{"work":{"id":"75f57f43-cb6d-44a9-9cc5-9b8cfc702ea3","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:7dd2695b15ce098924caa955","title":"Tetreault , title =","authors":null,"authors_text":"Mohammad Sadegh Rasooli and Joel R","year":2015,"venue":null,"abstract":null,"external_url":null,"cited_by_count":null,"metadata_source":"raw_reference","metadata_fetched_at":"2026-05-27T02:38:25.620397+00:00","pith_arxiv_id":null,"created_at":"2026-05-12T03:33:46.027220+00:00","updated_at":"2026-05-27T02:38:25.620397+00:00","title_quality_ok":false,"display_title":"Tetreault , title =","render_title":"Tetreault , title ="},"hub":{"state":{"work_id":"75f57f43-cb6d-44a9-9cc5-9b8cfc702ea3","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":128,"external_cited_by_count":null,"distinct_field_count":15,"first_pith_cited_at":"2021-09-02T12:21:06+00:00","last_pith_cited_at":"2026-05-22T02:53:12+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":"2026-06-04T06:47:18.529827+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":7},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"unclear","n":4}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Tetreault , title =","claims":[{"claim_text":"comment-reply dataset for (dis) agreement detection in online debates. InThirty-fifth conference on neural information processing systems datasets and bench- marks track (round 2). Miklos Z Rácz and Daniel E Rigobon. 2023. Towards consensus: Reducing polarization by perturbing so- cial networks.IEEE Transactions on Network Sci- ence and Engineering, 10(6):3450-3464. ZP Rosen and Rick Dale. 2025. Antisemitic and islamophobic hate speech precedes a decrease in lexico-semantic diversity in comment ","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"2005. Ha- hacronym: A computational humor system. InPro- ceedings of the ACL Interactive Poster and Demon- stration Sessions, pages 113-116. David Tomás, Reynier Ortega-Bueno, Guobiao Zhang, Paolo Rosso, and Rossano Schifanella. 2023. Transformer-based models for multimodal irony de- tection.Journal of Ambient Intelligence and Human- ized Computing, 14(6):7399-7410. Robert West and Eric Horvitz. 2019. Reverse- engineering satire, or \"paper on computational hu- mor accepted despite making serious","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"We define N scales with two adapter sets: G= {G1, . . . ,GN } (MGFA) and C={C 1, . . . ,CN } (MCFA). At each scale n, features are reshaped to a grid X (0) v ∈R H×W×D v and downsampled by Down(·,2 n−1): X (n) v = Down(X(0) v ,2 n−1).(4) Let Xv,n = Seq(X (n) v ) denote the flattened se- quence. We then refine and fuse: Gn =G n(Xv,n), C n =C n(Xv,n, Xt),(5) ˜Xv,n =G n +w C n,(6) where w balances global and cross-modal adapta- tion. An interleave-repeat upsampling restores the (a) MGFA Module. (b) ","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"Householder mean-direction alignment.The nuisance mean-direction difference is removed by mapping the sample mean direction of X onto that of Y via Householder reflection. Let ¯x= 1 n Pn i=1 xi, ¯y= 1 m Pm j=1 yj, ˆµx = ¯x ∥¯x∥2 , ˆµy = ¯y ∥¯y∥2 . If ˆµx ̸= ˆµy, the Householder axis is defined as u= ˆµx − ˆµy ∥ˆµx − ˆµy∥2 ,(5) and the reflection matrix is H=I−2uu ⊤,(6) which satisfies Hˆµx = ˆµy and H⊤H=I . We then alignXby applyingHto every vector inX: x′ i =Hx i (i= 1, . . . , n),(7) and Y is ","claim_type":"background","confidence":0.7,"evidence_strength":"citation_context"},{"claim_text":"t→1 as the query requires more changes, thus (1−t)→1 as the query increases in accuracy. 3.6 Query Mutation Given the mutation temperaturet and assessment A from the critic, the original candidate QC is then rewritten via LLMmutate, which is prompted to produce an updated query candidate QC′ that in- corporates the changes recommended by the critic: QC′ =LLM mutate(Q, S′ i, QC, H, A, t)(6) We consider a single refinement step to consist of a call to the critic, followed by a subsequent call to t","claim_type":"other","confidence":0.6,"evidence_strength":"citation_context"},{"claim_text":"contribution of Q and P without the CoT rationale. Correspondingly, al no-CoT represents the attention activation excluding CoT. The additional term WV R(WKR)T q represents the contribution of the CoT rationale R to the hid- den activation. We can get the hidden activation by transforming the attention activation by a non- linear functionf: hl ≈h l no-CoT +f \u0010 WV R(WKR)T q \u0011 (7) Thus, we conclude that the rationale R in the CoT primarily contributes a shift in hidden acti- vation values, emphasi","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Tetreault , title = because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (7 contexts).","role_counts":[{"n":7,"context_role":"background"},{"n":1,"context_role":"other"}]},"error":null,"updated_at":"2026-05-23T11:14:30.522832+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"ba76245f-e388-4491-89be-9beb764793e1","orcid":null,"display_name":"Mohammad Sadegh Rasooli and Joel R"}]},"error":null,"updated_at":"2026-05-23T11:14:31.330262+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-21T05:32:40.519857+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":null,"work_id":"852d89f5-1e7b-4296-b4f2-71e578b5e9f6","shared_citers":58},{"title":"Chandra and Dexter C","work_id":"c3270592-bd69-4213-95e1-4aaf8312be9b","shared_citers":56},{"title":null,"work_id":"aca2b566-99e0-4ebb-9c7a-a81219531259","shared_citers":55},{"title":"A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =","work_id":"6d196829-7173-4c45-aa5c-d0ee30947345","shared_citers":54},{"title":"Aho and Jeffrey D","work_id":"b1f5cb43-a3c7-4ea0-85e7-9ccc9dfe1588","shared_citers":54},{"title":"Scalable training of","work_id":"aef70eae-f816-4598-84ec-429a2c09f5fc","shared_citers":53},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":11},{"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","shared_citers":7},{"title":"2024 , eprint=","work_id":"94860f33-c1e9-46de-b7ef-cdfde74468a5","shared_citers":6},{"title":"2025 , eprint=","work_id":"26c7b6ed-f86e-4ed8-b9ed-b1783d90255b","shared_citers":6},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":6},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":6},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":6},{"title":"Advances in neural information processing systems , volume=","work_id":"12f5a236-ef7a-4d13-b4de-b51465a6f977","shared_citers":5},{"title":"A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =","work_id":"84a2ed32-0a4c-4845-a075-fb640276536c","shared_citers":5},{"title":"and Tukey, John W","work_id":"cc2e8405-2dab-4e00-b3b7-3020d891ee7f","shared_citers":5},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":5},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":5},{"title":"Language Models are Few-Shot Learners , url =","work_id":"518a19dc-59e5-4fa9-b31b-b2c1f0d6676c","shared_citers":5},{"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","shared_citers":5},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":5},{"title":"Scalable training of","work_id":"0bf357a4-bf12-484d-91c5-45d8c83932a5","shared_citers":5}],"time_series":[{"n":1,"year":2021},{"n":4,"year":2023},{"n":6,"year":2024},{"n":1,"year":2025},{"n":48,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-21T05:32:40.585468+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":"2026-05-21T05:32:45.045966+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Tetreault , title =","claims":[{"claim_text":"comment-reply dataset for (dis) agreement detection in online debates. InThirty-fifth conference on neural information processing systems datasets and bench- marks track (round 2). Miklos Z Rácz and Daniel E Rigobon. 2023. Towards consensus: Reducing polarization by perturbing so- cial networks.IEEE Transactions on Network Sci- ence and Engineering, 10(6):3450-3464. ZP Rosen and Rick Dale. 2025. Antisemitic and islamophobic hate speech precedes a decrease in lexico-semantic diversity in comment ","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"2005. Ha- hacronym: A computational humor system. InPro- ceedings of the ACL Interactive Poster and Demon- stration Sessions, pages 113-116. David Tomás, Reynier Ortega-Bueno, Guobiao Zhang, Paolo Rosso, and Rossano Schifanella. 