observation_id":"c511d676-7c56-4c8f-93bc-2b64950ebc1d","resolution":{"observed_at":"2026-07-03T14:58:32.446550Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.19773/citation-record","integrity":"/paper/2506.19773/integrity","json":"/paper/2506.19773/citation-record.json","paper":"/paper/2506.19773"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:28:49.931929Z","title":"Knowledge Graphs","venue":null,"work_id":"59865211-6ae8-4d1c-8a2f-2446458fe8d9","year":2021},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.182573Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:8ac74a59a5580c97d460825bf0a1f85157d552cddaa27b477febc86852d2815f","observation_id":"f0a72b94-4b39-413b-b777-26712d6e6ec7","resolution":{"observed_at":"2026-08-15T18:28:50.008243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.910520Z","title":"A Comprehensive Survey on Automatic Knowl- edge Graph Construction","venue":null,"work_id":"055011cd-713f-48fb-ae3d-47692a0dae73","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.243965Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:e97ccd438ee2f79087e78298f786640a5e428d85769545f2b3b850ec5b17e66f","observation_id":"5ba564b2-5f82-4331-b257-34463ec54a84","resolution":{"observed_at":"2026-08-15T18:28:49.916897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.892411Z","title":"A survey of current approaches for mapping of relational databases to rdf","venue":null,"work_id":"f31145af-12f1-4fce-bc68-f8fd0f89d846","year":2009},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.248787Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:5cc151c64cea3770a2917be4a1a8081d480c288243fb2073beb4f8c5b378bfe2","observation_id":"b4a5dfea-94ab-4375-846d-ea6e57c5a058","resolution":{"observed_at":"2026-08-15T18:28:49.898744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.773499Z","title":"Rml: A generic language for integrated rdf mappings of heterogeneous data","venue":null,"work_id":"ab4fc841-d10e-4d4f-8486-36263d7cd925","year":2014},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.254020Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:0165b6981cc27e742ff2250356934662432851ddd92aabb524c25c1aba5226c7","observation_id":"703bcec7-793d-4943-b542-59e579a67809","resolution":{"observed_at":"2026-08-15T18:28:49.848140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.697380Z","title":"Wikidata: A Free Collaborative Knowledge Base","venue":null,"work_id":"b7db41b3-7768-48a3-84e7-e4eb78fccb6f","year":2014},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.259510Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:61b6b385401d6f65133a2d3f9fc5f84ff2fe6ed98e8ad1a0e259c01722e3371a","observation_id":"651c343f-d514-4bf3-903b-3d321fba0094","resolution":{"observed_at":"2026-08-15T18:28:49.702762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.677879Z","title":"Research trends for the interplay between large language models and knowledge graphs","venue":null,"work_id":"684eb349-02dd-42d9-ac47-9db37e7d5019","year":2024},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.264249Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:6fb8f62b3704be56e4117e9ceedffd65c8654a17a7e2f1e05a063da40014f6f1","observation_id":"763a7e60-6664-4c69-9ee6-f85dd976d13a","resolution":{"observed_at":"2026-08-15T18:28:49.684400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.653633Z","title":"Rodriguez-Méndez","venue":null,"work_id":"ae27d6bf-47ba-41c5-89fc-346ddba10f87","year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.269655Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:b37f08bf4b03da09a7b2a349ca3bc3f57d6ce97a40e3075eeb059e7ddf22bb10","observation_id":"20652f16-0471-4f94-b55f-93a3a77e397c","resolution":{"observed_at":"2026-08-15T18:28:49.665673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.535041Z","title":"Language models as knowledge bases? In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pages 2463–2473, Hong Kong, China, November 2019","venue":null,"work_id":"96a8ec95-6129-4492-b9d9-7dbb8875227e","year":2019},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.274204Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:2649f8a6160e2df2532b923cb84b13791013bc1b83f1528316315d8979059321","observation_id":"61afc7e1-d684-4fc6-b110-4ee82acc2c2b","resolution":{"observed_at":"2026-08-15T18:28:49.581119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.515847Z","title":"Knowledge graph generation from text","venue":null,"work_id":"9bbd03e4-37bb-4c92-9fab-c34e085a10e1","year":2022},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.352329Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:bb88736a30ad0764ef45c0eaacefc6a80b31d1c9360be2bab03c5e6f217ef1ed","observation_id":"5ff98b62-597c-4004-87db-34109c57d3b2","resolution":{"observed_at":"2026-08-15T18:28:49.522105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.496421Z","title":"Faisal Mahbub Chowdhury, Nandana Mihindukulasooriya, Owen Cornec, and Al- fio Massimiliano