Paper Citation Record · LEDGER

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval

As of 9 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2608.06060.

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

pith.paper-citation-record.v1
2608.06060 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T18:30:14.608010Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

17 of 17 outbound references displayed

verified exact0
verified fuzzy0
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7f1dddab-eb44-4019-8c3f-db21b1a3070f · outbound

This paper cites MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.527131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 742b9810-5892-4143-b4ab-5b95769784c3 · outbound

This paper cites Embed-rl: Reinforcement learning for reasoning-driven multimodal embeddings.arXiv preprint arXiv:2602.13823,.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Embed-rl: Reinforcement learning for reasoning-driven multimodal embeddings.arXiv preprint arXiv:2602.13823,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.550576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c57ff9-17ae-4ee2-a47f-c7cc6957cb82 · outbound

This paper cites VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.554873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba9a618-5492-42cf-be31-7c0106c94e0c · outbound

This paper cites Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.559722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d6f7373-29c3-4b45-b6a1-990da47f48b2 · outbound

This paper cites Ume-r1: Exploring reasoning- driven generative multimodal embeddings.arXiv preprint arXiv:2511.00405,.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Ume-r1: Exploring reasoning- driven generative multimodal embeddings.arXiv preprint arXiv:2511.00405,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.564287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab78b92b-216d-47a3-bc02-d8a657440da9 · outbound

This paper cites VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.572507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85f421ea-4091-4a7b-82a6-397c160dea31 · outbound

This paper cites VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.584902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6135702c-b638-46ac-b88a-cda1b3231667 · outbound

This paper cites MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.590920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad2330b3-fa39-44ba-99bb-fd0df4870258 · outbound

This paper cites Qwen3 Technical Report.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Qwen3 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.598702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5ffab50-e40f-431a-a8d9-172804f68d5a · outbound

This paper cites GME: Improving Universal Multimodal Retrieval by Multimodal LLMs.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.603232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f1fb02-e0e9-475e-aa65-791472167c6d · outbound

This paper cites MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.608010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6efd0bf0-e9c2-4c1d-9862-307840b2d3d5 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.577817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422daba4-f477-4d6d-80ae-2107f7d2da6a · outbound

This paper cites Rzenembed: Towards comprehensive multimodal retrieval.arXiv preprint arXiv:2510.27350,.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Rzenembed: Towards comprehensive multimodal retrieval.arXiv preprint arXiv:2510.27350,

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.545936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 285969cf-af0f-4145-9132-eb5211656639 · outbound

This paper cites Rematch: Boosting representation through matching for multimodal retrieval.arXiv preprint arXiv:2511.19278, 2025a.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Rematch: Boosting representation through matching for multimodal retrieval.arXiv preprint arXiv:2511.19278, 2025a

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.568558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2baeb1c9-e4c8-4cba-a3e4-4d3d9e67e6e8 · outbound

This paper cites Think then embed: Generative context improves multimodal embedding.arXiv preprint arXiv:2510.05014,.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Think then embed: Generative context improves multimodal embedding.arXiv preprint arXiv:2510.05014,

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.532201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d898673-6972-4693-bf25-bfa801d33b80 · outbound

This paper cites ColPali: Efficient Document Retrieval with Vision Language Models.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval ColPali: Efficient Document Retrieval with Vision Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.536725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4e211a-a7be-4b94-afdd-2a8fbb05409f · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-07T18:30:14.541475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.