{"as_of":"2026-08-09T02:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ec9990a155eee74c3bfb197f78916afcb35e8a9b13adeb9c98c929a9baa2761a","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T09:02:59.078398Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2601.15037/citation-record","integrity":"/paper/2601.15037/integrity","json":"/paper/2601.15037/citation-record.json","paper":"/paper/2601.15037"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T09:02:55.053110Z","title":"Knowledge graph based synthetic corpus generation for knowledge-enhanced language model pre-training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.053110Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:e565c6042b882b6461e8da0e8ed75fd65c93fb69283b6027d8beb95a52348d0e","observation_id":"a5a61224-6882-4cb0-aa13-98f2629eba51","resolution":{"observed_at":"2026-08-03T09:02:55.053110Z","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":"2026-08-03T09:02:55.091563Z","title":"Cafarella, Stephen Soderland, Matthew Broadhead, and Oren Etzioni","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.091563Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:0678978d8fafd5ddcc5e20e46356aa05ac84a64aabca5f285d0185ebd662a0b3","observation_id":"fbe1daef-1cd6-479b-9e33-360b470eba0c","resolution":{"observed_at":"2026-08-03T09:02:55.091563Z","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":"2026-08-03T09:02:55.153715Z","title":"Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, et al","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.153715Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:23cbbdc85ceba4b11f58437a2b3fad2a536e31ad7b2e82d55b3878a837f19fc8","observation_id":"caacd6d6-0a7e-4b9f-93ea-bb525216cdbd","resolution":{"observed_at":"2026-08-03T09:02:55.153715Z","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":"2026-08-03T09:02:55.224962Z","title":"REBEL: relation extraction by end-to-end language generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.224962Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:42aeb2b543c23d877e9b4d230369b745efccd63f0b45d158f37788f54c5eead1","observation_id":"89905702-f4e4-45c8-bdeb-16251339ee5e","resolution":{"observed_at":"2026-08-03T09:02:55.224962Z","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":"2026-08-03T09:02:55.306519Z","title":"Exploiting syntactico-semantic structures for relation extraction","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.306519Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:c1fdb6e7196f5e593a2ad57a0a55ff72d62bb5bc098a7e1fecd328eb42712831","observation_id":"edd27948-90ec-410a-9850-af61e1518a26","resolution":{"observed_at":"2026-08-03T09:02:55.306519Z","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":"2026-08-03T09:02:55.367481Z","title":"SAC-KG: exploiting large language models as skilled automatic constructors for domain knowledge graph","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.367481Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:af360ef96dd6aea7b96105480ac5ac67c4458ac8f373fbe675e83bcd815cc6a7","observation_id":"6defc8ad-c440-4167-8a52-2cb42b328dba","resolution":{"observed_at":"2026-08-03T09:02:55.367481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03216","last_updated":"2025-12-12T11:26:32Z","snapshot_observed_at":"2026-07-06T17:25:35.493362Z","submitted_at":"2024-02-05T17:26:49Z","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03216","snapshot_observed_at":"2026-08-03T09:02:55.441644Z","title":"BGE m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.441644Z"},"links":{"cited_paper":"/paper/2402.03216","citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:9f8c6888ddc472aafde75a1aa76dbc7a2143dcca2fb629d45c1e3f83afa3d393","observation_id":"454a0215-9bb7-4edd-9e5a-b649402fe718","resolution":{"observed_at":"2026-08-03T09:02:55.441644Z","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":"2026-08-03T09:02:55.495105Z","title":"Overview of MUC-7","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.495105Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:797837e27763a5603f6365b892a3f6263548fb5f7e004ec620fb6238a6cc8a72","observation_id":"56b00b1a-9d3a-4188-96a3-bcf763ada314","resolution":{"observed_at":"2026-08-03T09:02:55.495105Z","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":"2026-08-03T09:02:55.561611Z","title":"Unsupervised