Gliozzo","venue":null,"work_id":"4c14c8a6-3c7a-4db1-aa41-9b09b882a1df","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.426876Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:9a42d181e735a5d5370b8c2088e8fea9148f8ca7235563039a1a3d014bb86044","observation_id":"33601d89-a33f-4fdc-93c2-68c590dae921","resolution":{"observed_at":"2026-08-15T18:28:49.502870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.322321Z","title":"Ex- ploring In-Context Learning Capabilities of Foundation Models for Generating Knowledge Graphs from Text","venue":null,"work_id":"9d4c44cf-98b1-461b-ba11-6934148faf32","year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.526722Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:672640e20b2b729da20f3ea10535196c51f39e22175ee21a90815b9e45ef563a","observation_id":"3b5345e1-bd3e-40e9-98de-390ce9a1e960","resolution":{"observed_at":"2026-08-15T18:28:49.359124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.302517Z","title":"Re2G: Retrieve, rerank, generate","venue":null,"work_id":"48c62d5b-3f98-4f51-9f4a-60752e8783a3","year":2022},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.570633Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:6235466e7870d03de8cf3c870c837e9ae0df4a140d201833ebd41bc88f6d38a1","observation_id":"3ebc1190-3e86-461a-b265-679ff87749f5","resolution":{"observed_at":"2026-08-15T18:28:49.309372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16130","last_updated":"2025-02-19T10:49:41Z","snapshot_observed_at":"2026-08-16T12:38:40.131901Z","submitted_at":"2024-04-24T18:38:11Z","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16130","snapshot_observed_at":"2026-08-15T18:28:46.575685Z","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.575685Z"},"links":{"cited_paper":"/paper/2404.16130","citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:8078cf69a43d7483866552a73593ed0ad0599486f8c0343b7efbd3bc14014056","observation_id":"f78e3ea8-9626-4ee8-8ef5-6ade9a52cc80","resolution":{"observed_at":"2026-08-15T18:28:46.575685Z","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":"2026-08-15T18:28:49.181220Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":"08e3bac5-007c-4004-b867-83c827caa1ad","year":2020},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.580142Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:f042fbe1730d5467cafd85beb6a37fa606064ed30e1baea390f0f5fd7d83a0e3","observation_id":"bc4909fd-d5d6-4b0e-afb6-6c13eb2fcfb2","resolution":{"observed_at":"2026-08-15T18:28:49.257912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:46.586205Z","title":"Learning to summarize with human feedback","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.586205Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:bbc10ba8285108bbbd42c58b9abb9e3d258ea4b130e4bb5dd6ee07854cc28440","observation_id":"dc60351d-dae1-44ee-8873-abd2d778d960","resolution":{"observed_at":"2026-08-15T18:28:46.586205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-15T18:28:46.591890Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.591890Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:99fff970230358007da821c54daed5ce01a0347fae214c1ff52d43036bdc929b","observation_id":"51bb161e-2a37-4c14-8bba-eeba038b867e","resolution":{"observed_at":"2026-08-15T18:28:46.591890Z","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":"2026-08-15T18:28:49.146552Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","venue":null,"work_id":"61e6d1ba-5597-40f3-9c2a-e9c7599f9e5a","year":2022},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.597300Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:ae8ceffb591a8765517d068c3667f088523c8716891138438579747f99d0247e","observation_id":"137f918e-af94-4d34-96a0-10433f23a515","resolution":{"observed_at":"2026-08-15T18:28:49.153899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.127833Z","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","venue":null,"work_id":"05e75ce6-e8ba-440a-b393-878168e72d78","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.601927Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:32c8678b1203352f5236453c0edc8250aacaac355209e22d4350dc7175e7e9a9","observation_id":"cc373454-49b7-4a84-8263-d4e7def9cc4d","resolution":{"observed_at":"2026-08-15T18:28:49.134132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.043005Z","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","venue":null,"work_id":"73a70939-085f-4d2e-abc4-f53cd429187a","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.606862Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:a247582859c918ddfb00326e959af4d23d195af28a56aea1fc6252c40f436a47","observation_id":"bdbb5b3d-c8d9-45e6-9640-67bebb633f30","resolution":{"observed_at":"2026-08-15T18:28:49.091390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:49.022176Z","title":"Ask me anything: A simple strategy for prompting language models","venue":null,"work_id":"196f8270-5865-4857-9e66-681c5de2cdd6","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.700654Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:7127b253dd49bc9dd1eaf72ef90e8bfd27764bab45f09677084d516bd14f0390","observation_id":"f6937367-cbf1-43ed-99e1-7b0fcf0ae5b0","resolution":{"observed_at":"2026-08-15T18:28:49.029368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.890842Z","title":"Beyond