Pith. sign in

Paper Citation Record · LEDGER

Invariant Features in Language Models: Geometric Characterization and Model Attribution

As of 21 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2605.06458.

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

pith.paper-citation-record.v1
2605.06458 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T12:46:27.960345Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

22 of 22 outbound references displayed

  • verified exact1
  • verified fuzzy21
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 76b49099-c7cd-4c75-9083-49825127ac56 · outbound

This paper cites How contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings.

Invariant Features in Language Models: Geometric Characterization and Model Attribution How contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.384418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:cf4d458a187fa9d0b1e1a357d54a26b1d6b6e0296e9f14ddffcfd606c9921e89

Observation bd8ffad9-522e-4110-9e1e-60c451ee6c08 · outbound

This paper cites BERT rediscovers the classical NLP pipeline.

Invariant Features in Language Models: Geometric Characterization and Model Attribution BERT rediscovers the classical NLP pipeline

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.369629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:37e584842f1f864d90c5401e19f828b79ecf5554073b19aae67537b3541944d5

Observation 7c3257cb-af90-4691-9b10-febefba866bc · outbound

This paper cites A structural probe for finding syntax in word representations.

Invariant Features in Language Models: Geometric Characterization and Model Attribution A structural probe for finding syntax in word representations

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.354480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:10e8bef18168ac0c785555d06ff292d5fca77f1c43e5b4dbf75cc7272cda6e1c

Observation 21d92480-0254-4d6c-9ddc-d25edc6ef229 · outbound

This paper cites A primer in BERTology: What we know about how BERT works.

Invariant Features in Language Models: Geometric Characterization and Model Attribution A primer in BERTology: What we know about how BERT works

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.362417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:7780760442e3ab74c1a30aa0065698485a2090f069bed748c30a33130d77f0ec

Observation aee7af31-c29d-4f4c-94b2-1921466d7265 · outbound

This paper cites Visualizing and measuring the geometry of bert.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Visualizing and measuring the geometry of bert

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.350464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:2c5c8f0bd896566d8d5e2ea3ef6e46cb3e9268a6a19673e313fb333c89c7192b

Observation 5d131c33-438d-422e-98bf-95e1853a8390 · outbound

This paper cites Interpreting pretrained contextualized representations via reductions to static embeddings.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Interpreting pretrained contextualized representations via reductions to static embeddings

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.342539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:34362267770140aaea237ed6a57b6e3342c6ae6a1eb348811fa0ea5ff3b73357

Observation cfc13ab9-4819-4217-a27a-2c6c92402516 · outbound

This paper cites Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.346507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:a155f76ea8b6912539f5741754a809254d82fd0f6b0b41ce8e679e29adba9fa3

Observation 9a840e0d-da60-4fca-bf95-38c3504bc5e0 · outbound

This paper cites Insights on representational similarity in neural networks with canonical correlation.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Insights on representational similarity in neural networks with canonical correlation

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.358513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:590ea27caea997c6b521f5ce4a68067bf5485d7431a14365a4d22c3442a50908

Observation 36a6c13d-ac07-432b-9b39-66e22302ff78 · outbound

This paper cites Similarity of neural network representations revisited.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Similarity of neural network representations revisited

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.373121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:6554a3d73b7ffb7159f68167b0068baabe68edfd20c32c36419053e407515dbe

Observation fc18c0d2-1be0-4026-bbe0-0ee37c3027b1 · outbound

This paper cites The power of scale for parameter-efficient prompt tuning.

Invariant Features in Language Models: Geometric Characterization and Model Attribution The power of scale for parameter-efficient prompt tuning

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.366021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:ce3d0cd6043ce63a67cfb63dfcd0ab31bdba96046cc646458259e6389b5dafde

Observation b83bd384-b62d-469a-93b4-cbd3d7fbb397 · outbound

This paper cites Universal adversarial triggers for attacking and analyzing NLP.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Universal adversarial triggers for attacking and analyzing NLP

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.330047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:c3d70944980a79ce74f80a8b9dd14c430e6ac251c6bea17f3df09c82de51a66f

Observation 6ef16a64-dc3e-4e3c-8101-369f61b98ee5 · outbound

This paper cites From text to source: Results in detecting large language model-generated content.

Invariant Features in Language Models: Geometric Characterization and Model Attribution From text to source: Results in detecting large language model-generated content

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.377099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:f5ea30592083c013983c28fdfc0c013ade4373d4b162110dac2d6d409f6e2cf0

Observation 589f858f-ef9c-4e20-9b67-9eede684267b · outbound

This paper cites Source Attribution for Large Language Model-Generated Data.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Source Attribution for Large Language Model-Generated Data

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-05-11T19:06:08.597342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:6fe7a1613a627407279066fad305e40f07bef6d5e570c9a6458582f9fffbeb81

Observation 547e641a-42b0-48ba-ac8f-86adc4035937 · outbound

This paper cites Watermarking language models through language models.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Watermarking language models through language models

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.380967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:97fc1ebf36d58b2f33e2f55578f028a1ed139da096e2793e7d01c3cc967b338c

Observation 18bd508c-cb61-4511-a994-19d47da699db · outbound

This paper cites Instructional fingerprinting of large language models.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Instructional fingerprinting of large language models

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.322249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:4e9063439ebfd951acbc2c68f3fcf8ed7f7da01c9c147817cba6c7389060a271

Observation 33129850-47e5-4773-ad5a-41ae37530f1b · outbound

This paper cites Testing the manifold hypothesis.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Testing the manifold hypothesis

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.325726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:0ee95b901f84a2e8013c0d16d907233b75f0a261edca1225a63c28ada8d80003

Observation 28dc0fff-fb8f-4be1-8521-6db64fc8ba15 · outbound

This paper cites Deep learning without poor local minima.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Deep learning without poor local minima

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.338602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:63c6f8413de1c69ec57aa49ecb4471bff4632659e366c1dbad4055ed07ef6f2f

Observation bba8ab8e-2af3-4f0f-b0ae-c0e3c0287a77 · outbound

This paper cites The loss surfaces of multilayer networks.

Invariant Features in Language Models: Geometric Characterization and Model Attribution The loss surfaces of multilayer networks

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.315167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:b55abe1410e50a570244561badeb24c5893dacb49f48d039d56ad3f23d30cc15

Observation c74dfdec-f532-4642-980a-dcb178431e01 · outbound

This paper cites Prototypical networks for few-shot learning.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Prototypical networks for few-shot learning

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.307972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:b02fe6a9af5fac38492f054132deb5cd51b9336520a6bf3484862bfdf9e58f02

Observation 3c6bcd27-7320-4908-b40f-c451adb6d84b · outbound

This paper cites Stanford alpaca: An instruction-following llama model.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Stanford alpaca: An instruction-following llama model

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.311840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:d3750c9735603e6847071532fd05cd50279238319ba543ff37b295987618ea8d

Observation 35fc96d0-5757-4a6b-8ad7-38f5c174d2f5 · outbound

This paper cites Visualizing data using t-SNE.

Invariant Features in Language Models: Geometric Characterization and Model Attribution Visualizing data using t-SNE

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.318592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:5a4059b8b09eb3eb7e42b463e79f30b42c977aab6dccf59fb7d1e2cd5beefe96

Observation ac724930-f4a2-4a6e-83cb-d1ded54b1b24 · outbound

This paper cites MS MARCO: A human generated machine reading comprehension dataset.

Invariant Features in Language Models: Geometric Characterization and Model Attribution MS MARCO: A human generated machine reading comprehension dataset

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-26T13:02:23.334145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-08T12:46:27.960345Z digest=sha256:c9ae0bc0037bf4ceb2f8e16e5cfe744a6ec6967290323c9e7bef05eea9dc319c

Pith citing papers

No inbound Pith citation observations are available.