{"as_of":"2026-08-10T12:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84bc22025dfb474c80be5de0283cdc781da860e2542a2d28266ed12ce944958e","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:21:22.761418Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T23:55:22.768635Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"cited_work":{"arxiv_id":"2505.22068","doi":"10.48550/arxiv.2505.22068","metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22068","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"ArXiv.org","work_id":"21bc93e4-c4a0-48d7-9718-c0f8ca40292e","year":2025},"citing_paper":{"arxiv_id":"2605.04221","last_updated":"2026-06-10T05:50:04Z","snapshot_observed_at":"2026-07-06T23:16:59.568304Z","submitted_at":"2026-05-05T19:03:40Z","title":"Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-08T17:22:17.266351Z"},"links":{"cited_paper":"/paper/2505.22068","citing_paper":"/paper/2605.04221"},"observation_digest":"sha256:301c65de88d8173536134a6a0e1f4af9680541a9891df7f8ad47e71d5ed64736","observation_id":"379a3b1b-3cb7-459c-a496-f166fe5ee36e","resolution":{"observed_at":"2026-05-08T17:23:40.406161Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"cited_work":{"arxiv_id":"2505.22068","doi":"10.48550/arxiv.2505.22068","metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22068","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"ArXiv.org","work_id":"21bc93e4-c4a0-48d7-9718-c0f8ca40292e","year":2025},"citing_paper":{"arxiv_id":"2605.04221","last_updated":"2026-06-10T05:50:04Z","snapshot_observed_at":"2026-07-06T23:16:59.568304Z","submitted_at":"2026-05-05T19:03:40Z","title":"Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-30T23:55:22.768635Z"},"links":{"cited_paper":"/paper/2505.22068","citing_paper":"/paper/2605.04221"},"observation_digest":"sha256:6703a5c3b5456a54987053c7c73531c76278fb238c709583064930e3c58bac18","observation_id":"39cf0a59-5e35-438d-ad03-c352d175247f","resolution":{"observed_at":"2026-07-01T00:05:09.456610Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.22068/citation-record","integrity":"/paper/2505.22068/integrity","json":"/paper/2505.22068/citation-record.json","paper":"/paper/2505.22068"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T13:21:17.851292Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:17.851292Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:9c931f9cdd26b886d63508a57c7e3b0248b7201562158ae43782027272f27661","observation_id":"6a3f8e2f-e06c-4db9-bbb2-c245ab96de2c","resolution":{"observed_at":"2026-08-07T13:21:17.851292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.05862","last_updated":"2022-04-12T15:02:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-12T15:02:38Z","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.05862","snapshot_observed_at":"2026-08-07T13:21:17.903852Z","title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:17.903852Z"},"links":{"cited_paper":"/paper/2204.05862","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:280535ad26b9d3a813f2dbf07383b2f2bfae9bda82c81ed5417c887529910138","observation_id":"bd80d493-37c2-40d9-a7a3-840cc16515a7","resolution":{"observed_at":"2026-08-07T13:21:17.903852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-07T22:56:16.858302Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-07T13:21:18.036986Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.036986Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:69659debaa4615916aa987fc02f643a0cf05e7489452330f61021b22948dd940","observation_id":"7ca393dc-3240-484f-820c-5427b2b5b067","resolution":{"observed_at":"2026-08-07T13:21:18.036986Z","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":"2026-08-07T13:21:25.382377Z","title":"Codekgc: Code language model for generative knowledge graph