Papers › Visual Abductive Reasoning

Visual Abductive Reasoning

26 Mar 2022CVPR 2022 1arXiv:2203.14040archive 2025-07-28

Chen Liang, Wenguan Wang, Tianfei Zhou, Yi Yang

Abductive reasoning seeks the likeliest possible explanation for partial observations. Although abduction is frequently employed in human daily reasoning, it is rarely explored in computer vision literature. In this paper, we propose a new task and dataset, Visual Abductive Reasoning (VAR), for examining abductive reasoning ability of machine intelligence in everyday visual situations. Given an incomplete set of visual events, AI systems are required to not only describe what is observed, but also infer the hypothesis that can best explain the visual premise. Based on our large-scale VAR dataset, we devise a strong baseline model, Reasoner (causal-and-cascaded reasoning Transformer). First, to capture the causal structure of the observations, a contextualized directional position embedding strategy is adopted in the encoder, that yields discriminative representations for the premise and hypothesis. Then, multiple decoders are cascaded to generate and progressively refine the premise and hypothesis sentences. The prediction scores of the sentences are used to guide cross-sentence information flow in the cascaded reasoning procedure. Our VAR benchmarking results show that Reasoner surpasses many famous video-language models, while still being far behind human performance. This work is expected to foster future efforts in the reasoning-beyond-observation paradigm.

PaperPDFConference PDFCodeCode 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 21 code samples harvested from 1 repository linked to this paper: 11 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

leonnnop/var officialmentioned in papermentioned on GitHubpytorchSyntology: 21 samples, 11 ran (3 instrument-failed) · 10 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

21 samples harvested: 11 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
2ran; the contract check could not run
8ran
10unverified

Licence: 0 of the 21 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 leonnnop/var. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

leonnnop/var official repository 21 samples, 11 ran (3 instrument-failed) · 10 unverified
BertEmbeddingsWithSentence src/model/mainmodel.py ran MIT (permissive) · 62fbcc09b795d0d9 · report fixture: returned BertEmbeddingsWithSentence · level recorded 2026-09-22
BertLMPredictionHead in 10 papers src/model/mainmodel.py ran fingerprinted MIT (permissive) · 8dcc67f7cdd708fe · report fixture: returned BertLMPredictionHead · level recorded 2026-09-22
BertPredictionHeadTransform in 10 papers src/model/mainmodel.py ran fingerprinted MIT (permissive) · af63ac23a3503cdf · report fixture: returned BertPredictionHeadTransform · level recorded 2026-09-22
BertSelfAttention in 29 papers src/model/mainmodel.py ran MIT (permissive) · 1ad7e9bae41c84c2 · report fixture: returned BertSelfAttention · level recorded 2026-09-22
BertSelfAttentionSen src/model/mainmodel.py ran MIT (permissive) · 2a92c02716662f19 · report fixture: returned BertSelfAttentionSen · level recorded 2026-09-22
PositionEncoding in 9 papers src/model/mainmodel.py ran MIT (permissive) · e4821f9d2b6f5330 · report fixture: returned PositionEncoding · level recorded 2026-09-22
RelativeTemEmbedding src/model/mainmodel.py ran MIT (permissive) · 328e8c6cf27e19c8 · report fixture: returned RelativeTemEmbedding · level recorded 2026-09-22
TextEmbedding src/model/mainmodel.py ran MIT (permissive) · d3d0c34b93dc9fec · report fixture: returned TextEmbedding · level recorded 2026-09-22
_concat_list_of_tensors src/model/mainmodel.py ran · our draft was wrong MIT (permissive) · 9fe227d9a54173f6 · report fixture: signature _list:list/1/list · returned list · level recorded 2026-09-22
make_pad_shifted_mask src/model/mainmodel.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · ee2eb9135dec6e53 · report fixture: signature input_mask:Tensor/2/float, max_v_len:int/0/int, max_t_len:int/0/int, sentence_len:int/0/int · returned Tensor · level recorded 2026-09-22
make_shifted_mask src/model/mainmodel.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · ed3b9085302e4898 · report fixture: signature input_mask:Tensor/2/float, max_v_len:int/0/int, max_t_len:int/0/int, sentence_len:int/0/int · returned Tensor · level recorded 2026-09-22
BertAttention in 28 papers src/model/mainmodel.py unverified MIT (permissive) · 8a110cded88738a8 · report
BertEmbeddingsWithVideo src/model/mainmodel.py unverified MIT (permissive) · 860f9614a5fe7da7 · report
BertEncoder in 20 papers src/model/mainmodel.py unverified MIT (permissive) · 2fbca415e4e6bf08 · report
BertEncoderSen src/model/mainmodel.py unverified MIT (permissive) · 5aeb53ac7ae0499a · report
BertEncoderUntied src/model/mainmodel.py unverified MIT (permissive) · 3d9f583a9ae50be3 · report
BertLayer in 23 papers src/model/mainmodel.py unverified MIT (permissive) · 5a8e31314ed696b6 · report
BertLayerSen src/model/mainmodel.py unverified MIT (permissive) · a677dcf23ed7fc33 · report
BertLayerUntied src/model/mainmodel.py unverified MIT (permissive) · 4d48738bd0f321b8 · report
Reasoner src/model/mainmodel.py unverified MIT (permissive) · c9602cd24ba31174 · report
VideoEncodingTrans src/model/mainmodel.py unverified MIT (permissive) · 0efbd684f43cf4f6 · report

