Pith. sign in

Paper Citation Record · LEDGER

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?

As of 15 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 3 inbound Pith citation observations for arXiv:2502.08991.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.08991 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T23:10:14.485065Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:59:20.162242Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T20:38:56.102343Z

Reference resolution

39 of 39 outbound references displayed

  • verified exact0
  • verified fuzzy26
  • unresolved13
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 62aea5a4-be93-4f7a-b6d8-7c2e6c75a887 · outbound

This paper cites write newline.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.280082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.280082Z digest=sha256:21a45ea9efce4952b155f6008c1c362740abc1ffa3dce89d41c2971a1f833bef

Observation 0153bb8b-a30f-4a6b-8b59-bb62c4d17c0f · outbound

This paper cites How far can transformers reason? the locality barrier and inductive scratchpad.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? How far can transformers reason? the locality barrier and inductive scratchpad

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:15.145154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.287463Z digest=sha256:f20ccb9f73f99a3b66da2abc54e4f42641fbbda76ee3074d0ffda75484bede4a

Observation 924bd262-4e8a-4ceb-a6fc-5bc32624580b · outbound

This paper cites and Bengio, Y.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? and Bengio, Y

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:15.125955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.293128Z digest=sha256:98e2e1543acbdca87e1db49736944cd93574ccbe9589edb9f545210e7588340b

Observation 7fa4a20c-eaac-4e4c-9216-ec1a73cd7659 · outbound

This paper cites an unresolved cited work.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-07T23:10:15.101687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.298762Z digest=sha256:1269de9e8dee10aad99c0d61783ca01485caa69dc5c2ed49d83264c3e2865aee

Observation 75adaf68-3c6d-4afc-8ce7-abd4448c08c3 · outbound

This paper cites Invariant Risk Minimization.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Invariant Risk Minimization

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.304636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.304636Z digest=sha256:8d8167dd0d3a2595801940ec490fb46fc2d15f90ad74c39bd2584a692cb06310

Observation 6d037a70-9788-4a97-9627-28f2f26a3cf5 · outbound

This paper cites A Theory for Emergence of Complex Skills in Language Models.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? A Theory for Emergence of Complex Skills in Language Models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.310979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.310979Z digest=sha256:0520af36baf45828adb8e37de34ad8b0f8d2421a5deeda8c97731edd998305f4

Observation e88e531d-12c4-431c-be9c-1ffd59953628 · outbound

This paper cites Transformers as statisticians: Provable in-context learning with in-context algorithm selection.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Transformers as statisticians: Provable in-context learning with in-context algorithm selection

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:15.082589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.317694Z digest=sha256:c1dae7d9305c926d2c1bf192bc27564558a3e460006c144a1767f41798fb7898

Observation e0efbde0-df55-4f85-b71d-932c6f80aeb4 · outbound

This paper cites and Urner, R.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? and Urner, R

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:15.064939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.323553Z digest=sha256:598b8ef16c17a490334708278da0e36e6c96ce27a118986185e9acde6a4db0d3

Observation 1c9a15f2-ad4e-4f36-b68e-78474f51bea7 · outbound

This paper cites Understanding in-context learning in transformers and LLM s by learning to learn discrete functions.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Understanding in-context learning in transformers and LLM s by learning to learn discrete functions

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:15.046470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.328834Z digest=sha256:0e95bbbfb13cacf569df1705fbf40a3c5892bc93d66e299cd958ee8db4a69273

Observation b6a749bc-76bc-44e0-9487-0977fdee26c1 · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.333746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.333746Z digest=sha256:e0da8a5ff4b99b8458ac3e5b63bef6dae7d0d11c9e38aff1f47ffa530028f39c

Observation c25facf7-9000-4ad5-8dba-82f3cc751dfc · outbound

This paper cites Learning bounds for importance weighting.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Learning bounds for importance weighting

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:15.017566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.339167Z digest=sha256:c683a0823c7c26e9045ec6219a18366448edfd40e42e59521a3cd9b4a273111a

Observation bc32888e-2a2d-401f-9d0b-5e92843bf9fd · outbound

This paper cites S., Koushik, J., Singh, A., and P \'o czos, B.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? S., Koushik, J., Singh, A., and P \'o czos, B

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.998964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.344675Z digest=sha256:de0b6133f43eed86bfa6ad182e6b7795dabd95b9854cd529f12b9f856bb63451

Observation 35d20199-66ed-4056-a0ef-af79bc14d9e8 · outbound

This paper cites Distributionally robust losses for latent covariate mixtures.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Distributionally robust losses for latent covariate mixtures

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.979593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.350265Z digest=sha256:da64b9a6bcf8037b1e909f33b4c479c0459b90ef50ca6e59a8cd935103b5077e

Observation 1a73132f-4949-4874-9d37-6e6c152352b4 · outbound

This paper cites L., Jiang, L., Lin, B.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? L., Jiang, L., Lin, B

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.962907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.356052Z digest=sha256:afa3009cb43e54eacc14ca328e2f51712ffef348d9b1306c0fea56d1ded6e614

