Paper Citation Record · LEDGER

Reverse Preference Optimization for Complex Instruction Following

As of 8 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2505.22172.

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

pith.paper-citation-record.v1
2505.22172 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:18:57.734597Z

measured 40 of 40 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

40 of 40 outbound references displayed

verified exact0
verified fuzzy22
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9513806a-6e7a-40e2-b601-d8526ece903b · outbound

This paper cites at least three profession-related keywords must appear.

Reverse Preference Optimization for Complex Instruction Following at least three profession-related keywords must appear

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:05.580600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1af06f0b-4997-450a-b8f0-0c575bed1b26 · outbound

This paper cites forbidden to mention Van Gogh.

Reverse Preference Optimization for Complex Instruction Following forbidden to mention Van Gogh

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:05.434577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 117c52f6-c68a-44c9-9a58-91b76d70a01b · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Reverse Preference Optimization for Complex Instruction Following Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:53.711122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 337f4419-0198-4ef6-96cb-98c581c6ecd9 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Reverse Preference Optimization for Complex Instruction Following Instruction-Following Evaluation for Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:53.809468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation add0ac66-20fa-41b1-a76b-06c3984ea237 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:04.372062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4cb95338-e2bf-4b4b-b214-802c8977d3e1 · outbound

This paper cites I don’t know,.

Reverse Preference Optimization for Complex Instruction Following I don’t know,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:04.142097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation df08c77c-fa3f-4d02-a4a6-9a8f679f3b7a · outbound

This paper cites Hello," a catchphrase, a specific line of poetry, self-introduction. - ‘Ending content‘ (used in a minority of cases, less than 15%): For example, ending with.

Reverse Preference Optimization for Complex Instruction Following Hello," a catchphrase, a specific line of poetry, self-introduction. - ‘Ending content‘ (used in a minority of cases, less than 15%): For example, ending with

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:05.238601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b68d5360-1b4b-4b24-8b61-a8538084a86b · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:05.023349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cd7888d4-f242-4e5d-84a1-529a899dadf2 · outbound

This paper cites (The constraints added here must not conflict with any possible character setting in the given character reference information, so please add such constraints cautiously).

Reverse Preference Optimization for Complex Instruction Following (The constraints added here must not conflict with any possible character setting in the given character reference information, so please add such constraints cautiously)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:04.774377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 620f12d2-aed3-4710-b3c0-034c5eec6483 · outbound

This paper cites we," or.

Reverse Preference Optimization for Complex Instruction Following we," or

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:04.581471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 464eee10-0c88-4b70-ad5a-c1a70ef5e131 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:03.938583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f4144ed3-ea54-42ac-972b-e10b5491bba1 · outbound

This paper cites Generate a vivid and three-dimensional description of the character based on the given reference information, with no less than 100 characters.

Reverse Preference Optimization for Complex Instruction Following Generate a vivid and three-dimensional description of the character based on the given reference information, with no less than 100 characters

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:03.751594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f84ddfce-6ab1-467d-8c5d-0d92b7ebe615 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:03.593665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 32ed0cff-e79f-459e-84b7-f184c7b41787 · outbound

This paper cites Generate 6 to 12 non-repetitive, non-conflicting, and distinctive constraints as needed.

Reverse Preference Optimization for Complex Instruction Following Generate 6 to 12 non-repetitive, non-conflicting, and distinctive constraints as needed

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:03.401122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8696cd7c-3e63-4415-a091-97954c6137ca · outbound

This paper cites Generate more constraints that can be objectively verified, even constraints that can be directly checked using Python code.

Reverse Preference Optimization for Complex Instruction Following Generate more constraints that can be objectively verified, even constraints that can be directly checked using Python code

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:03.133605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eff49090-2f1d-4cb5-b2e6-6d5a5bcce715 · outbound

This paper cites The provided system is just a reference and not complete.

Reverse Preference Optimization for Complex Instruction Following The provided system is just a reference and not complete

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:02.912190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2d520d36-e32c-4313-aaed-347af08f1d05 · outbound

This paper cites It is not necessary to generate constraints one by one according to the ontology.

Reverse Preference Optimization for Complex Instruction Following It is not necessary to generate constraints one by one according to the ontology

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:02.679546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 215cd836-02e2-41ca-b3b5-c6e40d627d87 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:02.511109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ce6e6658-cf38-4d1d-8f80-029b8141be02 · outbound

This paper cites if the user is silent for more than 30 seconds,.