cross-lingual representation learning at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.561611Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:b6e40a97769b69a5e5d22e3f71d029e3c4d9e543a276fe9f9b50dd29391a9538","observation_id":"de63fd31-a068-4272-9908-cc3501e7c691","resolution":{"observed_at":"2026-08-03T09:02:55.561611Z","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":"2026-08-03T09:02:55.593908Z","title":"Rlprompt: Optimizing discrete text prompts with reinforcement learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.593908Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:f01914b52a86e1374e40073cae7d6c6055ab91511f5c930290695ec030b3e358","observation_id":"e3c1ba27-002d-41bc-a32b-95be23b2116c","resolution":{"observed_at":"2026-08-03T09:02:55.593908Z","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":"2026-08-03T09:02:55.647542Z","title":"Span-level model for relation extraction","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.647542Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:45bb54630ee9f1b9f85b91739714e933fc51875ee3d81ecc549a33643418d78f","observation_id":"f6f3f7a0-93c2-444e-922a-e1450686d019","resolution":{"observed_at":"2026-08-03T09:02:55.647542Z","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":"2026-08-03T09:02:55.703972Z","title":"Dognin, Inkit Padhi, Igor Melnyk, and Payel Das","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.703972Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:464e41170066df11cd199c0371caa931371ea3c4211001bda55a22ad3b71a96f","observation_id":"e57be485-701b-4c27-bcfe-544e9fd78bf3","resolution":{"observed_at":"2026-08-03T09:02:55.703972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16130","last_updated":"2025-02-19T10:49:41Z","snapshot_observed_at":"2026-07-06T18:05:11.700127Z","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":"2026-08-03T09:02:55.756538Z","title":"From local to global: A graph RAG approach to query-focused summarization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.756538Z"},"links":{"cited_paper":"/paper/2404.16130","citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:42f82b8761947f455e12f86b186bbf80b8a524e9e4d8a33a275fd3bc548d55ea","observation_id":"63eea9cf-5960-472a-aab5-baeef86e024f","resolution":{"observed_at":"2026-08-03T09:02:55.756538Z","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":"2026-08-03T09:02:55.843856Z","title":"The 2020 bilingual, bi-directional webnlg+ shared task overview and evaluation results (webnlg+ 2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.843856Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:6453286b9bfd3e943a02a1c92cc33b03a9298d9dbfab7219af07f08052d3f610","observation_id":"1cffee2a-3ca9-4209-a673-15868327280b","resolution":{"observed_at":"2026-08-03T09:02:55.843856Z","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":"2026-08-03T09:02:55.906040Z","title":"Suchanek","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.906040Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:8609ce9632fb0c8fc3f3622d6155b134d4d3300e17c301780db219ee81b752c7","observation_id":"f2ae3f55-d7a6-4954-a34d-8d321dcc80f9","resolution":{"observed_at":"2026-08-03T09:02:55.906040Z","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":"2026-08-03T09:02:55.971210Z","title":"PPDB: the paraphrase database","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:55.971210Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:ce296fdaf9a8dff6d398e72ac5e2041af33f85cd81103c8d89f76d0c6d31611f","observation_id":"4ebbccdc-30c6-46cf-9864-ff7e96e5ea25","resolution":{"observed_at":"2026-08-03T09:02:55.971210Z","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":"2026-08-03T09:02:56.050520Z","title":"Table filling multi-task recurrent neural network for joint entity and relation extraction","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.050520Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:7ba4bf7d836c0bc4f902a61324f24d1f81c5883e62187d7a303ed53c5b9f3652","observation_id":"847686d6-fced-41db-be89-b58cd57a32c6","resolution":{"observed_at":"2026-08-03T09:02:56.050520Z","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":"2026-08-03T09:02:56.114993Z","title":"Knowledge