construction","venue":null,"work_id":"0ff7bdf4-3685-4b81-a244-646baac4496d","year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.113341Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:79d1fa5662c628e3f8d0fa75d5560de395874c72226d3c899d050cb59ce6222a","observation_id":"2341ff3e-793d-4a1a-aeab-6dc2b8133375","resolution":{"observed_at":"2026-08-07T13:21:25.448870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:21:18.211283Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.211283Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:73de8f5f6045594c5b4ca51081bea642d4cd4046fe3ce2baf00ae06925c41abe","observation_id":"04573047-e383-4f8b-ba2f-79c16b3468fd","resolution":{"observed_at":"2026-08-07T13:21:18.211283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17161","last_updated":"2025-05-26T17:16:45Z","snapshot_observed_at":"2026-08-09T18:26:12.869738Z","submitted_at":"2025-01-28T18:59:44Z","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17161","snapshot_observed_at":"2026-08-07T13:21:18.285802Z","title":"Sft memorizes, rl generalizes: A comparative study of foundation model post-training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.285802Z"},"links":{"cited_paper":"/paper/2501.17161","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:31cedbf9d71bb1d64662926e46ff3becf8642e16806ccced626a217fc9fa1be7","observation_id":"91bcd34b-8f7f-4b2b-8100-ea520b5399ba","resolution":{"observed_at":"2026-08-07T13:21:18.285802Z","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":"2026-08-07T13:21:18.365373Z","title":"Scaling instruction-finetuned language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.365373Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:e221d7c5330b33f3f912bd65af8ec7c9662ca9129aaca295cf0376092e90149a","observation_id":"e4e00c76-b301-4b5a-8b76-f579a794ac1b","resolution":{"observed_at":"2026-08-07T13:21:18.365373Z","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":"2026-08-07T13:21:25.254337Z","title":"Structured information extraction from scientific text with large language models","venue":null,"work_id":"4460d278-24bd-41a3-8f9a-c6e8cdb7c83b","year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.448507Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:901e38f3a8f1bcf6d1593381c4ae3bafa18efe79c2891628d58b29d04742b15e","observation_id":"ec74b80f-6946-4fc0-9d9b-e2ad5249f325","resolution":{"observed_at":"2026-08-07T13:21:25.317141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:21:25.077265Z","title":"Gemini 2.0 flash thinking„ 2024","venue":null,"work_id":"befbb206-f206-49c2-9a7d-e4689b26bc42","year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.541170Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:b5f181903c2784a6b7c27031395009f9e2c0d2c72f50f1355c13a1598a342fea","observation_id":"3ba9158f-3c1d-4e4f-913c-7d9c53c918b3","resolution":{"observed_at":"2026-08-07T13:21:25.139098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:21:18.697037Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.697037Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:49e2ac7b4b60ebfa07265fd489a3d840bb4e7dd57159a6b93fbcf3f6f1845fc8","observation_id":"81a27feb-74a8-4a7a-96fe-e8fb2f0c3392","resolution":{"observed_at":"2026-08-07T13:21:18.697037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06807","last_updated":"2025-02-18T22:21:40Z","snapshot_observed_at":"2026-08-09T14:06:29.234036Z","submitted_at":"2025-02-03T23:00:15Z","title":"Competitive Programming with Large Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06807","snapshot_observed_at":"2026-08-07T13:21:18.875663Z","title":"Competitive programming with large reasoning models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.875663Z"},"links":{"cited_paper":"/paper/2502.06807","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:a2744ee3e4a111ec38dc9a953743cbee7227565b0b8f4c08d7a25c1f0a06523c","observation_id":"13dec200-0d14-48b3-96be-be1c4cf7a765","resolution":{"observed_at":"2026-08-07T13:21:18.875663Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-08-07T13:21:18.994514Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.994514Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:df2b2355bfcd7af0f481f02e03a12d588a87786361aaa282f81368b8316a9431","observation_id":"7e0a3644-951e-467f-a446-214c0ebd8069","resolution":{"observed_at":"2026-08-07T13:21:18.994514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-07T13:21:19.081057Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.081057Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:b1b63277f82d1b470c6c27361b81dd98d9893883f5806a5200d696719baf6981","observation_id":"659cf4d1-57a4-4519-b01b-e0d923780aac","resolution":{"observed_at":"2026-08-07T13:21:19.081057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.15556","last_updated":"2022-03-29T13:38:03Z","snapshot_observed_at":"2026-08-09T19:52:33.533277Z","submitted_at":"2022-03-29T13:38:03Z","title":"Training