Observation bde05660-c5eb-480b-b506-2778bedaecd8 · outbound

This paper cites S., and Valiant, G.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? S., and Valiant, G

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.945925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.361832Z digest=sha256:7d6703be6acfcaa7667a028c002c60b4306e4dec42715bf4db2c3d6c48b7ff28

Observation 4c76ca32-5ed3-4f26-9243-f056d20f4db0 · outbound

This paper cites Instruct-skillmix: A powerful pipeline for llm instruction tuning.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Instruct-skillmix: A powerful pipeline for llm instruction tuning

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.928932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.366695Z digest=sha256:770da4b5e87d4f5e34d1ddb8295f2d745cc0c29f92bf1d8d1f40ba306f4a1411

Observation 999df2fa-119e-44b3-8af4-a8c116bad283 · outbound

This paper cites Measuring compositional generalization: A comprehensive method on realistic data.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Measuring compositional generalization: A comprehensive method on realistic data

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.912147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.371708Z digest=sha256:77b99200284c5c4d479c0d7d7518a94de65b8a68219e3f751f29b214d56b9567

Observation 97f8fbd3-52b7-4e3e-a67b-94fe78deabe7 · outbound

This paper cites an unresolved cited work.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.376523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.376523Z digest=sha256:95478c1565a8ad4f65e7d252889f25b1119ba98a9387f8110e4feccce016695a

Observation 6db14cab-7fae-41c9-913e-20eff14460bc · outbound

This paper cites and Martinet, G.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? and Martinet, G

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.381963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.381963Z digest=sha256:cb304670cc82cc620da5870f407ae12dd09f0bdfe22439f2b0097760c39dd0e2

Observation 0a3d8ac9-66d6-4824-bea0-8582f3732b69 · outbound

This paper cites and Baroni, M.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? and Baroni, M

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.870747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.387788Z digest=sha256:14efe52202df0ae041d50002ecc4a9cd8d0c13cdebdf913b6192d8594b3e3488

Observation 8f67344f-aad9-4c64-aefb-41455b28fc04 · outbound

This paper cites Near-optimal linear regression under distribution shift.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Near-optimal linear regression under distribution shift

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.852964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.393334Z digest=sha256:d34582a6f33ddd48139e148040926cf99c80ed4a40c3bcaad7d4ddbcdf9dd529

Observation 88fb128e-1ae8-49cf-a731-8f3842999ca9 · outbound

This paper cites E., Papailiopoulos, D., and Oymak, S.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? E., Papailiopoulos, D., and Oymak, S

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.835428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.398853Z digest=sha256:b67c00a791875ab6f09bf779b26b76eb13956809a8c7860809facd61e5a494b0

Observation 083c735f-4e75-4d3e-a084-292b7b9cf967 · outbound

This paper cites and Stachenfeld, K.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? and Stachenfeld, K

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.818514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.403832Z digest=sha256:101568b83e0b433a1cb702efe46b66131bd60156abdc3b36d880bc6d513cf7ab

Observation 77878615-63e6-4435-9eff-22704501f82e · outbound

This paper cites an unresolved cited work.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Unresolved cited work

Reference 24

Resolution
unresolved
raw_fallback, observed 2026-08-07T23:10:14.800681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.408814Z digest=sha256:177bd7dc8342668d3991cf789444b72b732db847941e691358c95959bd3ce2c7

Observation 1325c223-ad76-49c5-9bdb-1c3c5e33185f · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Towards deep learning models resistant to adversarial attacks

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.413618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.413618Z digest=sha256:067cd6f18f73ab11c79cf9a787d787ba4435cef75676514e4ef0e764bf9ce2f5

Observation 6aad1bfb-0c11-4b31-b29a-959e79369dcf · outbound

This paper cites Domain adaptation: Learning bounds and algorithms.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Domain adaptation: Learning bounds and algorithms

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.769652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.418585Z digest=sha256:f9c293b277b9132721bf0e34e7de9fb4090fc9521efc9968e7c507874eae226c

Observation 247e6d12-133f-41b8-9a37-335c01f52891 · outbound

This paper cites M., Yang, F., Duchi, J., and Liang, P.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? M., Yang, F., Duchi, J., and Liang, P

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.751151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.423653Z digest=sha256:3438c8c35315dd9ade2137d9964f774ace3cdb1892f8ec4a45fe8984ead2f7f5

Observation f0c22ce3-2071-4c01-bd02-27e0e3578c4c · outbound

This paper cites Y., Padmakumar, V., Joshi, N., Kazemi, M., Kim, N., and He, H.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Y., Padmakumar, V., Joshi, N., Kazemi, M., Kim, N., and He, H

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.734372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.428500Z digest=sha256:fc273f864ac9ddf4ccc2e28b98c3ec0b7f555401a79f456be381a7e9df4a2beb

Observation f53b3e7e-2e6d-482a-bd0d-ffdda26056c2 · outbound

This paper cites M., Von Oswald, J., Pascanu, R., Sacramento, J., and Steger, A.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? M., Von Oswald, J., Pascanu, R., Sacramento, J., and Steger, A

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.717244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.434234Z digest=sha256:564eccd8819557bed2b599efe0765ca7121844aef4704bb928189cd20914410d