english: The impact of prompt translation strategies across languages and tasks in multilingual llms","venue":null,"work_id":"10b6d6d0-dad3-438d-acc8-ba0351fd1306","year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.732929Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:6ad01789393eebf4a7d049733a58efa8aadd2cf1983fa72e469c42b816691185","observation_id":"baeb5413-6737-425e-9f33-9b268590aaf2","resolution":{"observed_at":"2026-08-15T18:28:49.009066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:46.792663Z","title":"A systematic survey of automatic prompt optimization tech- niques","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.792663Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:dc460d537e2fa00fb8f8e76fd1e03e496c2c223d523c7d41a362b1629bfa790c","observation_id":"fdce67d8-c35e-4b92-b991-4b0d1a9d6140","resolution":{"observed_at":"2026-08-15T18:28:46.792663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11560","last_updated":"2025-02-17T08:48:07Z","snapshot_observed_at":"2026-08-16T12:57:49.784855Z","submitted_at":"2025-02-17T08:48:07Z","title":"A Survey of Automatic Prompt Engineering: An Optimization Perspective","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11560","snapshot_observed_at":"2026-08-15T18:28:46.798143Z","title":"A survey of automatic prompt engineering: An optimiza- tion perspective","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.798143Z"},"links":{"cited_paper":"/paper/2502.11560","citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:7edc0d88bc3a51f4d7b9f7f7df6602d9eaa5129cee5b217d8e4623a9b6f5fa0f","observation_id":"5ad7fafa-c6c0-430d-a583-42906290b944","resolution":{"observed_at":"2026-08-15T18:28:46.798143Z","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":"2026-08-15T18:28:48.872756Z","title":"Open information extraction from the web","venue":null,"work_id":"2b64e984-6efa-4290-953a-900d974152ab","year":2008},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.803097Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:d5f0c63c95f2cfd731bb31063cf4e6596f765f074417b204ae0a3158dbd6e541","observation_id":"4257377e-661d-42b7-8aef-ee8753152530","resolution":{"observed_at":"2026-08-15T18:28:48.879135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.721109Z","title":"Knowledge Graph Embedding with Hierar- chical Relation Structure","venue":null,"work_id":"5b991992-388a-425c-ad71-b04237a7397c","year":2018},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.807821Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:612543996726a07904a12bb322da3aa43342bda9d1226dac7bb5d9877984fcde","observation_id":"8ec90f16-0a07-4e02-a222-8ec62fcdd75a","resolution":{"observed_at":"2026-08-15T18:28:48.805184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.704583Z","title":"Open knowl- edge graphs canonicalization using variational autoencoders","venue":null,"work_id":"a15c7542-88b0-4e7e-9578-c95eb3dbccfd","year":2021},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.812925Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:64d2a7148d7c3be2459b242340788e6f569052020551c8427c8100dd0bfda04f","observation_id":"453ec30e-e74d-4311-b9e2-47c85e8f0da8","resolution":{"observed_at":"2026-08-15T18:28:48.709918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.615815Z","title":"Generative relation linking for question answering over knowledge bases","venue":null,"work_id":"201b0d56-eaad-47c2-8ead-27677edda2c4","year":2021},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.817622Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:01a12e2034fab0f11dbdafe9123b93bad66a197ac38d8787066288e14649cd58","observation_id":"2a3b55f0-42d2-4c67-82de-39dc0964f55b","resolution":{"observed_at":"2026-08-15T18:28:48.692973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:46.823410Z","title":"Training language models to follow instructions with human feedback","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.823410Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:441a1b2c741d896915a84691a4dfefd7c2dac8d53db36fe41d35e2d9aebf85ef","observation_id":"7f3edb0c-dae5-4b12-945d-4bc7172e423f","resolution":{"observed_at":"2026-08-15T18:28:46.823410Z","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":"2026-08-15T18:28:46.829420Z","title":"Deep reinforcement learning from human preferences","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.829420Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:dff09cd868e1ec5cf03a4958252ec93aa77358e80d6d94f648c7926d92d98937","observation_id":"33f60090-a3e5-4e78-874d-8556caf39dea","resolution":{"observed_at":"2026-08-15T18:28:46.829420Z","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":"2026-08-15T18:28:48.534941Z","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? EMNLP 2022, 