2023. Transformer-based models for multimodal irony de- tection.Journal of Ambient Intelligence and Human- ized Computing, 14(6):7399-7410. Robert West and Eric Horvitz. 2019. Reverse- engineering satire, or \"paper on computational hu- mor accepted despite making serious","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"We define N scales with two adapter sets: G= {G1, . . . ,GN } (MGFA) and C={C 1, . . . ,CN } (MCFA). At each scale n, features are reshaped to a grid X (0) v ∈R H×W×D v and downsampled by Down(·,2 n−1): X (n) v = Down(X(0) v ,2 n−1).(4) Let Xv,n = Seq(X (n) v ) denote the flattened se- quence. We then refine and fuse: Gn =G n(Xv,n), C n =C n(Xv,n, Xt),(5) ˜Xv,n =G n +w C n,(6) where w balances global and cross-modal adapta- tion. An interleave-repeat upsampling restores the (a) MGFA Module. (b) ","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"Householder mean-direction alignment.The nuisance mean-direction difference is removed by mapping the sample mean direction of X onto that of Y via Householder reflection. Let ¯x= 1 n Pn i=1 xi, ¯y= 1 m Pm j=1 yj, ˆµx = ¯x ∥¯x∥2 , ˆµy = ¯y ∥¯y∥2 . If ˆµx ̸= ˆµy, the Householder axis is defined as u= ˆµx − ˆµy ∥ˆµx − ˆµy∥2 ,(5) and the reflection matrix is H=I−2uu ⊤,(6) which satisfies Hˆµx = ˆµy and H⊤H=I . We then alignXby applyingHto every vector inX: x′ i =Hx i (i= 1, . . . , n),(7) and Y is ","claim_type":"background","confidence":0.7,"evidence_strength":"citation_context"},{"claim_text":"t→1 as the query requires more changes, thus (1−t)→1 as the query increases in accuracy. 3.6 Query Mutation Given the mutation temperaturet and assessment A from the critic, the original candidate QC is then rewritten via LLMmutate, which is prompted to produce an updated query candidate QC′ that in- corporates the changes recommended by the critic: QC′ =LLM mutate(Q, S′ i, QC, H, A, t)(6) We consider a single refinement step to consist of a call to the critic, followed by a subsequent call to t","claim_type":"other","confidence":0.6,"evidence_strength":"citation_context"},{"claim_text":"contribution of Q and P without the CoT rationale. Correspondingly, al no-CoT represents the attention activation excluding CoT. The additional term WV R(WKR)T q represents the contribution of the CoT rationale R to the hid- den activation. We can get the hidden activation by transforming the attention activation by a non- linear functionf: hl ≈h l no-CoT +f \u0010 WV R(WKR)T q \u0011 (7) Thus, we conclude that the rationale R in the CoT primarily contributes a shift in hidden acti- vation values, emphasi","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Tetreault , title = because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (7 contexts).","role_counts":[{"n":7,"context_role":"background"},{"n":1,"context_role":"other"}]},"error":null,"updated_at":"2026-05-23T11:14:31.334822+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Tetreault , title =","claims":[{"claim_text":"comment-reply dataset for (dis) agreement detection in online debates. InThirty-fifth conference on neural information processing systems datasets and bench- marks track (round 2). Miklos Z Rácz and Daniel E Rigobon. 2023. Towards consensus: Reducing polarization by perturbing so- cial networks.IEEE Transactions on Network Sci- ence and Engineering, 10(6):3450-3464. ZP Rosen and Rick Dale. 2025. Antisemitic and islamophobic hate speech precedes a decrease in lexico-semantic diversity in comment ","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"2005. Ha- hacronym: A computational humor system. InPro- ceedings of the ACL Interactive Poster and Demon- stration Sessions, pages 113-116. David Tomás, Reynier Ortega-Bueno, Guobiao Zhang, Paolo Rosso, and Rossano Schifanella. 2023. Transformer-based models for multimodal irony de- tection.Journal of Ambient Intelligence and Human- ized Computing, 14(6):7399-7410. Robert West and Eric Horvitz. 2019. Reverse- engineering satire, or \"paper on computational hu- mor accepted despite making serious","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"We define N scales with two adapter sets: G= {G1, . . . ,GN } (MGFA) and C={C 1, . . . ,CN } (MCFA). At each scale n, features are reshaped to a grid X (0) v ∈R H×W×D v and downsampled by Down(·,2 n−1): X (n) v = Down(X(0) v ,2 n−1).