Compute-Optimal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.15556","snapshot_observed_at":"2026-08-07T13:21:19.159809Z","title":"Training compute-optimal large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.159809Z"},"links":{"cited_paper":"/paper/2203.15556","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:fc2a69de6e717dbc086410e0b45a08e2af17bb33911d0e0596cd788d952d2a80","observation_id":"18924d5b-a9d3-469a-8511-f19d5b197149","resolution":{"observed_at":"2026-08-07T13:21:19.159809Z","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":"2026-08-07T13:21:19.256717Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.256717Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:264575567f27889365e8db0f6c5241cf5675b5bc88044241693f6841da070634","observation_id":"14e1bd0d-0391-4816-98b5-7065283ce54c","resolution":{"observed_at":"2026-08-07T13:21:19.256717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16720","last_updated":"2026-04-30T02:46:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-21T18:04:31Z","title":"OpenAI o1 System Card","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16720","snapshot_observed_at":"2026-08-07T13:21:19.379751Z","title":"Openai o1 system card","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.379751Z"},"links":{"cited_paper":"/paper/2412.16720","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:c083f5259491871f10afff22dac0e899f58b05bd37bb1dfd1eb02ae31b4757ed","observation_id":"2bad962b-a4c0-4032-b2cd-6819a4681f28","resolution":{"observed_at":"2026-08-07T13:21:19.379751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-07T13:21:19.424609Z","title":"Scaling laws for neural language models","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.424609Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:0ef4e8e4015c433da9d1c1cbaeedea72b6a6f612e7b945e5db839300bf625cad","observation_id":"40f1b00d-9b0b-4b32-9bbb-e9947080bd6a","resolution":{"observed_at":"2026-08-07T13:21:19.424609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.07374","last_updated":"2025-02-18T05:20:33Z","snapshot_observed_at":"2026-08-09T18:38:39.510086Z","submitted_at":"2025-02-11T08:48:48Z","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.07374","snapshot_observed_at":"2026-08-07T13:21:19.506483Z","title":"Llms can easily learn to rea- son from demonstrations structure, not content, is what matters!, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.506483Z"},"links":{"cited_paper":"/paper/2502.07374","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:1590f8af74d555c5ea8af17a5d5dc91c0e961e42a487f14b9d4467c8956ce17e","observation_id":"b38defa1-fe24-4b5c-a4d9-92b76c4a108d","resolution":{"observed_at":"2026-08-07T13:21:19.506483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05028","last_updated":"2023-11-24T14:34:57Z","snapshot_observed_at":"2026-08-10T00:58:15.106733Z","submitted_at":"2023-10-08T06:17:39Z","title":"Revisiting Large Language Models as Zero-shot Relation Extractors","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05028","snapshot_observed_at":"2026-08-07T13:21:19.586236Z","title":"Revisiting large language models as zero-shot relation extractors","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.586236Z"},"links":{"cited_paper":"/paper/2310.05028","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:ce524b5b357ba19a0638f0b4078be81b83a1e3326fabd290ea65b656268b4667","observation_id":"de0020d1-3bd6-4cf7-8a3d-535e121a91a9","resolution":{"observed_at":"2026-08-07T13:21:19.586236Z","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":"2026-08-07T13:21:24.914804Z","title":"Getting more juice out of the sft data: Reward learning from human demonstration improves sft for llm