Pith. sign in

Paper Citation Record · LEDGER

Conditional Unigram Tokenization with Parallel Data

As of 10 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2507.07824.

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

pith.paper-citation-record.v1
2507.07824 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:35:44.562542Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

32 of 32 outbound references displayed

  • verified exact3
  • verified fuzzy10
  • unresolved18
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 77f33ca5-ac96-401e-bcd2-7dc775b95995 · outbound

This paper cites Do all languages cost the same? tokenization in the era of commercial language models.

Conditional Unigram Tokenization with Parallel Data Do all languages cost the same? tokenization in the era of commercial language models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.414116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.414116Z digest=sha256:b559408daf78c7ac9e2fd40542428aafa2a717b3208d4a8a8b88828d46cc0417

Observation c0ec52fd-c846-4712-a59d-ba7485d6131d · outbound

This paper cites an unresolved cited work.

Conditional Unigram Tokenization with Parallel Data Unresolved cited work

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.419221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.419221Z digest=sha256:3b3a7a6e5386b94b5f14db669ca6e91b478583e2317bf7801284ba7ac5a5e4aa

Observation c245d5f8-f3c1-4ebf-9d18-c209eee0b1f3 · outbound

This paper cites F., Della-Pietra, S.

Conditional Unigram Tokenization with Parallel Data F., Della-Pietra, S

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:45.086897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.424228Z digest=sha256:d053b574ee705c97f960f08135cdda802e8eeb281f86b3eb54a7acfe3009fea3

Observation 214d5a65-0d0a-422e-9db2-5db2ca7ec439 · outbound

This paper cites and Gildea, D.

Conditional Unigram Tokenization with Parallel Data and Gildea, D

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:45.070376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.428765Z digest=sha256:884fcdc40ae0f70279f147dd64b61bd586d11386a0e7e31d3f941251166dde96

Observation 1d9f4ebb-be58-4a70-9ca1-ec0eebed4b2a · outbound

This paper cites Bilingual subword segmentation for neural machine translation.

Conditional Unigram Tokenization with Parallel Data Bilingual subword segmentation for neural machine translation

Reference 5

Resolution
verified exact
doi, observed 2026-08-06T18:35:44.741472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.433757Z digest=sha256:be69d9e892df379594395e0c763d9ffa8e4b3dbdb0b906e3cbd2fca630dbc613

Observation dcf4f5e6-da66-4b00-b4a9-83dd15f92d57 · outbound

This paper cites and Neubig, G.

Conditional Unigram Tokenization with Parallel Data and Neubig, G

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:45.053862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.439497Z digest=sha256:21202e4721f48bf7f1f20b6305ba66419b6f1080f3d87ae95a4977f67112e967

Observation 404e8589-a896-4f62-9b0b-2032ad944587 · outbound

This paper cites an unresolved cited work.

Conditional Unigram Tokenization with Parallel Data Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-06T18:35:45.038191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.444591Z digest=sha256:8333e908990803452a9887ba0dc8951d6a75a498019f5b35772148ccc538e3c1

Observation 66a952df-1706-40f5-b815-ed49da267573 · outbound

This paper cites Beyond literal token overlap: Token alignability for multilinguality.

Conditional Unigram Tokenization with Parallel Data Beyond literal token overlap: Token alignability for multilinguality

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:45.023443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.448841Z digest=sha256:45911829f0bde2655c2413b5d50a3f7144cc346aaaeb9bd30d4cae0fe5854c1f

Observation 276acd2e-72af-4633-882e-c661f88495cb · outbound

This paper cites The state and fate of linguistic diversity and inclusion in the NLP world.

Conditional Unigram Tokenization with Parallel Data The state and fate of linguistic diversity and inclusion in the NLP world

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.453373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.453373Z digest=sha256:4560e282a9b5390a1634ca4a22ae55966a33982fd693c9eea5262a083c57ec57

Observation c8b25ad3-8890-4910-85d3-930965c088a9 · outbound

This paper cites an unresolved cited work.

Conditional Unigram Tokenization with Parallel Data Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-06T18:35:45.007365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.457758Z digest=sha256:8670754d5913f79f01e373cc49f0aada4ab75509b41e031475fa0144b288e2ce

Observation 104eb6a3-2c41-427f-bcca-2142750e42a1 · outbound

This paper cites Subword regularization: Improving neural network translation models with multiple subword candidates.

