Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-25T07:41:38.513152Z
Paper Citation Record · LEDGER
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
As of 6 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 1 inbound Pith citation observation for arXiv:2510.00526.
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 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-10T18:28:58.515666Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-11T00:30:53.546973Z
Reference resolution
22 of 22 outbound references displayed
- verified exact0
- verified fuzzy6
- unresolved16
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 182d7cb3-a1ed-4877-9687-437534648298 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.866521Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2ef103cc-a80e-4da6-ab6a-89a689c08c9e · outbound
This paper cites Then max q∈∆V−1 F(q) = 11 √ 33−59 768 ≤0.00546, and the maximizer is attained by a vector with qi =q j = 9− √ 33 24 ,all remaining mass1−2q i placed on one coordinate.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Then max q∈∆V−1 F(q) = 11 √ 33−59 768 ≤0.00546, and the maximizer is attained by a vector with qi =q j = 9− √ 33 24 ,all remaining mass1−2q i placed on one coordinate
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T07:46:43.910694Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7acf9f7a-8f61-4cd7-8d13-b4ea4fd095a8 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.923047Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5f453720-012b-407b-80c7-d96696c94cf8 · outbound
This paper cites Substituting and simplifying, max q∈∆V−1 F(q) =G(x ⋆) = 11 √ 33−59 768 ≤0.00546.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Substituting and simplifying, max q∈∆V−1 F(q) =G(x ⋆) = 11 √ 33−59 768 ≤0.00546
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T07:46:43.935938Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c226ba57-eb42-40e3-953c-2f4b1633565b · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 5
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.939570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 21a36db4-d6fc-44cb-b564-cec8a4123560 · outbound
This paper cites • ˙R(θ(1) t ) t=0 ≤ ˙R(θ(2) t ) t=0 in Model Weak End.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum • ˙R(θ(1) t ) t=0 ≤ ˙R(θ(2) t ) t=0 in Model Weak End
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T07:46:43.944845Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f2de253f-1c32-4b15-8560-809be80ea72b · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 7
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.927303Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f32419b0-1819-400c-b7f8-9c6d977deb55 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.856090Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 22218665-224b-4281-8d29-7cb8c03a7027 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.917368Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation aeca0771-0669-4902-ad6e-1ef76609097d · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.880111Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ad5e230b-1b7a-4b92-aa48-ad5e2e135041 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.883811Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 74446913-8880-475c-8ffa-fbee1110b7b3 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.905949Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6c45d53e-2e27-494a-80a9-91aefea34454 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 13
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.895821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e7590d63-aac1-40bb-bc43-e85d8ba9c4e8 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.907530Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6ed42eb2-0cc9-45c8-9215-2133b67a383e · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 15
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.893510Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3b5dd3a2-a958-420f-85f5-750a9d35456c · outbound
This paper cites Denote the label noise rate to beE.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Denote the label noise rate to beE
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T07:46:43.911338Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3ab523ca-ae29-49d6-a372-9f36e6baf09b · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 17
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.898493Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0a6dd900-6202-4501-a53c-8093edc1b9ff · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 18
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.949181Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8d418451-5bbb-4015-a807-065976140735 · outbound
This paper cites 1 E Ex h q˜yqy∗ (f ′ 2 −f ′.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum 1 E Ex h q˜yqy∗ (f ′ 2 −f ′
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T07:46:43.870721Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7a2d0e4f-0735-45b2-a039-974997f72089 · outbound
This paper cites 5, we have that givenQ <0, min 0.95≥q ˜y+qy∗ ≥0.55 |Q| ≤ −max 0.95≥q ˜y+qy∗ ≥0.55 1 + 2(q˜y+q y∗)2 −3(q ˜y+q y∗)≤0.045 Also by Assumpion.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum 5, we have that givenQ <0, min 0.95≥q ˜y+qy∗ ≥0.55 |Q| ≤ −max 0.95≥q ˜y+qy∗ ≥0.55 1 + 2(q˜y+q y∗)2 −3(q ˜y+q y∗)≤0.045 Also by Assumpion
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-25T07:46:43.931873Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4fc04d83-0db5-49a0-9dd6-50f12af0f7f5 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.875667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8c4a213e-a27b-447e-bf85-63c9217764d1 · outbound
This paper cites an unresolved cited work.
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Unresolved cited work
Reference 22
- Resolution
- unresolved
- raw_fallback, observed 2026-05-25T07:46:43.875455Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
Observation 68d7d5b9-93b3-4089-8a19-d8225f32db37 · inbound
Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning cites this paper.
Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Reference 129
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T03:01:06.856807Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.