Graphs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.114993Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:44e9ab73277f0e1a9a52dbabf7486f1cbbfa570f27a58f46f0cb848e7c46f13e","observation_id":"a282ed9d-c653-42d4-a88e-04229edb6c24","resolution":{"observed_at":"2026-08-03T09:02:56.114993Z","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":"2026-08-03T09:02:56.160233Z","title":"Relink: Constructing query-driven evidence graph on-the-fly for graphrag","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.160233Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:134e5572ef613612133c3200ef46506fb7858cea1e10d57535a028fcf0a0d0b2","observation_id":"b0fb52c9-8a31-4dc6-a5f3-383ba20c8c24","resolution":{"observed_at":"2026-08-03T09:02:56.160233Z","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":"2026-08-03T09:02:56.218590Z","title":"Xu, Jun Araki, and Graham Neubig","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.218590Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:b6cdfa9c0172a98c8abc30fac096c54772959f6c0be80a3ea802048e76c700d3","observation_id":"a4884f5e-3907-49bd-9f30-e46a8307245b","resolution":{"observed_at":"2026-08-03T09:02:56.218590Z","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":"2026-08-03T09:02:56.274532Z","title":"Genie: Generative information extraction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.274532Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:0ae0c3061ea8f9b3b6cb63ff47260f358db0661be6ea64c04417ef96de4aa888","observation_id":"f6e97899-fb45-4b59-98ba-a5fe568ec9ea","resolution":{"observed_at":"2026-08-03T09:02:56.274532Z","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":"2026-08-03T09:02:56.377000Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.377000Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:6d41014353176f65fdeab75920650e4e2e06dfab460d7b0bda3c3c1c3d296d91","observation_id":"a8b667df-283b-4385-9275-325dfd4d2fe0","resolution":{"observed_at":"2026-08-03T09:02:56.377000Z","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":"2026-08-03T09:02:56.413800Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.413800Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:6034d6bc5016ddeaa31b1cbb9b0887ef0f94c3f9a0137efb7c1e8b2588761adc","observation_id":"51833f10-4d5b-4cea-8ccc-e8649c739bf1","resolution":{"observed_at":"2026-08-03T09:02:56.413800Z","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":"2026-08-03T09:02:56.497829Z","title":"P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.497829Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:1e1f8849e934cd86504cf4785698eb038a9d9d24c61f4f08c97f90a834710e43","observation_id":"0d6455b1-2418-4435-8c07-89f58d010fdf","resolution":{"observed_at":"2026-08-03T09:02:56.497829Z","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":"2026-08-03T09:02:56.577557Z","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.577557Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:3f7bf5acd7c40b3083b84ca9046271284d79980636d9d4f78685b79845ff97c9","observation_id":"26d5b7ba-c4e6-4dbb-81cf-4e35f8704242","resolution":{"observed_at":"2026-08-03T09:02:56.577557Z","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":"2026-08-03T09:02:56.660238Z","title":null,"venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.660238Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:532e05a2fe919748b1aa17fe6e5793ad4165387de91e5c18903066ffbcffe8b0","observation_id":"ccc7734d-c9f1-4e24-8ffa-238de6f54e22","resolution":{"observed_at":"2026-08-03T09:02:56.660238Z","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":"2026-08-03T09:02:56.712306Z","title":"Kanatsoulis, and Sanmi Koyejo","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.712306Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:87e87cb3455189b56b8f7386191a4d02919a3eaeb13b8bf939c2409e918fce4d","observation_id":"e333490c-ccb1-4472-803a-e053f82711f2","resolution":{"observed_at":"2026-08-03T09:02:56.712306Z","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":"2026-08-03T09:02:56.765844Z","title":"Pan, Guido Vetere, Jos \\' e Manu \\' e l G \\' o mez - P \\' e rez, and Honghan Wu","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.765844Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:d68f97c2b4452d649ec1cdccfe699c5a2e4125084eb65373ca5d14881d487960","observation_id":"04f90316-f4a7-4855-87a8-a86ff7f1dc3e","resolution":{"observed_at":"2026-08-03T09:02:56.765844Z","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":"2026-08-03T09:02:56.832830Z","title":"Unifying