Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T19:14:56.145852Z
Paper Citation Record · LEDGER
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
As of 11 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 4 inbound Pith citation observations for arXiv:2507.06187.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-10T18:11:50.571844Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Reference resolution
17 of 17 outbound references displayed
- verified exact0
- verified fuzzy10
- unresolved7
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 6a2fb232-df05-4d9e-9e69-45f43cdef048 · outbound
This paper cites math, code), we find pairs where Qwen 3B responds correctly but Qwen 1.5B does not (Figure A2).
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains math, code), we find pairs where Qwen 3B responds correctly but Qwen 1.5B does not (Figure A2)
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:15:00.118175Z
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 37ce8142-7b6a-4e94-b2c4-6ece943fe743 · outbound
This paper cites an unresolved cited work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Unresolved cited work
Reference 2
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T19:14:59.898463Z
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 3b326221-4129-41d1-8ba9-2ebbf244483b · outbound
This paper cites Note that these deltas are not exhaustive ; we simply highlight a few here as interesting examples to motivate future work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Note that these deltas are not exhaustive ; we simply highlight a few here as interesting examples to motivate future work
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:59.594108Z
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 39106cc7-a3bd-4d42-9b97-0210770f725d · outbound
This paper cites First, let’s calculate the total number of cupcakes Dani brought.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains First, let’s calculate the total number of cupcakes Dani brought
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:57.289238Z
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 68414a29-b03d-4a54-9af3-6a1c2df9b00e · outbound
This paper cites backbone.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains backbone
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:59.299278Z
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 3aedc4d3-add6-44da-bb04-25439ca7954b · outbound
This paper cites Standard tail bounds due to Laurent & Massart (2000) give that Pr x(t,i) 2 ≥ 4 √ d ≤ e−4d.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Standard tail bounds due to Laurent & Massart (2000) give that Pr x(t,i) 2 ≥ 4 √ d ≤ e−4d
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:59.052134Z
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 f4f88643-13c0-43a9-ba53-dd37bcb2950f · outbound
This paper cites (50) Then by Lemma F.2, for any δ2 ∈ (0, 1) we have with probability at least 1 − δ2 T ∑ i=1 ζt 2 ≤ s 2dT B ln d + 1 δ2 + 4 √ d ln d + 1 δ2.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains (50) Then by Lemma F.2, for any δ2 ∈ (0, 1) we have with probability at least 1 − δ2 T ∑ i=1 ζt 2 ≤ s 2dT B ln d + 1 δ2 + 4 √ d ln d + 1 δ2
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:58.815388Z
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 b8821b52-fa1b-4972-a25e-4c6b5eb17695 · outbound
This paper cites G.2 Pilot Study on U LTRA FEEDBACK -WEAK Data and filtering.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains G.2 Pilot Study on U LTRA FEEDBACK -WEAK Data and filtering
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:58.486504Z
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 18283c0c-bbdf-44a7-b1a1-7765a011e8d9 · outbound
This paper cites an unresolved cited work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T19:14:57.982284Z
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 d60d945e-9dd0-48f2-ac82-7e3c2e52bddf · outbound
This paper cites an unresolved cited work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T19:14:57.780147Z
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 bc47611d-7ea8-4464-863e-124de54ed609 · outbound
This paper cites an unresolved cited work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T19:14:57.517980Z
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 92d495d9-db1c-4a6d-b78d-07b78d943f39 · outbound
This paper cites This migration involved groups moving into Europe, the Middle East, and eventually Asia.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains This migration involved groups moving into Europe, the Middle East, and eventually Asia
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:57.041833Z
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 159c9b34-aedb-4cfd-b613-7a79fd06ad3c · outbound
This paper cites an unresolved cited work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Unresolved cited work
Reference 15
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T19:14:56.778819Z
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 ab3a4335-4dac-473d-b99a-e4b0a4c32d7e · outbound
This paper cites an unresolved cited work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T19:14:56.527202Z
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 4dc56044-df36-41e4-b428-c3fc78584584 · outbound
This paper cites an unresolved cited work.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Unresolved cited work
Reference 17
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T19:14:56.314766Z
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 d3040673-83c2-4a54-95ea-9bcc78591980 · outbound
This paper cites Include bolded sections in your re- sponse.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains Include bolded sections in your re- sponse
Reference 1100
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:14:58.259874Z
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 b36142f3-9f9c-4f5f-a30c-e2bdecdeb233 · outbound
This paper cites weak responses.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains weak responses
Reference 2024
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T19:15:00.366527Z
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 1c90ee3f-7a6f-4f96-93ad-8c500b62a840 · inbound
Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models) cites this paper.
Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models) The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T18:41:09.049645Z
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 a6063add-cbbc-4559-a14d-675d7245b70a · inbound
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher cites this paper.
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
Reference 44
- Resolution
- verified exact
- arxiv_id, observed 2026-06-28T17:42:24.952269Z
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 fb343c3f-3a6c-4328-8c45-dac17b21d3fc · inbound
Bridging Expert Knowledge and Automated Feature Engineering via Self-Evolution cites this paper.
Bridging Expert Knowledge and Automated Feature Engineering via Self-Evolution The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T22:57:26.451974Z
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 3a3848f3-e475-4b3c-b983-4fa9d7185d29 · inbound
Ask-E: An Environment for Calibrated Question Generation cites this paper.
Ask-E: An Environment for Calibrated Question Generation The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T18:11:50.571844Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.