Conditional Unigram Tokenization with Parallel Data Subword regularization: Improving neural network translation models with multiple subword candidates

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.462215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.462215Z digest=sha256:a442f3a77763b2ccb3c424636cce3ee412286d837ea524b93231e0f7655119fe

Observation 8e576d87-52e5-4f1c-8f53-f258c86fc470 · outbound

This paper cites and Fraser, A.

Conditional Unigram Tokenization with Parallel Data and Fraser, A

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:44.992392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.466444Z digest=sha256:aec2bd5a1fa70a0e089cdae509a7e9d8f80df0d72bd82150855d0a75fb114b7e

Observation 7d48bc60-255f-4c9b-96e7-59f6277e529e · outbound

This paper cites and Helcl, J.

Conditional Unigram Tokenization with Parallel Data and Helcl, J

Reference 13

Resolution
verified exact
doi, observed 2026-08-06T18:35:44.703806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.474029Z digest=sha256:c717f22757f25e411b808783901439cb4d10436bf00eff6254e58bdca7b3155c

Observation 51fb6002-29ca-41f8-859a-392575ab6711 · outbound

This paper cites Tokenization impacts multilingual language modeling: Assessing vocabulary allocation and overlap across languages.

Conditional Unigram Tokenization with Parallel Data Tokenization impacts multilingual language modeling: Assessing vocabulary allocation and overlap across languages

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.478471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.478471Z digest=sha256:e53e598ec97fa811a5632454552fe0d84f7aea0ca7b1ee7d586839441577af32

Observation 9f61a3ec-f325-4bd5-ac86-9cf12dbc240c · outbound

This paper cites WECHSEL : Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Conditional Unigram Tokenization with Parallel Data WECHSEL : Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.483452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.483452Z digest=sha256:1451765c1c2fe0e67fef6decb39b5ab59d34423b5e3937eda5075420a9fe3077

Observation d5700e42-f094-4b92-bf54-2cde7530d9cc · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

Conditional Unigram Tokenization with Parallel Data No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.488511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.488511Z digest=sha256:0bb18df8ebebc7ef731f371fcf1238afdf856adc8fe7e141ef5b781d60f1d974

Observation 875828a4-f630-4df6-8355-c065c47909c7 · outbound

This paper cites and Tiedemann, J.

Conditional Unigram Tokenization with Parallel Data and Tiedemann, J

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:44.976947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.493537Z digest=sha256:1fdb5b2f08e3e6e25095f5bf1581ec5aed168635964870d11f0901080bb56867

Observation 22083a4d-4dde-4c6a-8c77-f23e0616f09d · outbound

This paper cites Bleu: a Method for Automatic Evaluation of Machine Translation.

Conditional Unigram Tokenization with Parallel Data Bleu: a Method for Automatic Evaluation of Machine Translation

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.497932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.497932Z digest=sha256:c4b8396e80ae6014f66d9e27124523325585df7c40f24504c5cfbbb30b9b9c97

Observation c66bfc7a-f612-472e-89ff-d201b26e7cc8 · outbound

This paper cites Language Model Tokenizers Introduce Unfairness Between Languages.

Conditional Unigram Tokenization with Parallel Data Language Model Tokenizers Introduce Unfairness Between Languages

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:44.960471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.502188Z digest=sha256:d698a441dc344873efaa4f823333afecec56b88c725a011ab8248c586ae2afd4

Observation c4060262-5718-436e-ba8a-0be7214a3df2 · outbound

This paper cites How multilingual is multilingual BERT ? In Korhonen, A., Traum, D., and M \`a rquez, L.

Conditional Unigram Tokenization with Parallel Data How multilingual is multilingual BERT ? In Korhonen, A., Traum, D., and M \`a rquez, L

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.506406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.506406Z digest=sha256:292fad2a3f7561e34a7a596d2751d883b34d6ec0b3f4c61c02eb873ac6e139df

Observation d298363c-ce56-40f3-868a-575b745537f2 · outbound

This paper cites A call for clarity in reporting BLEU scores.

Conditional Unigram Tokenization with Parallel Data A call for clarity in reporting BLEU scores

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.511081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.511081Z digest=sha256:4ff9b4faf5ca692895224b05794efa2672bd99cfd12344ad9af4607935e9d6bd

Observation 5fa5563b-b172-4b29-96a3-2fc1dbeb3c5a · outbound

This paper cites Language models are unsupervised multitask learners.

