{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J35VJDTMMGQ2ZLNP5KUSSJ6K64","short_pith_number":"pith:J35VJDTM","schema_version":"1.0","canonical_sha256":"4efb548e6c61a1acadafeaa92927caf731e0121853625f7d671cf5e44bcb20fb","source":{"kind":"arxiv","id":"2506.23678","version":1},"attestation_state":"computed","paper":{"title":"Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chu Li, Jeffrey Heer, Katharina Reinecke, K. J. Kevin Feng, Rock Yuren Pang, Shangbin Feng, Weijia Shi, Yulia Tsvetkov","submitted_at":"2025-06-30T10:00:43Z","abstract_excerpt":"The output quality of large language models (LLMs) can be improved via \"reasoning\": generating segments of chain-of-thought (CoT) content to further condition the model prior to producing user-facing output. While these chains contain valuable information, they are verbose and lack explicit organization, making them tedious to review. Moreover, they lack opportunities for user feedback, such as to remove unwanted considerations, add desired ones, or clarify unclear assumptions. We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.23678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-30T10:00:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7240eef2a1950af1455625a3bbc82da83194fc3233800f5fefcbc543e52fad01","abstract_canon_sha256":"ee9ee99775e1fc0bd5b7682239e01499ce6b4140fb99c4f98c07fd3b57ea55cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:26.239799Z","signature_b64":"Y296eay1H/nwhLV1UVd7Ld3edKtbu6h4z0EJ8B+kRkKnik8/mcWlfFoAGxdKIwwhFfw9Zao+PwiugbdOvNzdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4efb548e6c61a1acadafeaa92927caf731e0121853625f7d671cf5e44bcb20fb","last_reissued_at":"2026-07-05T11:29:26.239293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:26.239293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chu Li, Jeffrey Heer, Katharina Reinecke, K. J. Kevin Feng, Rock Yuren Pang, Shangbin Feng, Weijia Shi, Yulia Tsvetkov","submitted_at":"2025-06-30T10:00:43Z","abstract_excerpt":"The output quality of large language models (LLMs) can be improved via \"reasoning\": generating segments of chain-of-thought (CoT) content to further condition the model prior to producing user-facing output. While these chains contain valuable information, they are verbose and lack explicit organization, making them tedious to review. Moreover, they lack opportunities for user feedback, such as to remove unwanted considerations, add desired ones, or clarify unclear assumptions. We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23678","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.23678/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.23678","created_at":"2026-07-05T11:29:26.239362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23678v1","created_at":"2026-07-05T11:29:26.239362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23678","created_at":"2026-07-05T11:29:26.239362+00:00"},{"alias_kind":"pith_short_12","alias_value":"J35VJDTMMGQ2","created_at":"2026-07-05T11:29:26.239362+00:00"},{"alias_kind":"pith_short_16","alias_value":"J35VJDTMMGQ2ZLNP","created_at":"2026-07-05T11:29:26.239362+00:00"},{"alias_kind":"pith_short_8","alias_value":"J35VJDTM","created_at":"2026-07-05T11:29:26.239362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15455","citing_title":"Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21286","citing_title":"When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13221","citing_title":"An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00497","citing_title":"\"What Are You Really Trying to Do?\": Co-Creating Life Goals from Everyday Computer Use","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18724","citing_title":"Beyond One Output: Visualizing and Comparing Distributions of Language Model Generations","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64","json":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64.json","graph_json":"https://pith.science/api/pith-number/J35VJDTMMGQ2ZLNP5KUSSJ6K64/graph.json","events_json":"https://pith.science/api/pith-number/J35VJDTMMGQ2ZLNP5KUSSJ6K64/events.json","paper":"https://pith.science/paper/J35VJDTM"},"agent_actions":{"view_html":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64","download_json":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64.json","view_paper":"https://pith.science/paper/J35VJDTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23678&json=true","fetch_graph":"https://pith.science/api/pith-number/J35VJDTMMGQ2ZLNP5KUSSJ6K64/graph.json","fetch_events":"https://pith.science/api/pith-number/J35VJDTMMGQ2ZLNP5KUSSJ6K64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64/action/storage_attestation","attest_author":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64/action/author_attestation","sign_citation":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64/action/citation_signature","submit_replication":"https://pith.science/pith/J35VJDTMMGQ2ZLNP5KUSSJ6K64/action/replication_record"}},"created_at":"2026-07-05T11:29:26.239362+00:00","updated_at":"2026-07-05T11:29:26.239362+00:00"}