Papers › Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales

Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales

31 Oct 2024arXiv:2411.00132archive 2025-07-28

Tang Li, Mengmeng Ma, Xi Peng

Large pretrained foundation models demonstrate exceptional performance and, in some high-stakes applications, even surpass human experts. However, most of these models are currently evaluated primarily on prediction accuracy, overlooking the validity of the rationales behind their accurate predictions. For the safe deployment of foundation models, there is a pressing need to ensure double-correct predictions, i.e., correct prediction backed by correct rationales. To achieve this, we propose a two-phase scheme: First, we curate a new dataset that offers structured rationales for visual recognition tasks. Second, we propose a rationale-informed optimization method to guide the model in disentangling and localizing visual evidence for each rationale, without requiring manual annotations. Extensive experiments and ablation studies demonstrate that our model outperforms state-of-the-art models by up to 10.1% in prediction accuracy across a wide range of tasks. Furthermore, our method significantly improves the model's rationale correctness, improving localization by 7.5% and disentanglement by 36.5%. Our dataset, source code, and pretrained weights: https://github.com/deep-real/DCP

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 13 ran (6 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 13 samples that ran have no recorded date.

deep-real/dcp officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 13 ran (7 instrument-failed) · 1 unverified 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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · violated contract
7ran · our draft was wrong
4ran
1unverified

Licence: 14 of the 14 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 deep-real/dcp. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

deep-real/dcp official repository 14 samples, 13 ran (7 instrument-failed) · 1 unverified
SparsityLoss loss.py ran no licence file found · pointer only · 2a8a7d60ebb22e99 · report fixture: signature heatmaps:list/1/Tensor · returned Tensor · level recorded 2026-09-24
convert_to_custom_text_state_dict in 59 papers utils/model.py ran · violated contract no licence file found · pointer only · f19962ebb134b3d7 · report fixture: signature state_dict:dict/0/? · returned dict · level recorded, date not recorded
create_logits in 7 papers loss.py ran no licence file found · pointer only · cad29a7a417c68d3 · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float, logit_scale:Tensor/0/float · returned tuple · level recorded 2026-09-26
get_cast_dtype in 67 papers utils/model.py ran · our draft was wrong no licence file found · pointer only · dcd422d66b0581d8 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
get_input_dtype in 30 papers utils/model.py ran · our draft was wrong no licence file found · pointer only · b476c8cfbf0f1f47 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
hook_prs_logger prs_hook.py ran no licence file found · pointer only · 05fa0d707c66255c · report fixture: signature model:callable/0/?, device:device/0/? · returned PRSLogger · level recorded 2026-09-25
load_json in 344 papers loading_helpers.py ran · our draft was wrong no licence file found · pointer only · 1069918b276d2855 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22
make_descriptor_sentence loading_helpers.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6775b1940ad09da2 · report fixture: signature descriptor:str/0/str · returned str · level recorded 2026-09-22
mod_stringtolist descriptor_strings.py ran · our draft was wrong no licence file found · pointer only · 0eac6e65494da061 · report fixture: signature description:str/0/str · returned list · level recorded 2026-09-25
normalize_heatmap loss.py ran · violated contract fingerprinted no licence file found · pointer only · e9b027ab862daf7d · report fixture: signature heatmap:Tensor/4/float · returned Tensor · level recorded 2026-09-22
stringtolist in 7 papers descriptor_strings.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 46062947cf3ab0e6 · report fixture: signature description:str/0/str · returned list · level recorded, date not recorded
stringtolist_opt descriptor_strings.py ran fingerprinted no licence file found · pointer only · 1fa486482cc060ee · report fixture: signature description:str/0/str, prompt_to_trim:NoneType/0/? · returned list · level recorded 2026-09-25
wordify in 5 papers loading_helpers.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 1812ba359126089a · report fixture: signature string:str/0/str · returned str · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for rationale-informed optimization method (graph method: rationale-informed optimization method). 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. SparsityLoss entry · level 1 · ran · 2a8a7d60ebb22e99
  2. normalize_heatmap helper · level 1 · ran · violated contract · e9b027ab862daf7d

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2411.00132") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DisentanglementPrediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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