(4) Let Xv,n = Seq(X (n) v ) denote the flattened se- quence. We then refine and fuse: Gn =G n(Xv,n), C n =C n(Xv,n, Xt),(5) ˜Xv,n =G n +w C n,(6) where w balances global and cross-modal adapta- tion. An interleave-repeat upsampling restores the (a) MGFA Module. (b) ","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"Householder mean-direction alignment.The nuisance mean-direction difference is removed by mapping the sample mean direction of X onto that of Y via Householder reflection. Let ¯x= 1 n Pn i=1 xi, ¯y= 1 m Pm j=1 yj, ˆµx = ¯x ∥¯x∥2 , ˆµy = ¯y ∥¯y∥2 . If ˆµx ̸= ˆµy, the Householder axis is defined as u= ˆµx − ˆµy ∥ˆµx − ˆµy∥2 ,(5) and the reflection matrix is H=I−2uu ⊤,(6) which satisfies Hˆµx = ˆµy and H⊤H=I . We then alignXby applyingHto every vector inX: x′ i =Hx i (i= 1, . . . , n),(7) and Y is ","claim_type":"background","confidence":0.7,"evidence_strength":"citation_context"},{"claim_text":"t→1 as the query requires more changes, thus (1−t)→1 as the query increases in accuracy. 3.6 Query Mutation Given the mutation temperaturet and assessment A from the critic, the original candidate QC is then rewritten via LLMmutate, which is prompted to produce an updated query candidate QC′ that in- corporates the changes recommended by the critic: QC′ =LLM mutate(Q, S′ i, QC, H, A, t)(6) We consider a single refinement step to consist of a call to the critic, followed by a subsequent call to t","claim_type":"other","confidence":0.6,"evidence_strength":"citation_context"},{"claim_text":"contribution of Q and P without the CoT rationale. Correspondingly, al no-CoT represents the attention activation excluding CoT. The additional term WV R(WKR)T q represents the contribution of the CoT rationale R to the hid- den activation. We can get the hidden activation by transforming the attention activation by a non- linear functionf: hl ≈h l no-CoT +f \u0010 WV R(WKR)T q \u0011 (7) Thus, we conclude that the rationale R in the CoT primarily contributes a shift in hidden acti- vation values, emphasi","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Tetreault , title = because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (7 contexts).","role_counts":[{"n":7,"context_role":"background"},{"n":1,"context_role":"other"}]},"error":null,"updated_at":"2026-05-21T05:32:45.048612+00:00"}},"summary":{"title":"Tetreault , title =","claims":[{"claim_text":"comment-reply dataset for (dis) agreement detection in online debates. InThirty-fifth conference on neural information processing systems datasets and bench- marks track (round 2). Miklos Z Rácz and Daniel E Rigobon. 2023. Towards consensus: Reducing polarization by perturbing so- cial networks.IEEE Transactions on Network Sci- ence and Engineering, 10(6):3450-3464. ZP Rosen and Rick Dale. 2025. Antisemitic and islamophobic hate speech precedes a decrease in lexico-semantic diversity in comment ","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"2005. Ha- hacronym: A computational humor system. InPro- ceedings of the ACL Interactive Poster and Demon- stration Sessions, pages 113-116. David Tomás, Reynier Ortega-Bueno, Guobiao Zhang, Paolo Rosso, and Rossano Schifanella. 2023. Transformer-based models for multimodal irony de- tection.Journal of Ambient Intelligence and Human- ized Computing, 14(6):7399-7410. Robert West and Eric Horvitz. 2019. Reverse- engineering satire, or \"paper on computational hu- mor accepted despite making serious","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"We define N scales with two adapter sets: G= {G1, . . . ,GN } (MGFA) and C={C 1, . . . ,CN } (MCFA). At each scale n, features are reshaped to a grid X (0) v ∈R H×W×D v and downsampled by Down(·,2 n−1): X (n) v = Down(X(0) v ,2 n−1).