Conditional Unigram Tokenization with Parallel Data Language models are unsupervised multitask learners

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:44.944507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.515339Z digest=sha256:6f6ab63fa029afe9b3e3a35f2829c03df0a6eb9a4f69ffbcfa7a6189b6ad93c9

Observation 9c0ae07a-b9d7-4497-acd9-a27346c868f9 · outbound

This paper cites C., and Lavie, A.

Conditional Unigram Tokenization with Parallel Data C., and Lavie, A

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.519581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.519581Z digest=sha256:a8c5b4b407b5343d25692a6a0e1edcec688e836c9b972850281bfb9e1905b9bf

Observation a8665cf7-5cfd-4b4a-929e-248b00747615 · outbound

This paper cites Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation.

Conditional Unigram Tokenization with Parallel Data Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.523916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.523916Z digest=sha256:03bf3621219746675a245ffb1d09c50815f533fa335f7a2a6b89023b01fdd5a1

Observation 4d79e9c4-25fe-4109-b931-7409933b5139 · outbound

This paper cites Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP.

Conditional Unigram Tokenization with Parallel Data Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.528703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.528703Z digest=sha256:dac2d8e554558ca6df3a4f9241131a9ccc58542904f61f341375a50631a95619

Observation 7bb0fe1d-d9b0-45db-95ca-30cfd322eb58 · outbound

This paper cites How Good is Your Tokenizer ? On the Monolingual Performance of Multilingual Language Models.

Conditional Unigram Tokenization with Parallel Data How Good is Your Tokenizer ? On the Monolingual Performance of Multilingual Language Models

Reference 26

Resolution
malformed identifier
no resolver link, observed 2026-08-06T18:35:44.533454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.533454Z digest=sha256:455c254ce3f564ed761c6019261ee91f3acc34f2e4027ea9b785a4bcd9a802a1

Observation 8df6990b-ccaf-428f-8535-be850487643d · outbound

This paper cites W., Reddy, V., Zhang, H., Alameddine, A., Uzan, O., Pinter, Y., and Tanner, C.

Conditional Unigram Tokenization with Parallel Data W., Reddy, V., Zhang, H., Alameddine, A., Uzan, O., Pinter, Y., and Tanner, C

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:44.928832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.538629Z digest=sha256:e07f395bc285c9d48562340aaee8e28708b13d5712791b973ea63142f8117c62

Observation 41589531-8b84-4d7b-945a-ea26408c880e · outbound

This paper cites Neural machine translation of rare words with subword units.

Conditional Unigram Tokenization with Parallel Data Neural machine translation of rare words with subword units

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.542993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.542993Z digest=sha256:0a56c278a06158613fc92e1d8d19da5128c34db565b50fcac1bce28eb0397b7c

Observation 457187fc-0531-45c3-883e-f8340b0676e3 · outbound

This paper cites N., Kaiser, ., and Polosukhin, I.

Conditional Unigram Tokenization with Parallel Data N., Kaiser, ., and Polosukhin, I

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:35:44.912397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.548767Z digest=sha256:f1c04c5e74cc558f3cbc71ed3be4d4f20f26f0c7ca38ce7bdc89b2ad4785f910

Observation b25b0c18-afce-4873-96ec-1c3513c7fb28 · outbound

This paper cites The U niversity of H elsinki submission to the WMT 19 parallel corpus filtering task.

Conditional Unigram Tokenization with Parallel Data The U niversity of H elsinki submission to the WMT 19 parallel corpus filtering task

Reference 30

Resolution
verified exact
doi, observed 2026-08-06T18:35:44.897215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-06T18:35:44.553635Z digest=sha256:600ea93ad6c92d10e750a17abfd1f17720431c1fdc0fe041714e49b296cce071

Observation 84b8d306-3a99-4b72-a2fc-cd6d3be95d2a · outbound

This paper cites Vocabulary learning via optimal transport for neural machine translation.

Conditional Unigram Tokenization with Parallel Data Vocabulary learning via optimal transport for neural machine translation

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.557893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.557893Z digest=sha256:f9bb16fde699863ec89097484d880b09b9d67f5086f03dd70fa630ad7f5350a6

Observation ff2a1ee5-93e3-4856-ae44-ed3d73095443 · outbound

This paper cites Tokenization and the Noiseless Channel.

Conditional Unigram Tokenization with Parallel Data Tokenization and the Noiseless Channel

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T18:35:44.562542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:35:44.562542Z digest=sha256:8b8b01f8136d11d27be2e176b354762f6770a023a7553e0881e0725f58f7d7e5

Pith citing papers

No inbound Pith citation observations are available.