{"work":{"id":"b6ace3ad-bd44-4a95-86ee-c7b73bd4cda2","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:c0b777c8bcc2b704cd636bee","title":"write newline","authors":null,"authors_text":"\" write newline \"\" before","year":null,"venue":null,"abstract":null,"external_url":null,"cited_by_count":null,"metadata_source":"raw_reference","metadata_fetched_at":"2026-05-27T10:03:55.922576+00:00","pith_arxiv_id":null,"created_at":"2026-05-13T20:48:16.105531+00:00","updated_at":"2026-05-27T10:03:55.922576+00:00","title_quality_ok":false,"display_title":"write newline","render_title":"write newline"},"hub":{"state":{"work_id":"b6ace3ad-bd44-4a95-86ee-c7b73bd4cda2","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":192,"external_cited_by_count":null,"distinct_field_count":13,"first_pith_cited_at":"2024-04-02T17:49:40+00:00","last_pith_cited_at":"2026-04-30T10:08:35+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-27T21:37:56.407502+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":9},{"context_role":"other","n":5},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":8},{"context_polarity":"unclear","n":6},{"context_polarity":"use_method","n":2}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"write newline","claims":[{"claim_text":"3Zhejiang University, Hangzhou, China, 4Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, guoyanl@zju.edu.cn Abstract Recent reinforcement learning (RL) ap- proaches have advanced radiology report gen- eration (RRG), yet two core limitations per- sist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faith- fulness; and (2) current methods lack an explicit self-improving mechanism to align with clinical preference. We introduce clini- cal","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Figure 3: Framework of DAID. DAID dynamically identifies dual-anchor layers guided by the visual attention and calibrates the final output by leveraging both the Spotlight and Shadow anchors to ensure visual grounding. we identify the positive anchor (Spotlight layer) as the layer exhibiting maximum visual grounding: Lt spot. = argmax l∈{1,...,L} V ASt(l).(2) By anchoring to Lt spot., we retrieve authentic visual details that are otherwise diluted in the final layers. Shadow Anchor: Visual Agnos","claim_type":"other","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"allgold passages and penalizes partial recovery proportionally. Bridge-comparison queries.A query isbridge- comparisonifg 2 is only weakly aligned withqbut strongly aligned with the entity resolved byg 1. Formally, letb ∗ be the ideal bridge (the passage that resolves the intermediate entity). Define the chain-disambiguation gap ∆(q, b∗, c) =sim(q, c)−sim(q⊕b ∗, c),(2) whereq⊕b ∗ denotes the joint context. On bridge- comparison queries,∆(q, b ∗, g2)<0: condition- ing on the bridge lifts the gold","claim_type":"other","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"from the MetFuse dataset. Each annotator was provided with a sample and asked to rate the fig- urative texts on a scale of 1 to 5, with the literal sentences as references. We used four criteria from Chakrabarty et al. (2021), in addition to one of ours: (1)Fluency(\"How fluent, grammatical, well formed and easy to understand are the generated utterances?\"), (2)Meaning(\"Are the input and the output referring or meaning the same thing?\") (3) Creativity(\"How creative are the generated utter- ances?","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"notated with model assistance rather than taken from public datasets. We also build a complete workflow integrating data annotation, evaluation metrics, and structured assessment, making Tax- PraBen scalable. Following Bloom's taxonomy of cognitive skills (Fei et al., 2024; Chen et al., 2025), we divide the tasks into three groups: (1)Knowl- edge Memorization, (2)Knowledge Understanding, and (3)Knowledge Application. Evaluating 19 representative general LLMs on TaxPraBen yields the following res","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"To achieve realistic simulation, we buildCus- tomerLM, a specialized user simulator trained on 8,000+ crowdworker dialogues using SFT and DPO (Brown et al., 2020; Rafailov et al., 2023), addressing formal language bias and role confusion in general-purpose simulators. Our contributions include: (1) SalesLLM bench- mark, a benchmark with 1,805 multi-turn scenarios in Chinese and English; (2) CustomerLM, a real- istic user simulator reducing role inversion; (3) an automated dual-scoring framework ","claim_type":"method","confidence":0.75,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks write newline because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (9 contexts).","role_counts":[{"n":9,"context_role":"background"},{"n":5,"context_role":"other"},{"n":2,"context_role":"method"}]},"error":null,"updated_at":"2026-05-19T05:51:31.819555+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"ac6873e2-34b6-473a-8aae-6009abdcfe0e","orcid":null,"display_name":"\" write newline \"\" before"}]},"error":null,"updated_at":"2026-05-19T05:51:33.840905+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-17T09:49:45.422162+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"online\" 'onlinestring :=","work_id":"38c07273-5071-4bbb-b2af-067af11becc7","shared_citers":45},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":17},{"title":"Qwen2.5 Technical Report","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","shared_citers":8},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":6},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":6},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":6},{"title":"Bleu: a method for automatic evaluation of machine translation","work_id":"7a0e7f56-7c92-470e-b7bf-2e9974bf9a93","shared_citers":5},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":5},{"title":"Gemma 3 Technical Report","work_id":"f93e08bf-9e96-409b-8ac6-b8385fd17fd7","shared_citers":5},{"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","shared_citers":5},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":5},{"title":"online\" 'onlinestring :=","work_id":"f969ad36-6879-4127-aa9a-2fab0f2ec82b","shared_citers":5},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":5},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":4},{"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","shared_citers":4},{"title":"Hellaswag: Can a machine really finish your sentence? In Korhonen, A., Traum, D., and M \\`a rquez, L","work_id":"11bfc949-547c-40f3-a86d-953eb9b2154c","shared_citers":4},{"title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","work_id":"9d86da8d-01d3-41af-a0d2-ee14897927a9","shared_citers":4},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":4},{"title":"Qwen2 Technical Report","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","shared_citers":4},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":4},{"title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","shared_citers":4},{"title":null,"work_id":"d715ff4d-f31d-49cf-bf54-8217373c5c82","shared_citers":4},{"title":"BERTScore: Evaluating Text Generation with BERT","work_id":"9eaaaac1-0a96-4f5f-9b13-30c46e9e1346","shared_citers":3}],"time_series":[{"n":11,"year":2025},{"n":39,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-17T09:49:42.333827+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-17T09:49:49.528926+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"write newline","claims":[{"claim_text":"3Zhejiang University, Hangzhou, China, 4Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, guoyanl@zju.edu.cn Abstract Recent reinforcement learning (RL) ap- proaches have advanced radiology report gen- eration (RRG), yet two core limitations per- sist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faith- fulness; and (2) current methods lack an explicit self-improving mechanism to align with clinical preference. We introduce clini- cal","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Figure 3: Framework of DAID. DAID dynamically identifies dual-anchor layers guided by the visual attention and calibrates the final output by leveraging both the Spotlight and Shadow anchors to ensure visual grounding. we identify the positive anchor (Spotlight layer) as the layer exhibiting maximum visual grounding: Lt spot. = argmax l∈{1,...,L} V ASt(l).(2) By anchoring to Lt spot., we retrieve authentic visual details that are otherwise diluted in the final layers. Shadow Anchor: Visual Agnos","claim_type":"other","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"allgold passages and penalizes partial recovery proportionally. Bridge-comparison queries.A query isbridge- comparisonifg 2 is only weakly aligned withqbut strongly aligned with the entity resolved byg 1. Formally, letb ∗ be the ideal bridge (the passage that resolves the intermediate entity). Define the chain-disambiguation gap ∆(q, b∗, c) =sim(q, c)−sim(q⊕b ∗, c),(2) whereq⊕b ∗ denotes the joint context. On bridge- comparison queries,∆(q, b ∗, g2)<0: condition- ing on the bridge lifts the gold","claim_type":"other","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"from the MetFuse dataset. Each annotator was provided with a sample and asked to rate the fig- urative texts on a scale of 1 to 5, with the literal sentences as references. We used four criteria from Chakrabarty et al. (2021), in addition to one of ours: (1)Fluency(\"How fluent, grammatical, well formed and easy to understand are the generated utterances?\"), (2)Meaning(\"Are the input and the output referring or meaning the same thing?