Paper Citation Record · LEDGER

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

As of 21 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 3 inbound Pith citation observations for arXiv:2505.04560.

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

pith.paper-citation-record.v1
2505.04560 v3

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:32:58.224956Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T16:20:17.727753Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T10:39:45.633252Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy11
unresolved2
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e8eca142-0432-4e5f-88d3-3695167bdccd · outbound

This paper cites Ify1 andy2 are such thatδ1 <q t(y1) =q t(y2)≤p(y 1) (whereδ1 >0 ), andp(y1)≥p(y 2) +ζ , it holds that∆α1 t (y1,y 2)≥∆ α2 t (y1,y 2).

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence Ify1 andy2 are such thatδ1 <q t(y1) =q t(y2)≤p(y 1) (whereδ1 >0 ), andp(y1)≥p(y 2) +ζ , it holds that∆α1 t (y1,y 2)≥∆ α2 t (y1,y 2)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.470546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3459fa8b-950d-472b-add9-9ec75fc2c870 · outbound

This paper cites If y1 andy2 are such that p(y1)< qt(y1) =q t(y2)≤1−δ 2, but p(y1)≥p(y 2) +ζ , then, ∆r t (y1,y 2)> ∆f t (y1,y 2).

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence If y1 andy2 are such that p(y1)< qt(y1) =q t(y2)≤1−δ 2, but p(y1)≥p(y 2) +ζ , then, ∆r t (y1,y 2)> ∆f t (y1,y 2)

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.439676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 40a9f78b-4124-4f77-b89b-79ef193912ba · outbound

This paper cites The proof is in App.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence The proof is in App

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.484984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 15827d17-3b23-4519-8f41-a73cd3f0edf7 · outbound

This paper cites Ify1 andy2 are such thatqt(y2) +ζ≤q t(y1)≤1−δ 2, andc0·qt(y2)<p(y 1) =p(y 2)<c 1·qt(y1), wherec0 and c1 are constants withc 0 >1andc 1 <1, then,∆ r t (y1,y 2)>∆ f t (y1,y 2).

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence Ify1 andy2 are such thatqt(y2) +ζ≤q t(y1)≤1−δ 2, andc0·qt(y2)<p(y 1) =p(y 2)<c 1·qt(y1), wherec0 and c1 are constants withc 0 >1andc 1 <1, then,∆ r t (y1,y 2)>∆ f t (y1,y 2)

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.408040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 06e7c6dd-2d6e-4242-82fe-da6b0055050d · outbound

This paper cites Ify1 andy2 are such that δ1 < qt(y1) =q t(y2)< p(y 1) (whereδ1 >0,δ 2 >0 ), but p(y1)≥p(y 2) +ζ , then, ∆r t (y1,y 2)>∆ f t (y1,y 2).

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence Ify1 andy2 are such that δ1 < qt(y1) =q t(y2)< p(y 1) (whereδ1 >0,δ 2 >0 ), but p(y1)≥p(y 2) +ζ , then, ∆r t (y1,y 2)>∆ f t (y1,y 2)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.455258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 993e4e09-b336-42d0-904d-2d9a9e0e616d · outbound

This paper cites If y1 andy2 are such that qt(y2) +ζ≤q t(y1)≤1−δ 2, and p(y1) =p(y 2)> c 0·qt(y1), wherec0 is a positive constant>1, then,∆ r t (y1,y 2)>∆ f t (y1,y 2).

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence If y1 andy2 are such that qt(y2) +ζ≤q t(y1)≤1−δ 2, and p(y1) =p(y 2)> c 0·qt(y1), wherec0 is a positive constant>1, then,∆ r t (y1,y 2)>∆ f t (y1,y 2)

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.424195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6c9bd6a8-c1d2-427a-a8f0-f75fc1e60589 · outbound

This paper cites (36) Simplifying: ∂q(i) ∂f(i) =q(i)(1−q(i)).(37).

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence (36) Simplifying: ∂q(i) ∂f(i) =q(i)(1−q(i)).(37)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.392427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 51cee0a9-0c3c-44c1-afcb-d633cab0a4d2 · outbound

This paper cites q(y) 1−α (p(y)α−q(y) α) +q(y) X k q(k) 1−α(q(k)α−p(k)α) !#! .(47) Taking the logarithm on both sides, we get: logqα t+1(y) qt(y) =η.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence q(y) 1−α (p(y)α−q(y) α) +q(y) X k q(k) 1−α(q(k)α−p(k)α) !#! .(47) Taking the logarithm on both sides, we get: logqα t+1(y) qt(y) =η

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.376293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation de502133-de94-428d-88da-c3bd310a0d66 · outbound

This paper cites an unresolved cited work.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:32:58.358555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 39e346fc-a2ca-4425-b15f-080d5475d328 · outbound

This paper cites Moreover, for allp(y1)> c0, it holds that f(p(y 1))<0.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence Moreover, for allp(y1)> c0, it holds that f(p(y 1))<0

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.343184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0438db78-f617-420a-8792-1ac5e1ef2d5a · outbound

This paper cites X k q(k) 1−α (q(k)α−p(k)α) # . (121) Consideringf(α)≜∆ α(y1,y 2)/η, taking the derivative with respect toαyields: f′(α) = 1 α2.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence X k q(k) 1−α (q(k)α−p(k)α) # . (121) Consideringf(α)≜∆ α(y1,y 2)/η, taking the derivative with respect toαyields: f′(α) = 1 α2

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.327081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5d60ce0a-2813-4cb4-b209-52fc067ae3c2 · outbound

This paper cites Proof.First, we prove Case 1.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence Proof.First, we prove Case 1

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:58.311644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a09273f2-c889-4b91-a6b9-5d9cd8f94e3f · outbound

This paper cites f-Divergence Minimization for Sequence-Level Knowledge Distillation.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence f-Divergence Minimization for Sequence-Level Knowledge Distillation

Reference 340

Resolution: malformed identifier; no resolver link, observed 2026-08-15T23:32:58.154253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 839dc3fe-7bde-4790-bc74-54c7b8c0fe46 · outbound

This paper cites Sequence-Level Knowledge Distillation.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence Sequence-Level Knowledge Distillation

Reference 364

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:58.148277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7c65cdb-5602-425b-ae37-afdcda639d35 · outbound

This paper cites a photo of a{classname}.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence a photo of a{classname}

Reference 2023

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T23:32:58.296972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 1b28718b-df86-446b-9849-7abe7f5aa53e · inbound

Balancing Multimodal Learning through Label Space Reshaping cites this paper.

Balancing Multimodal Learning through Label Space Reshaping ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-06-30T16:24:55.682605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1a7d23ba-bd5a-4dc7-97bb-009202c9d384 · inbound

BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation cites this paper.

BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T04:56:39.148582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fdb004bb-8a7a-4662-87d3-2d34822da537 · inbound

PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation cites this paper.

PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:39:45.635129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.