Papers › Cognitive Graph for Multi-Hop Reading Comprehension at Scale

Cognitive Graph for Multi-Hop Reading Comprehension at Scale

14 May 2019ACL 2019 7arXiv:1905.05460archive 2025-07-28

Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang

We propose a new CogQA framework for multi-hop question answering in web-scale documents. Inspired by the dual process theory in cognitive science, the framework gradually builds a \textit{cognitive graph} in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2). While giving accurate answers, our framework further provides explainable reasoning paths. Specifically, our implementation based on BERT and graph neural network efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint F₁ score of 34.9 on the leaderboard, compared to 23.6 of the best competitor.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1905.05460")

Code

Syntology Ran 5 of 9 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · violated contract; 2 ran · our draft was wrong.

By repository: official repository: 7 samples from 1 repository, 3 ran; community (archive-listed): 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

THUDM/CogQA officialmentioned in papermentioned on GitHubpytorchMIT report
ShaoaAllen/CogQA mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 5 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · violated contract
2ran · our draft was wrong
4unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

exact_match_score THUDM/CogQA/hotpot_evaluate_v1.py official repository ran · violated contract fingerprinted MIT (permissive) · 9d0dc82a4491f803 · report
f1_score THUDM/CogQA/hotpot_evaluate_v1.py official repository ran · honoured contract MIT (permissive) · 32a5f1733d9a8971 · report
normalize_answer THUDM/CogQA/hotpot_evaluate_v1.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · dae7ab386661a4f4 · report
dp THUDM/CogQA/utils.py official repository unverified MIT (permissive) · e54c3ac5706d62dc · report
find_fact_content THUDM/CogQA/process_train.py official repository unverified MIT (permissive) · 48ef4a256160b865 · report
get_context_fullwiki THUDM/CogQA/utils.py official repository unverified MIT (permissive) · f21b310d4e20da30 · report
get_edges THUDM/CogQA/read_fullwiki.py official repository unverified MIT (permissive) · 04d7749f0d53e657 · report
get_pad_mask ShaoaAllen/CogQA/transform2_model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 733cd4727b4ed611 · report
get_subsequent_mask ShaoaAllen/CogQA/transform2_model.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 1eedfb10edb08c8a · report

Tasks

Graph Neural NetworkMulti-Hop Reading ComprehensionMulti-hop Question AnsweringQuestion AnsweringReading Comprehension

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering HotpotQA Cognitive Graph QA ANS-EM 0.371 #50 of 72 Archive leaderboard report
Question Answering HotpotQA Cognitive Graph QA ANS-F1 0.489 #50 of 72 Archive leaderboard report
Question Answering HotpotQA Cognitive Graph QA JOINT-EM 0.124 #50 of 72 Archive leaderboard report
Question Answering HotpotQA Cognitive Graph QA JOINT-F1 0.349 #50 of 72 Archive leaderboard report
Question Answering HotpotQA Cognitive Graph QA SUP-EM 0.228 #50 of 72 Archive leaderboard report
Question Answering HotpotQA Cognitive Graph QA SUP-F1 0.577 #50 of 72 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutGraph Neural NetworkLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections