Papers › Predictive Querying for Autoregressive Neural Sequence Models

Predictive Querying for Autoregressive Neural Sequence Models

12 Oct 2022arXiv:2210.06464archive 2025-07-28

Alex Boyd, Sam Showalter, Stephan Mandt, Padhraic Smyth

In reasoning about sequential events it is natural to pose probabilistic queries such as "when will event A occur next" or "what is the probability of A occurring before B", with applications in areas such as user modeling, medicine, and finance. However, with machine learning shifting towards neural autoregressive models such as RNNs and transformers, probabilistic querying has been largely restricted to simple cases such as next-event prediction. This is in part due to the fact that future querying involves marginalization over large path spaces, which is not straightforward to do efficiently in such models. In this paper we introduce a general typology for predictive queries in neural autoregressive sequence models and show that such queries can be systematically represented by sets of elementary building blocks. We leverage this typology to develop new query estimation methods based on beam search, importance sampling, and hybrids. Across four large-scale sequence datasets from different application domains, as well as for the GPT-2 language model, we demonstrate the ability to make query answering tractable for arbitrary queries in exponentially-large predictive path-spaces, and find clear differences in cost-accuracy tradeoffs between search and sampling methods.

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 13 code samples harvested from 1 repository linked to this paper: 7 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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.

ajboyd2/prob_seq_queries officialmentioned in paperpytorchSyntology: 13 samples, 7 ran (5 instrument-failed) · 6 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

13 samples harvested: 7 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 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.

4ran · our draft was wrong
1ran; the contract check could not run
2ran
6unverified

Licence: 0 of the 13 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 ajboyd2/prob_seq_queries. “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.

ajboyd2/prob_seq_queries official repository 13 samples, 7 ran (5 instrument-failed) · 6 unverified
BSNode seq_queries/sample.py ran MIT (permissive) · 01f54e99a9a60e27 · report fixture: returned BSNode · level recorded 2026-09-22
BeamSearchSampleTree seq_queries/sample.py ran MIT (permissive) · 84afed32bac6237d · report fixture: returned BeamSearchSampleTree · level recorded 2026-09-22
_hidden_state_select seq_queries/sample.py ran; the contract check could not run (RAISES) MIT (permissive) · 2788500c55cb2165 · report fixture: signature state:tuple/1/tuple, i:int/0/int, is_root:bool/0/bool, uses_attention:bool/0/bool · returned tuple · level recorded 2026-09-22
_tup_cpu seq_queries/sample.py ran · our draft was wrong MIT (permissive) · 953f276962847553 · report fixture: signature tup:tuple/1/tuple, force:bool/0/bool · returned tuple · level recorded 2026-09-22
_tup_cpu_gpt2 seq_queries/sample.py ran · our draft was wrong MIT (permissive) · 5bd55c74b63a005b · report fixture: signature tup:tuple/1/tuple, force:bool/0/bool · returned tuple · level recorded 2026-09-22
min_variance_top_k seq_queries/sample.py ran · our draft was wrong fingerprinted MIT (permissive) · b0160851016bd79c · report fixture: signature logits:Tensor/1/float, min_var_reduction:float/0/float, filter_value:float/0/float, is_log_prob:bool/0/bool, max_num_tree_beams:int/0/int · returned Tensor · level recorded 2026-09-22
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind float, dtype float32
seq_queries/sample.py ran · our draft was wrong fingerprinted MIT (permissive) · d111355f8bf308f3 · report fixture: signature logits:Tensor/1/float, top_k:int/0/int, top_p:float/0/float, min_var:bool/0/bool, filter_value:float/0/float, is_log_prob:bool/0/bool · returned Tensor · level recorded 2026-09-22
beam_search_is_hybrid seq_queries/sample.py unverified MIT (permissive) · 485281e3d11416fa · report
beam_search_lower_bound seq_queries/sample.py unverified MIT (permissive) · 9e8a897fff3a55d9 · report
get_optimizer in 228 papers scripts/train/amazon.py unverified MIT (permissive) · 4e56934b09a04cad · report
train in 522 papers scripts/train/amazon.py unverified MIT (permissive) · d5586c4a77b49699 · report
tree_is_estimate_attn seq_queries/sample.py unverified MIT (permissive) · 81646133d69707bb · report
tree_is_estimate_rnn seq_queries/sample.py unverified MIT (permissive) · 80a1ab04938e54b2 · 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 predictive query estimation methods based on beam search, importance sampling, and hybrids (graph method: predictive query estimation methods based on beam search, importance sampling, and hybrids). 11 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. beam_search_is_hybrid entry · level 0 · unverified · 485281e3d11416fa
  2. BeamSearchSampleTree helper · level 1 · ran · 84afed32bac6237d
  3. beam_search_lower_bound sampler · level 0 · unverified · 9e8a897fff3a55d9
  4. tree_is_estimate_attn sampler · level 0 · unverified · 81646133d69707bb
  5. tree_is_estimate_rnn sampler · level 0 · unverified · 80a1ab04938e54b2
  6. BSNode helper · level 1 · ran · 01f54e99a9a60e27
  7. _hidden_state_select helper · level 1 · ran; the contract check could not run (RAISES) · 2788500c55cb2165
  8. min_variance_top_k helper · level 1 · ran · our draft was wrong · b0160851016bd79c
  9. top_k_top_p_filtering helper · level 1 · ran · our draft was wrong · d111355f8bf308f3
  10. _tup_cpu helper · level 1 · ran · our draft was wrong · 953f276962847553
  11. _tup_cpu_gpt2 helper · level 1 · ran · our draft was wrong · 5bd55c74b63a005b

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="2210.06464") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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