Pith. sign in

Paper Citation Record · LEDGER

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 21 inbound Pith citation observations for arXiv:2405.15071.

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

pith.paper-citation-record.v1
2405.15071 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 21 of 21 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:18:38.889675Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T01:09:18.582914Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation e8f38e03-4a92-4ab0-843c-ef103b38b4e6 · inbound

Do LLMs Really Think Step-by-step In Implicit Reasoning? cites this paper.

Do LLMs Really Think Step-by-step In Implicit Reasoning? Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-12T13:52:37.972647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-12T13:52:37.972647Z digest=sha256:fd3665d9f901ecea9ec9bf24e89135112ee21fa3ed459a8086b89a2c84dca780

Observation 7570cbcc-7abb-4a87-bbb9-1e6c657e3842 · inbound

Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts? cites this paper.

Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts? Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-12T12:53:38.935929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-12T12:53:38.935929Z digest=sha256:639c0b0942a85b31b149bc21536bd99362ffdcd60f9c19561ccc78569cde9a0f

Observation 50496835-9d32-4382-ad34-5be903cfd868 · inbound

Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring cites this paper.

Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-08T13:53:58.439406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T13:53:58.439406Z digest=sha256:3a30707c421ddbc94451976910254590b385cffbea5b6ae8829be9c10bf6c649

Observation 60fb0b32-6fdd-4301-9796-28c7e711193a · inbound

CryptoX : Compositional Reasoning Evaluation of Large Language Models cites this paper.

CryptoX : Compositional Reasoning Evaluation of Large Language Models Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-08T18:34:26.790561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T18:34:26.790561Z digest=sha256:788c577783ef9f23bf1c0e250346b3a77a7a2ab0bc6782ecf99793bfa61e156a

Observation 96dabb3c-ab02-4be5-847f-7a68d6c7ee16 · inbound

Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model cites this paper.

Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-16T12:18:38.889675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T12:18:38.889675Z digest=sha256:04da4d60546bcc7efd89de1e7abb21775a50f880464a23f136ff4a87a435bc37

Observation 056030f5-4be6-47f7-9caf-c65aef1c837c · inbound

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers cites this paper.

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-16T05:25:02.907050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T05:25:02.907050Z digest=sha256:00f61f8005fbd71c4d91fa30b3a4b28d32868ec0cc834cb5a89a9f6001053df9

Observation 0cde4bc6-68ba-454c-abbd-d6f98426de01 · inbound

Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens cites this paper.

Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-15T20:15:17.987943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:15:17.987943Z digest=sha256:ca9a801761869b5490d3acbb05feb25ce55834dcabae8238366b42f60731a407

Observation 43e43de8-b55d-4d46-8ce2-d425768a8620 · inbound

Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers cites this paper.

Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T05:04:55.954824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:04:55.954824Z digest=sha256:0321adef7f9b9a145d59e9ec5f4026444b59b9fd097a9c35af857b7ec9198b37

Observation a30a8d7b-151e-4400-8f44-17981b9ddca3 · inbound

A Survey on Latent Reasoning cites this paper.

A Survey on Latent Reasoning Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 106

Resolution
unresolved
no resolver link, observed 2026-08-06T19:14:31.669683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:14:31.669683Z digest=sha256:8bbe92c4ecb2901efe7bac81e5a02d5874ab07c233e2e28f95f47319fbaa8269

Observation 369cce04-b9bc-42a2-af45-81aa3c6c5399 · inbound

Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity cites this paper.

Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-04T22:25:54.929684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T22:25:54.929684Z digest=sha256:73b513cc61c1597077ccf79f8c16e5ac192d64f946a7390260deefcf5d9853c0

Observation 51b74ef3-b4e1-44c8-9fc1-40149da4906c · inbound

How Do Language Models Compose Functions? cites this paper.