alignment","venue":null,"work_id":"72c1103e-38c1-41c2-802d-f177b00f795a","year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.724379Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:4d15fbb65a0e9f624d597b37b45144a292fc6d13dc95225fd64e4fabaa53ea0e","observation_id":"c03ba290-79dc-4038-b887-e61deeb04c8c","resolution":{"observed_at":"2026-08-07T13:21:24.994412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14898","last_updated":"2023-05-24T08:52:08Z","snapshot_observed_at":"2026-08-06T01:22:40.764443Z","submitted_at":"2023-05-24T08:52:08Z","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","version":1},"cited_work":{"arxiv_id":"2305.14898","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.14898","snapshot_observed_at":"2026-08-07T13:21:23.746125Z","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","venue":"cs.CL","work_id":"19ed3ba3-b4e5-407a-bbca-8f2d2de7c9c1","year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.779256Z"},"links":{"cited_paper":"/paper/2305.14898","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:01b24eb2a9c2c45922e9828c0d58d09d127ab67c13b885197d2af63f4d9ced7c","observation_id":"49c73c6d-ccb6-4c18-916d-4f0226acd760","resolution":{"observed_at":"2026-08-07T13:21:23.850092Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06861","last_updated":"2024-10-06T03:40:58Z","snapshot_observed_at":"2026-07-06T17:28:18.945477Z","submitted_at":"2024-02-10T01:50:19Z","title":"UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06861","snapshot_observed_at":"2026-08-07T13:21:19.858040Z","title":"Urbankgent: A unified large language model agent framework for urban knowledge graph construction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.858040Z"},"links":{"cited_paper":"/paper/2402.06861","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:50be97128bd3db900fcbcdf0923889d1d4c6b8e725ca271862beeb20d18ac6b6","observation_id":"2f81de1e-9824-4510-89c4-b7fe78a72d13","resolution":{"observed_at":"2026-08-07T13:21:19.858040Z","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":"2026-08-07T13:21:24.707730Z","title":"Using of jaccard coefficient for keywords similarity","venue":null,"work_id":"3c4046d0-4ff5-4e70-90f7-0f5d9d9c8983","year":2013},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:19.969120Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:0ea974531d8f95acfcac5e5d6d2413b5afd69ec88f65cac13ff8736d82984f34","observation_id":"eae0750a-8d9d-4174-8624-7ca4861b8292","resolution":{"observed_at":"2026-08-07T13:21:24.800576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:21:20.115279Z","title":"Training language models to follow instructions with human feedback","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.115279Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:9af9b732045019f8baa52b1e9fc277f6f3006886d9cd3f78835acc6900d408e4","observation_id":"2ec4d59b-088c-48a0-a96d-203b6f570785","resolution":{"observed_at":"2026-08-07T13:21:20.115279Z","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":"2026-08-07T13:21:20.160573Z","title":"Improving language understanding by generative pre-training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.160573Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:98452da7700769ec2c8305a27d1c2ba763fbe33c1e4415050432f3545d9923fa","observation_id":"304425f7-a6b1-4abe-935a-c3b3cf361ed0","resolution":{"observed_at":"2026-08-07T13:21:20.160573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-07T13:21:20.300576Z","title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.300576Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:92854402c5be34bce689173e8381486d6cdd39bf45b984ae700327a74ef3b708","observation_id":"cc743bff-5d00-479f-ba35-297247534e6f","resolution":{"observed_at":"2026-08-07T13:21:20.300576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12183","last_updated":"2025-05-07T18:00:45Z","snapshot_observed_at":"2026-08-01T16:38:42.947080Z","submitted_at":"2024-09-18T17:55:00Z","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12183","snapshot_observed_at":"2026-08-07T13:21:20.484755Z","title":"To cot or not to cot? chain- of-thought helps mainly on math and symbolic reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.484755Z"},"links":{"cited_paper":"/paper/2409.12183","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:b164e43face07637a94b8a170935971ef061e4ac28248fe6b072febae3104126","observation_id":"c824a449-c453-44d9-a3ce-d7b91e5650fd","resolution":{"observed_at":"2026-08-07T13:21:20.484755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05530","last_updated":"2024-12-16T17:39:39Z","snapshot_observed_at":"2026-07-06T17:41:42.995949Z","submitted_at":"2024-03-08T18:54:20Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05530","snapshot_observed_at":"2026-08-07T13:21:20.594132Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.594132Z"},"links":{"cited_paper":"/paper/2403.05530","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:a3f48b826d2339918896502081b81276ed2681e5a3e9fa24e2a39a983f6e522d","observation_id":"a7c92e83-a342-43c9-a744-63c7090173fc","resolution":{"observed_at":"2026-08-07T13:21:20.594132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T13:21:20.690010Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.690010Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:c7986f35fcc743cb73b3ef684af91a9385cc3365c4e2e5518ecd79af56ea312a","observation_id":"8b204b30-57b2-4336-b42c-8b91c747260d","resolution":{"observed_at":"2026-08-07T13:21:20.690010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10428","last_updated":"2023-10-07T14:25:28Z","snapshot_observed_at":"2026-07-06T15:17:59.640907Z","submitted_at":"2023-04-20T16:17:26Z","title":"GPT-NER: Named Entity Recognition via Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10428","snapshot_observed_at":"2026-08-07T13:21:20.801599Z","title":"Gpt-ner: Named entity recognition via large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.801599Z"},"links":{"cited_paper":"/paper/2304.10428","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:d88fd1736f9bcd663a9dcdc4baee652d616fbb9cb7ec8d6dfcafa1919bfdd705","observation_id":"f2ab7f53-c5b5-4531-a70a-238b91a2991d","resolution":{"observed_at":"2026-08-07T13:21:20.801599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.01652","last_updated":"2022-02-08T20:26:45Z","snapshot_observed_at":"2026-08-10T07:52:08.606999Z","submitted_at":"2021-09-03T17:55:52Z","title":"Finetuned Language Models Are Zero-Shot Learners","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.01652","snapshot_observed_at":"2026-08-07T13:21:20.884237Z","title":"Finetuned language models are zero-shot learners","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.884237Z"},"links":{"cited_paper":"/paper/2109.01652","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:e896f9947c00789f240e33d5c50f7489c714fb65c15e4f7049c804c0a757ba26","observation_id":"dfe30051-4830-412b-9905-500de8302b9f","resolution":{"observed_at":"2026-08-07T13:21:20.884237Z","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":"2026-08-07T13:21:20.933984Z","title":"Chain-of-thought prompting elicits reasoning in large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.933984Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:4f846defa3c531e117a0b4cf47a540815e50ea8f42513e8e7a528405d90e3934","observation_id":"89187d1d-459b-4500-8d96-c63e4c9c971e","resolution":{"observed_at":"2026-08-07T13:21:20.933984Z","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":"2026-08-07T13:21:24.475863Z","title":"Zero-shot information extraction via chatting with chatgpt","venue":null,"work_id":"53cfcd7f-9b18-44be-9fb1-e45c53f8d802","year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:20.982314Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:a07275b1e1c0e3d1ba7c53d3c70de4a992d7e5e8a818f1d61b839942cb279775","observation_id":"ad9faa9e-cd34-4d34-904b-355b0f3a2737","resolution":{"observed_at":"2026-08-07T13:21:24.572520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10035","last_updated":"2023-10-16T03:40:03Z","snapshot_observed_at":"2026-08-10T09:56:17.662991Z","submitted_at":"2023-10-16T03:40:03Z","title":"Empirical Study of Zero-Shot NER with ChatGPT","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10035","snapshot_observed_at":"2026-08-07T13:21:21.117394Z","title":"Empirical study of zero-shot ner with