(4) Let Xv,n = Seq(X (n) v ) denote the flattened se- quence. We then refine and fuse: Gn =G n(Xv,n), C n =C n(Xv,n, Xt),(5) ˜Xv,n =G n +w C n,(6) where w balances global and cross-modal adapta- tion. An interleave-repeat upsampling restores the (a) MGFA Module. (b) ","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"Householder mean-direction alignment.The nuisance mean-direction difference is removed by mapping the sample mean direction of X onto that of Y via Householder reflection. Let ¯x= 1 n Pn i=1 xi, ¯y= 1 m Pm j=1 yj, ˆµx = ¯x ∥¯x∥2 , ˆµy = ¯y ∥¯y∥2 . If ˆµx ̸= ˆµy, the Householder axis is defined as u= ˆµx − ˆµy ∥ˆµx − ˆµy∥2 ,(5) and the reflection matrix is H=I−2uu ⊤,(6) which satisfies Hˆµx = ˆµy and H⊤H=I . We then alignXby applyingHto every vector inX: x′ i =Hx i (i= 1, . . . , n),(7) and Y is ","claim_type":"background","confidence":0.7,"evidence_strength":"citation_context"},{"claim_text":"t→1 as the query requires more changes, thus (1−t)→1 as the query increases in accuracy. 3.6 Query Mutation Given the mutation temperaturet and assessment A from the critic, the original candidate QC is then rewritten via LLMmutate, which is prompted to produce an updated query candidate QC′ that in- corporates the changes recommended by the critic: QC′ =LLM mutate(Q, S′ i, QC, H, A, t)(6) We consider a single refinement step to consist of a call to the critic, followed by a subsequent call to t","claim_type":"other","confidence":0.6,"evidence_strength":"citation_context"},{"claim_text":"contribution of Q and P without the CoT rationale. Correspondingly, al no-CoT represents the attention activation excluding CoT. The additional term WV R(WKR)T q represents the contribution of the CoT rationale R to the hid- den activation. We can get the hidden activation by transforming the attention activation by a non- linear functionf: hl ≈h l no-CoT +f \u0010 WV R(WKR)T q \u0011 (7) Thus, we conclude that the rationale R in the CoT primarily contributes a shift in hidden acti- vation values, emphasi","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Tetreault , title = because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (7 contexts).","role_counts":[{"n":7,"context_role":"background"},{"n":1,"context_role":"other"}]},"graph":{"co_cited":[{"title":null,"work_id":"852d89f5-1e7b-4296-b4f2-71e578b5e9f6","shared_citers":58},{"title":"Chandra and Dexter C","work_id":"c3270592-bd69-4213-95e1-4aaf8312be9b","shared_citers":56},{"title":null,"work_id":"aca2b566-99e0-4ebb-9c7a-a81219531259","shared_citers":55},{"title":"A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =","work_id":"6d196829-7173-4c45-aa5c-d0ee30947345","shared_citers":54},{"title":"Aho and Jeffrey D","work_id":"b1f5cb43-a3c7-4ea0-85e7-9ccc9dfe1588","shared_citers":54},{"title":"Scalable training of","work_id":"aef70eae-f816-4598-84ec-429a2c09f5fc","shared_citers":53},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":11},{"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","shared_citers":7},{"title":"2024 , eprint=","work_id":"94860f33-c1e9-46de-b7ef-cdfde74468a5","shared_citers":6},{"title":"2025 , eprint=","work_id":"26c7b6ed-f86e-4ed8-b9ed-b1783d90255b","shared_citers":6},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":6},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":6},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":6},{"title":"Advances in neural information processing systems , volume=","work_id":"12f5a236-ef7a-4d13-b4de-b51465a6f977","shared_citers":5},{"title":"A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =","work_id":"84a2ed32-0a4c-4845-a075-fb640276536c","shared_citers":5},{"title":"and Tukey, John W","work_id":"cc2e8405-2dab-4e00-b3b7-3020d891ee7f","shared_citers":5},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":5},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":5},{"title":"Language Models are Few-Shot Learners , url =","work_id":"518a19dc-59e5-4fa9-b31b-b2c1f0d6676c","shared_citers":5},{"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","shared_citers":5},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":5},{"title":"Scalable training of","work_id":"0bf357a4-bf12-484d-91c5-45d8c83932a5","shared_citers":5}],"time_series":[{"n":1,"year":2021},{"n":4,"year":2023},{"n":6,"year":2024},{"n":1,"year":2025},{"n":48,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"ba76245f-e388-4491-89be-9beb764793e1","orcid":null,"display_name":"Mohammad Sadegh Rasooli and Joel R","source":"manual","import_confidence":0.72}]}}