large language models and knowledge graphs: A roadmap","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.832830Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:eb021170a8fca0967cc3613cbc8eb0c2422413fb26259d4601a593d7c8414ed0","observation_id":"dd9773a5-f683-4a99-8d48-7cd56dd5a78c","resolution":{"observed_at":"2026-08-03T09:02:56.832830Z","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":"2026-08-03T09:02:56.909077Z","title":"Aligning open IE relations and KB relations using a siamese network based on word embedding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.909077Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:d65e104ab52546ced716395f004ce9dd54b8851781ad96b973a765c9123714cc","observation_id":"46d23486-0bf5-46d1-81f8-39f34908599e","resolution":{"observed_at":"2026-08-03T09:02:56.909077Z","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":"2026-08-03T09:02:56.987554Z","title":"Onerel: Joint entity and relation extraction with one module in one step","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:56.987554Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:86242c3e2f6475988ae8dfe050609455edaf461db5ad86625dbd43d4b9dad380","observation_id":"23b5b6af-f209-4416-8336-b6dbb3317e4e","resolution":{"observed_at":"2026-08-03T09:02:56.987554Z","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":"2026-08-03T09:02:57.065145Z","title":"Logan IV, Eric Wallace, and Sameer Singh","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.065145Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:0d04088683419117e89e338f84c7246b58d42e90b84e3f1c8081fa5e605399c0","observation_id":"e2de6665-e39f-4ef8-b90e-09310a148bf5","resolution":{"observed_at":"2026-08-03T09:02:57.065145Z","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":"2026-08-03T09:02:57.146866Z","title":"Overview of results of the MUC-6 evaluation","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.146866Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:a26017dcb65d7567a22e90d983794ff02d88e77741cdb41adb0a3a962a79adb9","observation_id":"bd3b7bc4-09d8-4a8a-9ea2-12d5dc2a2066","resolution":{"observed_at":"2026-08-03T09:02:57.146866Z","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":"2026-08-03T09:02:57.250877Z","title":"Neural relation extraction for knowledge base enrichment","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.250877Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:c4ac7f70bae560cd37cf0d580df7dae184cecac4c5ca017b09574fde6e0d4207","observation_id":"bdf461b7-abff-4471-b2b6-b8a95b9125c2","resolution":{"observed_at":"2026-08-03T09:02:57.250877Z","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":"2026-08-03T09:02:57.319147Z","title":"Talukdar","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.319147Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:6254d2c071ff0e675228fce6fe79d03cc77ded67559ead471f38ba45efe69a8a","observation_id":"a8f5115b-1cb8-4bb7-91cf-b0d05d8690f0","resolution":{"observed_at":"2026-08-03T09:02:57.319147Z","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":"2026-08-03T09:02:57.405554Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.405554Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:3ef1868af90111024ec178ff690e923728f223e3e3678826600e3ab4bc13cae3","observation_id":"97dddb0b-7e0f-46cd-8de2-ddfff0c59654","resolution":{"observed_at":"2026-08-03T09:02:57.405554Z","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":"2026-08-03T09:02:57.477730Z","title":"Tplinker: Single-stage joint extraction of entities and relations through token pair linking","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.477730Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:72d6db6406491874ab8a37b9fccc81cc6bcfe1985afb04884a24f5c2d13c1f67","observation_id":"f44fb66f-e1d7-4927-acd2-f7e3186b2a96","resolution":{"observed_at":"2026-08-03T09:02:57.477730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.02457","last_updated":"2023-08-04T16:49:54Z","snapshot_observed_at":"2026-08-03T21:39:56.945784Z","submitted_at":"2023-08-04T16:49:54Z","title":"A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.02457","snapshot_observed_at":"2026-08-03T09:02:57.577447Z","title":"A survey on temporal