chatgpt","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:21.117394Z"},"links":{"cited_paper":"/paper/2310.10035","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:3a1eebceaf226fc2d4608b288db482f886bb5178730736fa2af535baeb80d0b5","observation_id":"4c3fc912-cc2d-400e-a067-ef65e08273f8","resolution":{"observed_at":"2026-08-07T13:21:21.117394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17238","last_updated":"2023-10-26T08:36:39Z","snapshot_observed_at":"2026-08-01T18:02:29.637964Z","submitted_at":"2023-10-26T08:36:39Z","title":"Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks","version":1},"cited_work":{"arxiv_id":"2310.17238","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.17238","snapshot_observed_at":"2026-08-07T13:21:23.366916Z","title":"Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks","venue":"cs.CL","work_id":"789c9972-c0f1-4d42-b08d-39ea68d3aad5","year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:21.251678Z"},"links":{"cited_paper":"/paper/2310.17238","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:c47dd2dd4873a1b6d942446b85393f8f1a80e98c044ba574edd420d0f9c4ccd1","observation_id":"469f9c16-5ca2-4258-b505-8119ebb9e897","resolution":{"observed_at":"2026-08-07T13:21:23.469358Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T13:21:21.405550Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:21.405550Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:bdb6706385749bfe00f1fdbc37d8c24ed8ed59135289a5c209a7363eddd835ae","observation_id":"94710506-682a-4d63-a2c8-038793012fe6","resolution":{"observed_at":"2026-08-07T13:21:21.405550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.06067","last_updated":"2022-04-21T03:34:39Z","snapshot_observed_at":"2026-07-06T11:47:13.744987Z","submitted_at":"2021-09-13T15:38:13Z","title":"Packed Levitated Marker for Entity and Relation Extraction","version":5},"cited_work":{"arxiv_id":"2109.06067","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.06067","snapshot_observed_at":"2026-08-07T13:21:23.082334Z","title":"Packed Levitated Marker for Entity and Relation Extraction","venue":"cs.CL","work_id":"2a63887b-bf2f-4ebe-bbd3-df905382858f","year":2021},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:21.507010Z"},"links":{"cited_paper":"/paper/2109.06067","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:542c8b511917d378edbbb09c6cefc1d66ec40c72c08fd25ea6d6591e66bae432","observation_id":"be3678c0-6e28-485d-ad37-e37290279a75","resolution":{"observed_at":"2026-08-07T13:21:23.216161Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05454","last_updated":"2023-04-11T18:59:05Z","snapshot_observed_at":"2026-08-09T16:04:38.122829Z","submitted_at":"2023-04-11T18:59:05Z","title":"Zero-shot Temporal Relation Extraction with ChatGPT","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.05454","snapshot_observed_at":"2026-08-07T13:21:21.628275Z","title":"Zero-shot temporal relation extraction with chatgpt","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:21.628275Z"},"links":{"cited_paper":"/paper/2304.05454","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:46f75afd12dd30e128187f8c744d4ac9bc5da4ae79772a7587d480116e437681","observation_id":"9416ed9f-94b8-45ed-b018-00746d59ec93","resolution":{"observed_at":"2026-08-07T13:21:21.628275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13837","last_updated":"2025-11-24T06:11:04Z","snapshot_observed_at":"2026-07-06T21:11:34.701779Z","submitted_at":"2025-04-18T17:59:56Z","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13837","snapshot_observed_at":"2026-08-07T13:21:21.782500Z","title":"Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? arXiv preprint arXiv:2504.13837, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:21.782500Z"},"links":{"cited_paper":"/paper/2504.13837","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:2f103f05982a594cdf85d3277b14b34811009e977982a40509ce7a2a0423f181","observation_id":"537790ab-e959-47b1-a1d6-793e495383ce","resolution":{"observed_at":"2026-08-07T13:21:21.782500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.03868","last_updated":"2024-10-02T05:51:53Z","snapshot_observed_at":"2026-08-04T23:51:09.010085Z","submitted_at":"2024-04-05T02:53:51Z","title":"Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.03868","snapshot_observed_at":"2026-08-07T13:21:21.935101Z","title":"Extract, define, canonicalize: An llm-based framework for knowledge graph