Reverse Preference Optimization for Complex Instruction Following if the user is silent for more than 30 seconds,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:02.318524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2b26ac55-384c-4128-9377-19a127caf511 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:02.073448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2a32f733-bb72-4434-aec4-5e80aacf2b68 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:01.839511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5e52ba47-932f-480c-8c0c-0c04e3203000 · outbound

This paper cites For each question raised by the user, include a specific case or story in the response for added persuasive effect.

Reverse Preference Optimization for Complex Instruction Following For each question raised by the user, include a specific case or story in the response for added persuasive effect

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:01.669869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 189d7af8-95f7-4d46-9554-9d19980ae796 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:01.467541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 96fb76d0-9e89-4899-9636-bbcefe24753d · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:01.274003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e04f1af6-45df-4aee-b4e6-02ab924f32b1 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:01.108472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c6b9bb73-7344-4fac-9b83-af0dcc6b12b5 · outbound

This paper cites When users mention sustainable development, you must mention at least one relevant success case.

Reverse Preference Optimization for Complex Instruction Following When users mention sustainable development, you must mention at least one relevant success case

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:00.941615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 060972e1-3833-4ece-b9f2-0262104ead90 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:19:00.755702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a07116fb-e78e-4e5a-b6db-612ee389739b · outbound

This paper cites Please design the user’s query (query) for the next round of dialogue based on the provided information.

Reverse Preference Optimization for Complex Instruction Following Please design the user’s query (query) for the next round of dialogue based on the provided information

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:00.527876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e136d146-68bf-44aa-90f0-9763bb51cd1d · outbound

This paper cites Use more colloquial expressions, fewer overly formal expressions.

Reverse Preference Optimization for Complex Instruction Following Use more colloquial expressions, fewer overly formal expressions

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:00.380387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7a9e8ec0-c4bc-465f-aab6-8ce2330d44b2 · outbound

This paper cites Hey", "I’m thinking.

Reverse Preference Optimization for Complex Instruction Following Hey", "I’m thinking

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:19:00.162687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 96329fdb-ab8a-40b7-89e9-3da101aee0d8 · outbound

This paper cites You can choose any tone to generate queries, including but not limited to: characteristic, etc., or combinations of these tones (but tones cannot conflict with each other).

Reverse Preference Optimization for Complex Instruction Following You can choose any tone to generate queries, including but not limited to: characteristic, etc., or combinations of these tones (but tones cannot conflict with each other)

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:59.969899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2c1bf120-3695-4667-aa78-8c5a3b03d28d · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:18:59.703697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1752ca5d-e9f6-4e40-8ff2-660975f856a3 · outbound

This paper cites You cannot directly copy their name exactly to address them, as that’s too mechanical and unlike normal human expression.

Reverse Preference Optimization for Complex Instruction Following You cannot directly copy their name exactly to address them, as that’s too mechanical and unlike normal human expression

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:59.417751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 22b8b2bc-8b97-452f-b852-e2320c7a81cc · outbound

This paper cites ### In terms of query content: 1.

Reverse Preference Optimization for Complex Instruction Following ### In terms of query content: 1

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:59.148907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5515b4fa-1697-4c78-9ff5-8c6d24322683 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:18:58.817992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac15094a-3069-4102-994f-0be8aba9eb7c · outbound

This paper cites Since you just mentioned xx is interesting.

Reverse Preference Optimization for Complex Instruction Following Since you just mentioned xx is interesting

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:58.531235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 87baa248-cc71-4392-b408-954bb91bb866 · outbound

This paper cites an unresolved cited work.

Reverse Preference Optimization for Complex Instruction Following Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:18:58.291142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a70b06db-1cc5-4f23-b08b-6a864f08501d · outbound

This paper cites When describing AI application scenarios, at least one metaphor must be used,.

Reverse Preference Optimization for Complex Instruction Following When describing AI application scenarios, at least one metaphor must be used,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:58.037195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1c5e7746-b9f1-4ff3-a8cb-32c7370877db · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Reverse Preference Optimization for Complex Instruction Following Training Verifiers to Solve Math Word Problems

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:53.503242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a55b51-9bf6-4e65-b312-ba29c098f6e3 · outbound

This paper cites Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models.

Reverse Preference Optimization for Complex Instruction Following Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:53.599656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.