knowledge graph completion: Taxonomy, progress, and prospects","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.577447Z"},"links":{"cited_paper":"/paper/2308.02457","citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:0c4194a5dd04a6c0681baeecc188bc2632b83d2c7d4cc4859401cb07cedb1a31","observation_id":"655eabc1-80e9-4cfc-a0f1-395037ae3fbe","resolution":{"observed_at":"2026-08-03T09:02:57.577447Z","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":"2026-08-03T09:02:57.633542Z","title":"Ime: Integrating multi-curvature shared and specific embedding for temporal knowledge graph completion","venue":null,"work_id":null,"year":1954},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.633542Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:32dafcf07750e093a20836471a4d4227ab38d3c0460eebb889e3a298a0e9ebe0","observation_id":"3a833c7e-93ff-4bb3-9b56-b332dcd02be5","resolution":{"observed_at":"2026-08-03T09:02:57.633542Z","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":"2026-08-03T09:02:57.724512Z","title":"Large language models-guided dynamic adaptation for temporal knowledge graph reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.724512Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:840b4ea56a4ad199041ae7ca308676578cc2fd94b56c885e074e13ba2b3755f4","observation_id":"f9fd49cc-5682-4351-8f0e-a39644bd8fb4","resolution":{"observed_at":"2026-08-03T09:02:57.724512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.10205","last_updated":"2024-05-27T07:08:31Z","snapshot_observed_at":"2026-08-04T23:18:08.595429Z","submitted_at":"2023-02-20T12:57:12Z","title":"ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.10205","snapshot_observed_at":"2026-08-03T09:02:57.822452Z","title":"Zero-shot information extraction via chatting with chatgpt","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.822452Z"},"links":{"cited_paper":"/paper/2302.10205","citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:78aec6558a7394b3c251ec89796c69b250d5537e7374b7231debb56db39969a6","observation_id":"7bc022a2-60ca-49d4-9004-5d85f756af47","resolution":{"observed_at":"2026-08-03T09:02:57.822452Z","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":"2026-08-03T09:02:57.916649Z","title":"Explicit semantic ranking for academic search via knowledge graph embedding","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:57.916649Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:b50dcf005c67b7f5722745c9d4400934c09a764d4a93b965cd5bcf4afa4e7f68","observation_id":"5dbd8a64-0666-481b-90f4-39d05645a8f4","resolution":{"observed_at":"2026-08-03T09:02:57.916649Z","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":"2026-08-03T09:02:58.012174Z","title":"Large language models for generative information extraction: a survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.012174Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:79a5971e057df61e68742f4667aea50300dd95576d6bce68c79c3dc9e9209e83","observation_id":"818238d8-9351-4480-950b-e72b39ec80c9","resolution":{"observed_at":"2026-08-03T09:02:58.012174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.03409","last_updated":"2024-04-15T07:50:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-07T00:07:15Z","title":"Large Language Models as Optimizers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.03409","snapshot_observed_at":"2026-08-03T09:02:58.109440Z","title":"Le, Denny Zhou, and Xinyun Chen","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.109440Z"},"links":{"cited_paper":"/paper/2309.03409","citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:132bc81fe45c1a7ba4f497fbaed1d9f4aee67beb6175ad71437c13ddcea73af9","observation_id":"4bd794b1-3fbc-49d2-8be0-a2e6482c6b12","resolution":{"observed_at":"2026-08-03T09:02:58.109440Z","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":"2026-08-03T09:02:58.168522Z","title":"u ksekg \\","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.168522Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:8f5c9cc12c702e57c3b88cedacb785eb4b5a0f6c72ae06ffa2094c2111d355fe","observation_id":"7fc63274-2235-4bad-9453-da8b2f0331a7","resolution":{"observed_at":"2026-08-03T09:02:58.168522Z","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":"2026-08-03T09:02:58.294741Z","title":"Kernel methods for relation