Paper Citation Record · LEDGER

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning

As of 7 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2607.22996.

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

pith.paper-citation-record.v1
2607.22996 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T04:00:54.997773Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

19 of 19 outbound references displayed

verified exact0
verified fuzzy0
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a28832b8-786c-4f28-835e-fa85a29f33d3 · outbound

This paper cites GPT-4 Technical Report.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.939835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b2dffd-c3e2-489f-ae3f-d0d9bacef4ca · outbound

This paper cites Addison Wesley Longman, Inc.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning Addison Wesley Longman, Inc

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.944418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d031f8-9a0a-4af7-b8bb-431945942992 · outbound

This paper cites Handbook 1: Cognitive domain.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning Handbook 1: Cognitive domain

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.947754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0514c1df-1f5e-4680-8a83-3c25ae562808 · outbound

This paper cites IEEE Transactions on Education 48(4), 612–618 (2005).

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning IEEE Transactions on Education 48(4), 612–618 (2005)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.951100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc6b65db-6aa4-44fe-842b-811eeaf6f6a1 · outbound

This paper cites In: HGAIS@ ISWC (2024).

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: HGAIS@ ISWC (2024)

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.954431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2557b7f1-2458-41cc-bfed-92ea4d90e849 · outbound

This paper cites In: International Conference on Learning Representations.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: International Conference on Learning Representations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.958006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d59d26da-0620-49bc-ba2d-e93034b74acf · outbound

This paper cites In: Text summarization branches out.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: Text summarization branches out

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.961399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d842d21a-1454-473c-ac49-e2a926e24c4b · outbound

This paper cites arXiv preprint arXiv:2508.06583 (2025).

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning arXiv preprint arXiv:2508.06583 (2025)

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.964373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5999ecfe-c60d-4b5b-94bd-846cfd0e9548 · outbound

This paper cites In: Findings of the Association for Computational Linguistics: EMNLP 2023.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: Findings of the Association for Computational Linguistics: EMNLP 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.967429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b2fc866-584a-48d4-89fd-b214e73a1ae0 · outbound

This paper cites In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.970153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26b3d22a-b454-4ce6-ac57-ef4d7a4219d0 · outbound

This paper cites Advances in neural information processing systems35, 27730–27744 (2022).

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning Advances in neural information processing systems35, 27730–27744 (2022)

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.972904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1848c2a5-4421-4783-9980-d891baf5b47e · outbound

This paper cites In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.975744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eb3251b-39a2-44fc-81cb-d2645cb7628d · outbound

This paper cites In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP).

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP)

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.979022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c0f9505-bd6c-4103-9acf-3d2b73cf73e9 · outbound

This paper cites In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.982121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f52e00ed-97c1-43f9-a3f0-b4a27a4d85d9 · outbound

This paper cites Simulated Students in Tutoring Dialogues: Substance or Illusion?.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning Simulated Students in Tutoring Dialogues: Substance or Illusion?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.984768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba13ca8b-8c8b-47ba-b7ed-316bcf040b86 · outbound

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

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.988084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce6b6d91-1879-4855-962e-645e52ebe9b4 · outbound

This paper cites The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.991558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cc5f055-9f18-4687-ac23-aec4a34e87b5 · outbound

This paper cites an unresolved cited work.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.994742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dfdbb62-80a9-4e68-8f97-759ead65877b · outbound

This paper cites Emergent Abilities of Large Language Models.

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning Emergent Abilities of Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T04:00:54.997773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.