2022","venue":null,"work_id":"dfb10117-45a9-4a0b-b464-5478b010b6dd","year":2022},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.834341Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:3747f3c395e57e5d920754462fad822371a4512b22feeb15da5abe33ef8fc982","observation_id":"04ddcbbc-a5cc-413c-98e3-96b78a9ca008","resolution":{"observed_at":"2026-08-15T18:28:48.543335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.482124Z","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","venue":null,"work_id":"6eb70917-af4f-483f-bdbb-464ab19e6f51","year":2022},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.856018Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:fdfefc11a253d5befc7c281ba3364f14ce90f6293a54d10f7d28dd948c55f6aa","observation_id":"87a2f38d-fed5-473f-b13f-f34122698353","resolution":{"observed_at":"2026-08-15T18:28:48.521941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.382568Z","title":"Enguix, and Kusum Lata","venue":null,"work_id":"f60e57cb-bb3d-43d7-9156-90445ed27fb6","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.914614Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:e5c89c87b37d9f734f571f3ebd566741eda4d5437b7be4590668802b66808069","observation_id":"09f6862b-d3c0-4521-ac9d-377401e33f24","resolution":{"observed_at":"2026-08-15T18:28:48.388589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18746","last_updated":"2025-07-12T20:39:40Z","snapshot_observed_at":"2026-08-16T12:55:10.608311Z","submitted_at":"2025-02-26T01:42:08Z","title":"A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18746","snapshot_observed_at":"2026-08-15T18:28:46.958249Z","title":"Automatic prompt optimization via heuristic search: A survey","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.958249Z"},"links":{"cited_paper":"/paper/2502.18746","citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:4b56fa0897d33b139119089dbabcb082a3ef20e9ae6bc114e2e84c116a4e32c8","observation_id":"634b5b59-34a3-4d73-8329-5a9a943dcb28","resolution":{"observed_at":"2026-08-15T18:28:46.958249Z","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":"2026-08-15T18:28:48.322873Z","title":"Fairness-guided few-shot prompting for large language models","venue":null,"work_id":"af0bb2d3-739a-4b8e-9416-1b9ede08e12c","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.963390Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:d85c6fb221c4d03f62deb670ca48d3728a001608f5c77cdbead949608189e43d","observation_id":"bfd8b7f1-fac9-4f46-b880-9131a1dbe7c0","resolution":{"observed_at":"2026-08-15T18:28:48.370393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.167998Z","title":"Gradient Descent","venue":null,"work_id":"27af0808-1294-4f59-b0d8-051f34e8fab9","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.968633Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:29faae44a1157eb613ed72a101dbaaee838a5e7d95da36571c97cf830fca98f7","observation_id":"90fc8f9a-073c-4dc5-ad0c-2bcba7d403a9","resolution":{"observed_at":"2026-08-15T18:28:48.203420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:48.150491Z","title":"Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization","venue":null,"work_id":"9383158f-0ca4-46cf-b937-2e900808dba9","year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.974261Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:aa53b11bb79e2f29225fb179cfae3519409570ce0b5bb96f40b325e048fe9734","observation_id":"fdb07435-3823-48c3-980c-3a2462448755","resolution":{"observed_at":"2026-08-15T18:28:48.156519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.999313Z","title":"Optimizing generative ai by backpropagating language model feedback","venue":null,"work_id":"09b33311-65d8-4afe-a2b6-864e5290d29e","year":2025},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.978519Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:c789672955977a5fd68b198e3597cda7ac171a39978ae17480631fb08eafb83d","observation_id":"fa1119d0-bec4-4474-af0a-acf0ca6ce09c","resolution":{"observed_at":"2026-08-15T18:28:48.110894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.942721Z","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","venue":null,"work_id":"c93f97a2-9a17-4dfa-8f3c-ba08969dbab4","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.982390Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:de2afd66ea2dad06af8109246fd99b3331650de78f4e755fea371b8e308590ff","observation_id":"14b3d8e4-7971-4d23-8dff-0d4dcb0df446","resolution":{"observed_at":"2026-08-15T18:28:47.948873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.926104Z","title":"Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, and Christopher Ré","venue":null,"work_id":"853ac1e6-edd8-4efa-8eee-b9501d3b3f4d","year":2024},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.986423Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:4b5c349da0b261dc6acb6e55e53686ed3c38d0761c6996c3d0c1b040670709f3","observation_id":"72fb413d-5e5f-40b2-b968-0d5b3ce42656","resolution":{"observed_at":"2026-08-15T18:28:47.930984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.706657Z","title":"Evoprompt: Connecting llms with evolutionary algorithms yields powerful prompt