extraction","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.294741Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:fc19471c40e7b4f9f8e032bae0bc4f8e084cc461c4d3ac616572bae84116fe0a","observation_id":"8afcd9f3-b7c8-45c0-a16b-b3ffb36d7d56","resolution":{"observed_at":"2026-08-03T09:02:58.294741Z","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":"2026-08-03T09:02:58.364436Z","title":"Extract, define, canonicalize: An llm-based framework for knowledge graph construction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.364436Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:e31f0d9c32d68975a0efa722d37ef83d365325ab4e9a20cec5896d7c225c15d2","observation_id":"363cac16-a09e-4d67-b4e1-33d3211c7b9f","resolution":{"observed_at":"2026-08-03T09:02:58.364436Z","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":"2026-08-03T09:02:58.459625Z","title":"Smola, and Le Song","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.459625Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:7d2cd73d1ca6871cd3dfb89e7e02eb2844465a400b39c22410ac60210b70c13a","observation_id":"7157138e-1172-48d7-87c3-29bd606c85b0","resolution":{"observed_at":"2026-08-03T09:02:58.459625Z","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":"2026-08-03T09:02:58.580950Z","title":"Large language models are human-level prompt engineers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.580950Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:9008603e1c18f751764ae68e8e11724bd6c69d342abdb801bb7382255a8c31bb","observation_id":"937e7247-2f52-4d06-af92-bd4210e2e718","resolution":{"observed_at":"2026-08-03T09:02:58.580950Z","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":"2026-08-03T09:02:58.667022Z","title":"Llms for knowledge graph construction and reasoning: recent capabilities and future opportunities","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.667022Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:290bff4bced35ea338a730bc291cd065acb0fd0fd8bb8ee1e39298c470cd9606","observation_id":"1313dc85-4474-4fcc-ac10-7e8d29ce6c42","resolution":{"observed_at":"2026-08-03T09:02:58.667022Z","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":"2026-08-03T09:02:58.769177Z","title":"Geometric-contextual mutual infomax path aggregation for relation reasoning on knowledge graph","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.769177Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:e18f0b30c200dd47e2e41185d971a166438eb3ff768f55286e634dc14e738fef","observation_id":"5178031e-d1a0-476f-9273-da4d9f3f7139","resolution":{"observed_at":"2026-08-03T09:02:58.769177Z","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":"2026-08-03T09:02:58.869021Z","title":"Progressive prefix-memory tuning for complex logical query answering on knowledge graphs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.869021Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:c02240b931c13f7ae516c19a646019a58d9389b5a581e32522185cc439f6d7aa","observation_id":"584d5d01-d037-4387-9d27-394eff912f31","resolution":{"observed_at":"2026-08-03T09:02:58.869021Z","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":"2026-08-03T09:02:58.967470Z","title":"Effective instruction parsing plugin for complex logical query answering on knowledge graphs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:58.967470Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:e956a9f9fdd4eaf699a7ef96a7c3e0cfe31b88227b69a3ea23ecebe5a0caaa19","observation_id":"04105a25-130e-4039-a291-3879220b6c75","resolution":{"observed_at":"2026-08-03T09:02:58.967470Z","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":"2026-08-03T09:02:59.078398Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-03T09:02:59.078398Z"},"links":{"citing_paper":"/paper/2601.15037"},"observation_digest":"sha256:c688713deaca6d774a24b0a23782ff1c8d7e8c61e52eef0cb7b82f13b281ca16","observation_id":"2b88e711-7e66-453f-8a04-8db195f1d145","resolution":{"observed_at":"2026-08-03T09:02:59.078398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.15037","last_updated":"2026-07-31T12:08:10Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T21:08:01.683100Z","submitted_at":"2026-01-21T14:42:13Z","title":"Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":54,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":54},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2601.15037."}