How Do Language Models Compose Functions? Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 42

Resolution
verified exact
arxiv_id, observed 2026-05-18T11:06:17.684827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-18T11:04:09.179536Z digest=sha256:a9c6098cba2b3c577ec352599dc922126c5df3d9ca201953e0e0fbc3c0c2e6a1

Observation 00c02a10-0d26-4324-a9df-1d0f15add338 · inbound

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior cites this paper.

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-05-14T21:17:58.770644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-14T21:16:40.430384Z digest=sha256:fdf3ceb0bd47de37cd6c834a9f517a89624009d31291dd08ac6a5b32d6817535

Observation 2583a2f7-60a4-4d89-8ebd-9a6f9356969c · inbound

The Power of Power Law: Asymmetry Enables Compositional Reasoning cites this paper.

The Power of Power Law: Asymmetry Enables Compositional Reasoning Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 51

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T19:31:08.397062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-05-08T11:49:49.787123Z digest=sha256:e4b46b1ae4aa555dbddfb2567fc52c2b371721c2acc1ad89a13ca496b672b8d0

Observation 5e548869-2b6b-4ca5-9f02-14c02470fd48 · inbound

The Power of Power Law: Asymmetry Enables Compositional Reasoning cites this paper.

The Power of Power Law: Asymmetry Enables Compositional Reasoning Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 51

Resolution
unresolved
no resolver link, observed 2026-07-12T18:26:05.728364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-12T18:26:05.728364Z digest=sha256:afaa680f6ef9849cbf0ed23bb162a14896d3e7b97a7d0f9b42b50d46e74a751a

Observation b85126d6-bc58-4ee4-bf8d-a719e671d729 · inbound

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds cites this paper.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 15

Resolution
metadata mismatch
arxiv_id, observed 2026-05-12T03:56:21.705746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-05-12T03:55:28.036044Z digest=sha256:f2d4b278f00943ed2a52138437b98744d621d7c9a2a3b291e388cf514d7089d1

Observation 3c7d77e0-20a9-418e-9d96-7564ee9e9bf4 · inbound

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory cites this paper.

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 24

Resolution
metadata mismatch
arxiv_id, observed 2026-05-13T05:27:18.424041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-13T05:26:59.138667Z digest=sha256:9b57435a68e03a8882da28779d5ab69869ce3aa6441408ba310c4fd72bbdc48e

Observation 2027839c-ce47-4976-baf2-cb3999f3be04 · inbound

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory cites this paper.

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 24

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T05:35:04.219411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-15T05:32:21.091094Z digest=sha256:020ae59527e0ad47b8205352b352fb465e0f8ce4fb2886c59429b7c107f112ae

Observation af142ca6-244a-4c1d-9459-d0ff60a2bf91 · inbound

Tracing Persona Vectors Through LLM Pretraining cites this paper.

Tracing Persona Vectors Through LLM Pretraining Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 12

Resolution
metadata mismatch
arxiv_id, observed 2026-05-14T20:29:27.784391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-14T20:28:17.086117Z digest=sha256:693937a99ad362895498b89f800e792cd589c1bf3b01f29cfdfb5d2b44530757

Observation 32457174-8b41-41d9-9aee-b911f2adf893 · inbound

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory cites this paper.

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 1

Resolution
metadata mismatch
arxiv_id, observed 2026-07-04T01:09:18.584418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T20:43:55.740662Z digest=sha256:ab4a874f8ebc2d932572ddec25f24cbaa5ac292b040dea8303032836f6f8dd7b

Observation ae16e335-33db-4412-add3-f064ae502bb1 · inbound

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning cites this paper.

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 19

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T13:56:59.363026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-07-02T13:46:59.407102Z digest=sha256:b0be1a7ea245d721dd98e40b4ca7490c9b14d2cf0a7a6666330c07e12df0ae5a

Observation 4837df6c-c697-4488-810c-d2ada4709b9f · inbound

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning cites this paper.

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T09:18:44.690153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T09:18:44.690153Z digest=sha256:2c41adf4c01accfb7bb2f3b8eb58506d73cbaff7d5a2dc50644b79c3ac5cafd9