optimizers","venue":null,"work_id":"e53a6e40-a9c9-4c74-9865-145cf9b5acd8","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.990875Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:91979c8fc7900e6f2cee23f26e3bbc85c1b429ef358f1774825741312f571e87","observation_id":"fcb44203-f4b6-4abb-9511-32d4fc112be9","resolution":{"observed_at":"2026-08-15T18:28:47.796698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.685777Z","title":"Large Language Models are Human-Level Prompt Engineers","venue":null,"work_id":"585a8f26-47f8-45ac-8c8b-724ee5f71d49","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:46.995633Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:c4c318c4d639f1954ef309220b06ec1043d1f468dd0ec977de2bd7d68ca87ca9","observation_id":"cfc9da92-bfc7-4b40-a997-20af7969c906","resolution":{"observed_at":"2026-08-15T18:28:47.692896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.665891Z","title":"Query-dependent prompt evaluation and optimization with offline inverse rl","venue":null,"work_id":"ad2463f5-1570-49c7-8731-ce2d21a2565d","year":2024},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:47.000585Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:503eb1a4b56b9f82fac50e21db9e13bece248d15f630cb84909e3d4b5843df8f","observation_id":"13cd64fa-9ed2-4bba-ac26-034ec80e4f2b","resolution":{"observed_at":"2026-08-15T18:28:47.671383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12954","last_updated":"2024-01-23T18:22:19Z","snapshot_observed_at":"2026-08-13T04:36:43.576712Z","submitted_at":"2024-01-23T18:22:19Z","title":"Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12954","snapshot_observed_at":"2026-08-15T18:28:47.047786Z","title":"Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:47.047786Z"},"links":{"cited_paper":"/paper/2401.12954","citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:21c83c888a7a46c5fe851abe0db8c53c354023f2653822f359b6f879a79a0f43","observation_id":"00b88803-2c41-4637-8c93-76fe269451fe","resolution":{"observed_at":"2026-08-15T18:28:47.047786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03714","last_updated":"2023-10-05T17:37:25Z","snapshot_observed_at":"2026-08-04T05:21:05.846165Z","submitted_at":"2023-10-05T17:37:25Z","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03714","snapshot_observed_at":"2026-08-15T18:28:47.093156Z","title":"Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christo- pher Potts","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:47.093156Z"},"links":{"cited_paper":"/paper/2310.03714","citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:a2985dc39575924cfe860f2b386f61def58b42f5db1288f670a9b86f0463b7ef","observation_id":"96fdc1ec-dbf6-45bd-968b-f4ce74875d9c","resolution":{"observed_at":"2026-08-15T18:28:47.093156Z","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":"2026-08-15T18:28:47.499415Z","title":"Exploiting asymmetry for synthetic training data generation: SynthIE and the case of information extraction","venue":null,"work_id":"c31dcecf-8c98-4bc8-b14a-0f724024d5fd","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:47.146618Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:63460440524ebf3895873a43d7ca04be4a2579e2d5fd93b5f12b2902eb841e0d","observation_id":"92f98df9-360b-4f76-ad9d-57b8d5215fb9","resolution":{"observed_at":"2026-08-15T18:28:47.579552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.478380Z","title":"REBEL: Relation extraction by end-to-end language generation","venue":null,"work_id":"475cc68e-a6f1-4c0e-a35d-37384fc51dfc","year":2021},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:47.153017Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:7a24431eb75ae052e5c712c31866ec6bd1b72eaf8ef1e3fa2d50f05d8e61dca8","observation_id":"68b3a8a2-1980-4eae-a434-96ae30b2adf0","resolution":{"observed_at":"2026-08-15T18:28:47.484739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.456018Z","title":"Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs","venue":null,"work_id":"dc40ce8f-68bf-47b2-ba40-fd9b4779cebe","year":2024},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:47.158015Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:8c8763511f57aae9dbb55961e8bfb2d9345091e3355920adc669e445d43cce05","observation_id":"9794cf37-0077-4a7f-a50d-4e8e24e9974d","resolution":{"observed_at":"2026-08-15T18:28:47.463932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:28:47.407056Z","title":"Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages","venue":null,"work_id":"5ef05042-9e5d-40fb-890f-965a59239584","year":2023},"citing_paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:28:47.163457Z"},"links":{"citing_paper":"/paper/2506.19773"},"observation_digest":"sha256:6d9536ef3297f3e725c93343a796a83ea5d053d63e8f2b9ee1e6e349072b9d21","observation_id":"90d86f3b-5b89-4e66-9821-55f9795c9521","resolution":{"observed_at":"2026-08-15T18:28:47.443121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.19773","last_updated":"2025-08-04T22:04:58Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-15T18:22:47.057828Z","submitted_at":"2025-06-24T16:38:49Z","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":0,"verified_fuzzy":38},"total_outbound_references":48},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 1 inbound Pith citation observation for arXiv:2506.19773."}