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 REASONER (graph method: REASONER). 27 bricks; individually on a fixture: 17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. Reasoner entry · level 0 · unverified · c9602cd24ba31174
  2. BertEmbeddingsWithSentence helper · level 1 · ran · 62fbcc09b795d0d9
  3. BertEmbeddingsWithVideo helper · level 0 · unverified · 860f9614a5fe7da7
  4. BertEncoder helper · level 0 · unverified · 2fbca415e4e6bf08
  5. BertEncoderSen helper · level 0 · unverified · 5aeb53ac7ae0499a
  6. BertLMPredictionHead helper · level 1 · ran · 8dcc67f7cdd708fe
  7. BertLayerNorm helper · level 1 · ran · 72b3695069bfff7f
  8. LabelSmoothingLoss helper · level 1 · ran · fa8f4c716c5e5c8d
  9. VideoEncodingTrans model · level 0 · unverified · 0efbd684f43cf4f6
  10. _concat_list_of_tensors helper · level 1 · ran · our draft was wrong · 9fe227d9a54173f6
  11. PositionEncoding helper · level 1 · ran · e4821f9d2b6f5330
  12. TextEmbedding helper · level 1 · ran · d3d0c34b93dc9fec
  13. BertLayer helper · level 0 · unverified · 5a8e31314ed696b6
  14. BertLayerSen helper · level 0 · unverified · a677dcf23ed7fc33
  15. BertPredictionHeadTransform helper · level 1 · ran · af63ac23a3503cdf
  16. BertEncoderUntied helper · level 0 · unverified · 3d9f583a9ae50be3
  17. BertAttention model · level 0 · unverified · 8a110cded88738a8
  18. BertIntermediate model · level 1 · ran · 455739c5ad6b2387
  19. BertOutput model · level 1 · ran · 5d7bf02e4a7c75a1
  20. make_pad_shifted_mask helper · level 1 · ran; the contract check could not run (RAISES) · ee2eb9135dec6e53
  21. BertSelfAttentionSen helper · level 1 · ran · 2a92c02716662f19
  22. gelu helper · level 1 · ran · honoured contract · a3abf3fe697fabd0
  23. BertLayerUntied helper · level 0 · unverified · 4d48738bd0f321b8
  24. BertSelfAttention model · level 1 · ran · 1ad7e9bae41c84c2
  25. BertSelfOutput model · level 1 · ran · bdf10bafd164be1e
  26. make_shifted_mask helper · level 1 · ran; the contract check could not run (RAISES) · ed3b9085302e4898
  27. RelativeTemEmbedding helper · level 1 · ran · 328e8c6cf27e19c8

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="2203.14040") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

BenchmarkingSentenceVisual Abductive Reasoning

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