Pith. sign in

Paper Citation Record · LEDGER

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 22 inbound Pith citation observations for arXiv:2305.14160.

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

pith.paper-citation-record.v1
2305.14160 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 22 of 22 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T20:12:25.357101Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T09:58:29.202524Z

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 2eb9a3f7-c326-414a-b4f5-2fbe7a305013 · inbound

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling cites this paper.

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-12T09:58:29.206330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-05-12T09:58:29.057357Z digest=sha256:7296d0e17be1151dc257b5ebf1f212776cddb0ec079fd182b3799c808b13e61e

Observation 2d09e604-e5bb-45b0-bb55-56cd6ae902f4 · inbound

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs cites this paper.

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-12T20:12:25.357101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T20:12:25.357101Z digest=sha256:54e8ee29a1cae1fec9cb00adafb66d35ca8ddb1feed048d0b7d9f23fcb23b466

Observation e34d5fb0-07dd-47bf-b1c1-e2b3c6cadfdc · inbound

Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering cites this paper.

Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-12T19:10:15.524088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:10:15.524088Z digest=sha256:4fb0312d6e112a9b08dd993706aa90ab3f5dd2c2e29c8ac45ae84bd1011da53e

Observation dbc8cd6a-4d42-44a7-b9ce-0ab0fcb4713f · inbound

Cross-modal Information Flow in Multimodal Large Language Models cites this paper.

Cross-modal Information Flow in Multimodal Large Language Models Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-12T11:06:10.126476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T11:06:10.126476Z digest=sha256:00972c5edf0db8cf8fb6e23e7f106be8839d9c899b88f7b882e88651cdadba0c

Observation 3899b909-679c-4e44-9f48-c4431af1c89f · inbound

Video Diffusion Transformers are In-Context Learners cites this paper.

Video Diffusion Transformers are In-Context Learners Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 90

Resolution
unresolved
no resolver link, observed 2026-08-11T15:40:20.118393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:40:20.118393Z digest=sha256:6cc2f9ab440b1d61291ff3979b29a4b837c7501d971b8da1b0c4f9a232ba2d0e

Observation 08cd6a83-fa9a-4c1d-98fe-70466edae396 · inbound

Enhancing Transformers for Generalizable First-Order Logical Entailment cites this paper.

Enhancing Transformers for Generalizable First-Order Logical Entailment Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-10T22:48:53.650325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T22:48:53.650325Z digest=sha256:251e7e49337ab63c9d09f7c7788952e68b1a12e55488df0d2e740714688a987e

Observation 2a87b37c-8e59-498d-b94a-983660750c0a · inbound

Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding cites this paper.

Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-10T18:53:21.282078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T18:53:21.282078Z digest=sha256:ec35967c41e3df1743efe83f86546d5eb6d6e7d828fb6105ee5470e6d7d9d1d0

Observation 82b18dec-b3da-4bec-8f00-16a65455e80c · inbound

StaICC: Standardized Evaluation for Classification Task in In-context Learning cites this paper.

StaICC: Standardized Evaluation for Classification Task in In-context Learning Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-10T14:06:14.497128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T14:06:14.497128Z digest=sha256:02c108fdb08a6f43ab2d96da7d88f68d7344acf8d84e9a64d12f981a64eea159

Observation bd5896f8-8a41-4384-8067-67e48f6e9198 · inbound

An Analysis for Reasoning Bias of Language Models with Small Initialization cites this paper.

An Analysis for Reasoning Bias of Language Models with Small Initialization Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-09T05:28:51.801401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T05:28:51.801401Z digest=sha256:025a481f9fd0948b0833da0f11138e46f8777db64e83007d9ea7bbc9e69d2eae

Observation 498d6077-4228-4514-9f1d-e2780b85452a · inbound

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage cites this paper.

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T23:09:36.663757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T23:09:36.663757Z digest=sha256:d9b2e2654e074ed26ab3c9f4f48522757cd25f9e4c150a3592e7e979fbd072c0

Observation eb8bec7c-a9c2-4160-9470-9559901e8d62 · inbound

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis cites this paper.