Observation b4d72497-09bb-4e5b-8080-f084fc31d32d · outbound

This paper cites Out-of-distribution generalization via composition: a lens through induction heads in transformers.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Out-of-distribution generalization via composition: a lens through induction heads in transformers

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.700090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.439460Z digest=sha256:6026ab63592a600efdd859bd4f5ba03287dd0c40cde3ff8aa778981f02e6b3f3

Observation 4d128c4b-71d7-4905-80fe-fee12b9b1fb9 · outbound

This paper cites Covariate shift adaptation by importance weighted cross validation.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Covariate shift adaptation by importance weighted cross validation

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.444257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.444257Z digest=sha256:97f24e15ae3d9c5a092f115f35b3eb45dfc2aae511bbe64146b303ef468fd483

Observation 37b26579-18f0-4cd6-b09f-af1463ae99f7 · outbound

This paper cites H., Hashimoto, T., Vinyals, O., Liang, P., Dean, J., and Fedus, W.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? H., Hashimoto, T., Vinyals, O., Liang, P., Dean, J., and Fedus, W

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.671092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.448847Z digest=sha256:98feb91b694abd194a5f30f6d9e95f6927739eaf8a8a14aef246d443f1a603fb

Observation a59d0f81-e176-49c5-87d3-fc061784cfa4 · outbound

This paper cites From sparse dependence to sparse attention: Unveiling how chain-of-thought enhances transformer sample efficiency.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? From sparse dependence to sparse attention: Unveiling how chain-of-thought enhances transformer sample efficiency

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.652867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.453447Z digest=sha256:8fc977d084b458880d12a8d1acdbbae94bcb5ae5a69b8aab32bab49d3ff4b436

Observation 7aa64d73-8eac-435d-b3ad-b9b734c68ccb · outbound

This paper cites Compositional generalization from first principles.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Compositional generalization from first principles

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.634476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.458108Z digest=sha256:d74123ed23380ab08a3db772933ae25d1995bb48bb3de06b5bc42948886f3639

Observation 65ae73e0-2392-4e54-b835-826e49d8e599 · outbound

This paper cites Transformers: State-of-the-art natural language processing.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Transformers: State-of-the-art natural language processing

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.617868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.462973Z digest=sha256:9ebcadcc6167994ca8aa74c7c4ad58f5e0ecfa287f19d3861ffb89b27c22dce9

Observation 354eac17-cda4-41fa-ac96-3e69543a0b5b · outbound

This paper cites Do large language models have compositional ability? an investigation into limitations and scalability.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Do large language models have compositional ability? an investigation into limitations and scalability

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T23:10:14.599849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-07T23:10:14.468358Z digest=sha256:3cab60fd7ca509da2063d13cd55ef50fdc784472a2b576df217e8cf51c8678a5

Observation c75f9c5d-be2b-4a30-b4dc-92bc57e582fc · outbound

This paper cites Towards a theoretical framework of out-of-distribution generalization.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Towards a theoretical framework of out-of-distribution generalization

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.473760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.473760Z digest=sha256:847eedd79b86244995fcf2a64fd90cf1d9adfb4f1a223e06b75e09c783fbf05a

Observation f0358ef3-3830-4caf-9417-1d990115148a · outbound

This paper cites Can models learn skill composition from examples? Advances in Neural Information Processing Systems, 37: 0 102393--102427, 2024.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Can models learn skill composition from examples? Advances in Neural Information Processing Systems, 37: 0 102393--102427, 2024

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.479644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.479644Z digest=sha256:0a9f38eaccd9e50fcdf02003507f1f69acd119abba510b90f35c6c104aa81dbe

Observation d6bcc1c9-cbc2-4027-892c-4be536d522be · outbound

This paper cites an unresolved cited work.

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks? Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T23:10:14.485065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T23:10:14.485065Z digest=sha256:a486dbe1e225f9708a8a3dc8eb9c0712138be70069c31e91a316fdb3ff6c7441

Pith citing papers

Observation 33880408-792c-4816-8f9c-0f58a1f37073 · inbound

Extrapolation by Association: Length Generalization Transfer in Transformers cites this paper.

Extrapolation by Association: Length Generalization Transfer in Transformers Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T04:59:20.162242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:59:20.162242Z digest=sha256:63ce77627a27eae2dd652f3d51c4bed760e5aab47ce11f86cc7be7890d465e99

Observation b02244a8-dde9-4b27-9c8f-467b56fadc67 · inbound

Generalization in LLM Problem Solving: The Case of the Shortest Path cites this paper.

Generalization in LLM Problem Solving: The Case of the Shortest Path Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-10T10:39:38.019624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-10T10:37:45.355872Z digest=sha256:aa692dda0b5de2826244c8127a227d09de778726e89416685a07159260190aa1

Observation 393580e0-f8a0-4f1e-be5f-a887f9cdb9eb · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?

Reference 145

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T20:38:56.103753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-06-27T01:13:11.483599Z digest=sha256:f6f67c55b11313224114c18e524d9f0a0a7c327c7852139f3ea674cf6009a4fa