academic search engine developers

Abstract: Scientific document embeddings such as SPECTER2 are optimized for retrieval over large, heterogeneous corpora. On a small specialized corpus their similarity distributions can become highly compressed, which limits their usefulness for exploratory literature mapping. We study whether weakly supervised in-domain adaptation, using only metadata already available in open citation databases, changes this geometry. On ArtCon, a curated corpus of 704 publications on artificial and machine consciousness, we adapt the SPECTER2 proximity model with a lightweight LoRA adapter trained on positive pairs derived from bibliographic coupling in OpenAlex, using no manually annotated similarity labels. We compare the adapted embeddings with lexical (TF-IDF), citation-based (bibliographic coupling) and generic semantic (SPECTER2) representations under thresholded, fixed-density and symmetric k-nearest-neighbour graph constructions. Adaptation substantially decompresses the similarity distribution (mean pairwise cosine similarity 0.9104 to 0.8663, standard deviation 0.0259 to 0.0594) and yields graphs with markedly higher Louvain modularity and better connectivity than the base encoder under matched edge and neighbourhood budgets. The effect is stable across all three graph constructions and is therefore not an artefact of a single sparsification choice. We report this as a case study on one corpus, and we are explicit about what it does not establish: the clustering indices used here are computed against community labels derived from each representation's own similarity graph, so they measure internal geometric self-consistency rather than agreement with an external topical ground truth, and adaptation and evaluation use the same documents. Evaluation against independent labels, on held-out documents, and against geometric controls is ongoing work.

Abstract: Resolving correct citations can be a time-consuming task for research writers. We address local citation recommendation (LCR), where the goal is to retrieve appropriate references for a given sentence. Web tools generally depend on the existing citation graph, which may bias results toward citation count or more recent publications. LCR research using full paper texts has been limited by the lack of publicly available data. We present a new dataset, the Local Citation Recommendation Corpus (LCRC), containing 14,735 scientific statements derived from astrophysics review papers, each with one or more citation targets whose full text is accessible via API. Using this dataset we systematically compare retrieval methods and develop a citation recommendation system that avoids citation graph bias while achieving 8.0% improvement in Recall@25 and 6.9% improvement in NDCG@25 over dense retrieval baselines without model fine-tuning. To support reproducibility, we make our code and dataset publicly available.

Abstract: Research results are prioritised by search engines, large language models and knowledge graphs chiefly through restatement rather than through the originating source. Although the open-access share of annual scholarly output has recently exceeded half, a substantial subscription corpus remains outside what machine readers may legitimately access under prevailing licences. A mechanism is described whereby subscription content is drawn into the open corpus through its citation and restatement in open-access articles---a process termed human mining, by analogy with the text and data mining performed by machines. An optimistic upper bound on what may thereby be inferred by a machine reader confined to the open literature is modelled, and the completeness, latency and licence constraints of that bound are quantified. A majority of subscription articles that have ever been cited is found to be reachable through at least one open citation, and the median interval between a subscription article's publication and its first open citation is shown to have fallen from thirteen years for work of 1990 to one year for work of 2020. The advantage once conferred by direct subscription access to machine readers has thereby been largely eroded, chiefly as a consequence of the growth of open publishing rather than any change in how researchers cite.

Abstract: What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs. To study this skill, we draw on researchers who know firsthand which earlier work advanced their completed projects, with papers serving as pointers to the ideas within. Using our automated pipeline that makes author annotation scalable, we build ScholarCatalyst by having 184 lead authors of 207 recent computer science papers label which candidates did or could have advanced their project, each with a detailed rationale. We introduce a retrieval task with author-provided judgments: given an initial research question, retrieve these papers from only the literature available when the project began. Agentic search does no better than embedding retrieval (0.42 vs. 0.48 Recall@20) despite calling that same retriever as a tool. Even an agent built on Claude Fable 5.1, which may have seen the completed papers during training, reaches only 0.51 R@20. These results highlight the need for new training recipes that equip models with expert intuition for searching broad corpora. We envision ScholarCatalyst as a step toward scientific agents that can take a half-formed idea and point to the prior research it needs.

Abstract: We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite the page and the table or figure where the answer lives, and answer in a requested format. Our main finding is that evidence grounding is limited by retrieval, not by reading. The page selector put the annotator's page, which we call the gold page, in front of the model that locates evidence only about half the time (52.6% gold-page recall), while that model, given the page, cited the right one in 45 of the 48 locators it emitted (94%). When the page was missing it rarely said so: of 45 such cases it returned nothing 14 times, a wrong page 24 times, and a correct page 7 times, so the pipeline failed quietly almost twice as often as it failed visibly. Since the failure was that the right page was never shown, the fix is to stop choosing: each retrieved paper fits in the model's context, so we show it whole. Page ranking survives only as a fallback inside papers too long to fit, which no test-split paper was, and gold-page recall reaches 100% on the papers we can parse. Separately, questions that identify their target by position rather than content, such as "the first author of the 24th reference", are served by parsing rather than retrieval: we resolve the bibliography into an addressable list, which also supplies identifiers the evidence metric scores. The final system scores 0.762 paper $F_1$, 0.441 evidence $F_1$ and 0.920 multiple-choice accuracy on the held-out test split. Because the pipeline depends on a closed model without seed control, we release a harness that verifies the paper's central claims against committed artifacts.