\") (3) Creativity(\"How creative are the generated utter- ances?","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"notated with model assistance rather than taken from public datasets. We also build a complete workflow integrating data annotation, evaluation metrics, and structured assessment, making Tax- PraBen scalable. Following Bloom's taxonomy of cognitive skills (Fei et al., 2024; Chen et al., 2025), we divide the tasks into three groups: (1)Knowl- edge Memorization, (2)Knowledge Understanding, and (3)Knowledge Application. Evaluating 19 representative general LLMs on TaxPraBen yields the following res","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"To achieve realistic simulation, we buildCus- tomerLM, a specialized user simulator trained on 8,000+ crowdworker dialogues using SFT and DPO (Brown et al., 2020; Rafailov et al., 2023), addressing formal language bias and role confusion in general-purpose simulators. Our contributions include: (1) SalesLLM bench- mark, a benchmark with 1,805 multi-turn scenarios in Chinese and English; (2) CustomerLM, a real- istic user simulator reducing role inversion; (3) an automated dual-scoring framework ","claim_type":"method","confidence":0.75,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks write newline because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (9 contexts).","role_counts":[{"n":9,"context_role":"background"},{"n":5,"context_role":"other"},{"n":2,"context_role":"method"}]},"error":null,"updated_at":"2026-05-19T05:51:33.846174+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"write newline","claims":[{"claim_text":"Flesch-Kincaid Grade Level 8.97 9.08 -0.11 -0.1673 -0.1528 Table 5: Textual complexity metrics and their correlation with frequency. Corr. denotes correlation. We use nlp = spacy.load(\"en_core_web_sm\") for calculation. Bin Range N BLEU(HF) BLEU(LF)∆BLEU(HF-LF) chrF(HF) chrF(LF)∆chrF(HF-LF) Strict Depth Match 144 20.82 16.04 +4.78 48.73 43.86 +4.87 [0%,5%) 144 20.82 16.04 +4.78 48.73 43.86 +4.87 [5%,10%) 6 22.45 14.79 +7.65 49.76 49.19 +0.57 [10%,15%) 71 19.12 15.38 +3.74 46.19 44.71 +1.47 [15%,2","claim_type":"background","confidence":0.7,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks write newline because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (1 contexts).","role_counts":[{"n":1,"context_role":"background"}]},"error":null,"updated_at":"2026-05-17T09:49:49.533069+00:00"}},"summary":{"title":"write newline","claims":[{"claim_text":"Flesch-Kincaid Grade Level 8.97 9.08 -0.11 -0.1673 -0.1528 Table 5: Textual complexity metrics and their correlation with frequency. Corr. denotes correlation. We use nlp = spacy.load(\"en_core_web_sm\") for calculation. Bin Range N BLEU(HF) BLEU(LF)∆BLEU(HF-LF) chrF(HF) chrF(LF)∆chrF(HF-LF) Strict Depth Match 144 20.82 16.04 +4.78 48.73 43.86 +4.87 [0%,5%) 144 20.82 16.04 +4.78 48.73 43.86 +4.87 [5%,10%) 6 22.45 14.79 +7.65 49.76 49.19 +0.57 [10%,15%) 71 19.12 15.38 +3.74 46.19 44.71 +1.47 [15%,2","claim_type":"background","confidence":0.7,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks write newline because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (1 contexts).","role_counts":[{"n":1,"context_role":"background"}]},"graph":{"co_cited":[{"title":"online\" 'onlinestring :=","work_id":"38c07273-5071-4bbb-b2af-067af11becc7","shared_citers":45},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":17},{"title":"Qwen2.5 Technical Report","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","shared_citers":8},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":6},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":6},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":6},{"title":"Bleu: a method for automatic evaluation of machine translation","work_id":"7a0e7f56-7c92-470e-b7bf-2e9974bf9a93","shared_citers":5},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":5},{"title":"Gemma 3 Technical Report","work_id":"f93e08bf-9e96-409b-8ac6-b8385fd17fd7","shared_citers":5},{"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","shared_citers":5},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":5},{"title":"online\" 'onlinestring :=","work_id":"f969ad36-6879-4127-aa9a-2fab0f2ec82b","shared_citers":5},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":5},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":4},{"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","shared_citers":4},{"title":"Hellaswag: Can a machine really finish your sentence? In Korhonen, A., Traum, D., and M \\`a rquez, L","work_id":"11bfc949-547c-40f3-a86d-953eb9b2154c","shared_citers":4},{"title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","work_id":"9d86da8d-01d3-41af-a0d2-ee14897927a9","shared_citers":4},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":4},{"title":"Qwen2 Technical Report","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","shared_citers":4},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":4},{"title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","shared_citers":4},{"title":null,"work_id":"d715ff4d-f31d-49cf-bf54-8217373c5c82","shared_citers":4},{"title":"BERTScore: Evaluating Text Generation with BERT","work_id":"9eaaaac1-0a96-4f5f-9b13-30c46e9e1346","shared_citers":3}],"time_series":[{"n":11,"year":2025},{"n":39,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"ac6873e2-34b6-473a-8aae-6009abdcfe0e","orcid":null,"display_name":"\" write newline \"\" before","source":"manual","import_confidence":0.72}]}}