construction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:21.935101Z"},"links":{"cited_paper":"/paper/2404.03868","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:91c535f9fa158ca4e7b3951295a74ae9a2e4c10fbed9fe46ba6a3cfba3274222","observation_id":"c11297b3-5917-4986-b901-15f9389e2c79","resolution":{"observed_at":"2026-08-07T13:21:21.935101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21155","last_updated":"2024-10-28T15:56:49Z","snapshot_observed_at":"2026-08-10T10:17:25.254341Z","submitted_at":"2024-10-28T15:56:49Z","title":"SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21155","snapshot_observed_at":"2026-08-07T13:21:22.082131Z","title":"Scier: An entity and relation extraction dataset for datasets, methods, and tasks in scientific documents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:22.082131Z"},"links":{"cited_paper":"/paper/2410.21155","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:8e0e7576e0466a1a917344fa0dd68aae97ddef9d4db11bc7186d692c589720e7","observation_id":"5bab54fc-8d2f-4db2-a277-40f68e025fa1","resolution":{"observed_at":"2026-08-07T13:21:22.082131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01068","snapshot_observed_at":"2026-08-07T13:21:22.266304Z","title":"Opt: Open pre-trained transformer language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:22.266304Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:9618facfa7c25fdb71e2fe1a7d75a7d4337f93cb29e2c46e7ddb6ada89274d66","observation_id":"b2387e02-6315-423f-abc3-671ea91c3574","resolution":{"observed_at":"2026-08-07T13:21:22.266304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.12812","last_updated":"2021-03-23T17:48:35Z","snapshot_observed_at":"2026-07-06T10:08:08.004416Z","submitted_at":"2020-10-24T07:14:01Z","title":"A Frustratingly Easy Approach for Entity and Relation Extraction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.12812","snapshot_observed_at":"2026-08-07T13:21:22.412626Z","title":"A frustratingly easy approach for joint entity and relation extraction","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:22.412626Z"},"links":{"cited_paper":"/paper/2010.12812","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:e9fc94a20cbe13803ddcc70fd4fd53368bf8e306034d90861631956b195ebce9","observation_id":"5e0fcd4c-b3a7-4634-a343-f3a26e281a97","resolution":{"observed_at":"2026-08-07T13:21:22.412626Z","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":"2026-08-07T13:21:22.522467Z","title":"Lima: Less is more for alignment","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:22.522467Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:734260a794505753cce98730e6ca37cce7350b255d4c2fde2cd5ddb8e9200480","observation_id":"08bb0454-2613-47ab-b291-42997fe354c4","resolution":{"observed_at":"2026-08-07T13:21:22.522467Z","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":"2026-08-07T13:21:24.180287Z","title":"Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities","venue":null,"work_id":"8d662f72-ff5a-4cd3-9d3c-19c550bc6af7","year":2024},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:22.613541Z"},"links":{"citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:ea13029e633f67929071f9878d6aa8bde93129e40c7535248f07d24501b9b070","observation_id":"7ad69383-1424-49d8-88f5-4444be72447c","resolution":{"observed_at":"2026-08-07T13:21:24.323264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08593","last_updated":"2020-01-08T23:02:36Z","snapshot_observed_at":"2026-08-08T07:44:49.921146Z","submitted_at":"2019-09-18T17:33:39Z","title":"Fine-Tuning Language Models from Human Preferences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.08593","snapshot_observed_at":"2026-08-07T13:21:22.761418Z","title":"factual, content-bearing","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:22.761418Z"},"links":{"cited_paper":"/paper/1909.08593","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:9a9d2b29e9bc85b9b3b0da9bff96a769478a605540e3d0e900e9a2e6d8248738","observation_id":"273102a3-d6ec-4b48-a481-b753e4ab3b7e","resolution":{"observed_at":"2026-08-07T13:21:22.761418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T13:13:34.125452Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":3,"verified_fuzzy":7},"total_outbound_references":46},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 2 inbound Pith citation observations for arXiv:2505.22068."}