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T15:39:19.983154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:39:19.983154Z digest=sha256:4f922861da173fc784775881eaf409b282dabd7d95ceabf2f564cd7e743c9295

Observation 1ce54816-f4f9-4630-aa7b-8d46f994fbe2 · inbound

Large Language Models as Computable Approximations to Solomonoff Induction cites this paper.

Large Language Models as Computable Approximations to Solomonoff Induction Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-07T15:16:57.387765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:16:57.387765Z digest=sha256:f4385fddba29ce81008614c688cb0de35b1b47895f6f2fe3f16fcb06efd61f16

Observation 5017c3a6-e926-4217-b057-3190eae5e1a4 · inbound

Understanding the learned look-ahead behavior of chess neural networks cites this paper.

Understanding the learned look-ahead behavior of chess neural networks Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-07T14:17:48.094636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:17:48.094636Z digest=sha256:0d2cdbd38a134b18ca22cb3805c9bc0599cb19751b8769bbda093acfe1fa8e5f

Observation 7c086cfc-74b3-45d2-9d1b-60353a67b8ae · inbound

ConText: Driving In-context Learning for Text Removal and Segmentation cites this paper.

ConText: Driving In-context Learning for Text Removal and Segmentation Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-07T11:01:12.487239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T11:01:12.487239Z digest=sha256:a011b2822ebc2fe1538bfa962ce38b555f9bc9b80ff82a89925eda39bd923f08

Observation 5f7ccba4-72b1-41af-b2b7-dd210c793768 · inbound

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation cites this paper.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T00:53:25.946504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T00:53:25.946504Z digest=sha256:d592b6532ef66e735ba026905acf274250fd7ca0e69b26b9f7418288f511d562

Observation 2e9bfb90-0e6c-4900-a15a-c4b9067f3bd9 · inbound

Unveiling Effective In-Context Configurations for Image Captioning: An External & Internal Analysis cites this paper.

Unveiling Effective In-Context Configurations for Image Captioning: An External & Internal Analysis Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-06T19:21:13.522033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T19:21:13.522033Z digest=sha256:f22ff4f402d6ebb1a124073ff41a12b3eecb800f8a069115d8e6873a4edbcaa7

Observation c396b57c-ee72-4e57-83bf-541e749a2636 · inbound

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models cites this paper.

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-06T18:09:09.900466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:09:09.900466Z digest=sha256:7690e48c7231064e86f2c1060c80ca21f3ce638f5d04c2e0f814dd26369c3bf7

Observation e5c998d5-459a-4534-866d-002bb050f289 · inbound

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning cites this paper.

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T17:52:37.589522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T17:52:37.589522Z digest=sha256:06926b534201b1680dbfad2a853d01b4a346be7e8ac6c9df4025dae60eb5a6c1

Observation efeb0a31-f453-4c1d-ad17-afd1aa922eda · inbound

NEAT: Concept driven Neuron Attribution in LLMs cites this paper.

NEAT: Concept driven Neuron Attribution in LLMs Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-05T18:01:19.720092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T18:01:19.720092Z digest=sha256:f772dcef36788781df8a640f06c3e819faabfd0b26a6722ae08a9995f4cd6f17

Observation fe512cfd-54da-4499-9888-9700cd979881 · inbound

Semantic Causality-Aware Vision-Based 3D Occupancy Prediction cites this paper.

Semantic Causality-Aware Vision-Based 3D Occupancy Prediction Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-04T20:48:59.844453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:48:59.844453Z digest=sha256:24cd35a5b6982ccc3d67e5bf3013e935ef89e25fcc228d3a616b0dfc74568204

Observation b0ea5ba7-73be-4cd4-8f3d-880d99310da9 · inbound

Multimodal Function Vectors for Visual Relations cites this paper.

Multimodal Function Vectors for Visual Relations Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T12:44:42.196116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T12:44:42.196116Z digest=sha256:e6e03b40ed2f576d507155d493878f3a65e0251782a504321756ec525b902928

Observation 04607001-7206-4189-90c2-fedc4447401f · inbound

Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks cites this paper.

Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 39

Resolution
verified exact
arxiv_id, observed 2026-05-10T13:45:28.164883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-05-10T13:41:37.942145Z digest=sha256:1b71db6faeb61cac6745afa4d8ba7cc7a9f0edbcc6433c121d7bfbf9f627e025