Paper Citation Record · LEDGER

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings

As of 11 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 2 inbound Pith citation observations for arXiv:2606.23475.

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

pith.paper-citation-record.v1
2606.23475 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T06:16:51.174659Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:03:02.277559Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T00:05:48.084953Z

Reference resolution

14 of 14 outbound references displayed

verified exact11
verified fuzzy0
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cfd76aa3-e834-481c-8b17-41ac3d791513 · outbound

This paper cites On strengths and limitations of single-vector embeddings.arXiv preprint arXiv:2603.29519,.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings On strengths and limitations of single-vector embeddings.arXiv preprint arXiv:2603.29519,

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:39:49.792088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ff40a0a3-e711-4b55-a711-f54d755b742a · outbound

This paper cites MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-04T12:39:49.789307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c13d6a93-816f-4780-aae9-337fcbc263a8 · outbound

This paper cites Colpali: Efficient document retrieval with vision language models.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings Colpali: Efficient document retrieval with vision language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T06:16:51.174659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81eec09f-f63f-41e3-b206-22e182d109ac · outbound

This paper cites COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T12:39:49.795061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e7fd8322-dd93-488a-b52f-1fd729f24306 · outbound

This paper cites Approximate Algorithms for Chamfer Distance Under Translation.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings Approximate Algorithms for Chamfer Distance Under Translation

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-04T12:39:49.783571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6a24d36c-b1ed-45d8-8378-c02fab6d388c · outbound

This paper cites Break- ing the curse of dimensionality: On the stability of modern vector retrieval.arXiv preprint arXiv:2512.12458,.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings Break- ing the curse of dimensionality: On the stability of modern vector retrieval.arXiv preprint arXiv:2512.12458,

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:39:49.800519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c4736170-74e4-4f71-b3df-fd01a616f9a9 · outbound

This paper cites MTEB: Massive Text Embedding Benchmark.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings MTEB: Massive Text Embedding Benchmark

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-04T12:39:49.805327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ace4a8e1-e6a4-4079-997d-5e17814afbf5 · outbound

This paper cites Efficient Multi-Vector Dense Retrieval Using Bit Vectors.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings Efficient Multi-Vector Dense Retrieval Using Bit Vectors

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:39:49.786884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 20c8f934-31d1-44a5-a2af-f803e3457456 · outbound

This paper cites Multi-Vector Retrieval as Sparse Alignment.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings Multi-Vector Retrieval as Sparse Alignment

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:39:49.778585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 84dcca59-99ab-4825-b206-463a4b5b32c0 · outbound

This paper cites ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:39:49.781109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation aa62ac6e-0c3a-4e0c-9d5f-aea6dbc37abe · outbound

This paper cites On the theoretical limitations of embedding-based retrieval.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings On the theoretical limitations of embedding-based retrieval

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:39:49.808184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 88c8fa89-3ef3-4e44-84d6-4972aeab72c6 · outbound

This paper cites Pseudo-relevance feedback for multiple representation dense retrieval.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings Pseudo-relevance feedback for multiple representation dense retrieval

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-26T06:16:51.174659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0994651-052d-49b9-90dc-93bc2c9e2906 · outbound

This paper cites FILIP: Fine-grained Interactive Language-Image Pre-Training.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings FILIP: Fine-grained Interactive Language-Image Pre-Training

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:39:49.797760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e3d58c49-272c-4e01-a9b6-75689b665d34 · outbound

This paper cites Neural Information Retrieval: A Literature Review.

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings Neural Information Retrieval: A Literature Review

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-04T12:39:49.803001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

Observation 2e870047-cb93-4562-bc09-52846cd6bcbe · inbound

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models cites this paper.

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-09T00:05:48.086399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e21b64fe-e7d1-47ae-8471-4d983116b108 · inbound

Near-Optimal Dimension Lower Bounds for Single-Vector Embeddings of Maximum Inner Product Similarity cites this paper.

Near-Optimal Dimension Lower Bounds for Single-Vector Embeddings of Maximum Inner Product Similarity Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T10:03:02.277559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.