{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TF23MJVUXP6K5SOV35BI45AZG2","short_pith_number":"pith:TF23MJVU","schema_version":"1.0","canonical_sha256":"9975b626b4bbfcaec9d5df428e741936b2a0cba2977d27a61e719852e49cb69c","source":{"kind":"arxiv","id":"2505.11107","version":1},"attestation_state":"computed","paper":{"title":"Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chan-Jan Hsu, Da-shan Shiu, Davide Buffelli, Feng-Ting Liao, Jamie McGowan, Sattar Vakili, Yi-Chang Chen","submitted_at":"2025-05-16T10:40:35Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to raise joint reasoning quality above individual outcomes. However, such agents typically interact in a turn-based manner, trading increased latency for improved quality. In this paper, we propose Group Think--a single LLM that acts as multiple concurrent reasoning agents, or thinkers. With shared visibility into each other's partial generation progress, Group Think introduces a new concurrent-reasoning paradigm in which m"},"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":"2505.11107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T10:40:35Z","cross_cats_sorted":[],"title_canon_sha256":"78a72cbbeb30c5c5c871acceebe438cbf809637411f3f6a1ab4db0e8eea94e3c","abstract_canon_sha256":"dadcb62ae6192c334ad5a1982dbe87367195cfbd15d7686fe017b2284d6f157f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:10.948876Z","signature_b64":"H1VP5vlma4JwCmSLBg29jefKtWl1Q4/u29+nJKsM0nDmdlkGK4btvx2leDYS0EZo1BNf5Fij4FSO4Y1O7YhyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9975b626b4bbfcaec9d5df428e741936b2a0cba2977d27a61e719852e49cb69c","last_reissued_at":"2026-07-05T11:04:10.948429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:10.948429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chan-Jan Hsu, Da-shan Shiu, Davide Buffelli, Feng-Ting Liao, Jamie McGowan, Sattar Vakili, Yi-Chang Chen","submitted_at":"2025-05-16T10:40:35Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to raise joint reasoning quality above individual outcomes. However, such agents typically interact in a turn-based manner, trading increased latency for improved quality. In this paper, we propose Group Think--a single LLM that acts as multiple concurrent reasoning agents, or thinkers. With shared visibility into each other's partial generation progress, Group Think introduces a new concurrent-reasoning paradigm in which m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11107","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/2505.11107/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":"2505.11107","created_at":"2026-07-05T11:04:10.948493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11107v1","created_at":"2026-07-05T11:04:10.948493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11107","created_at":"2026-07-05T11:04:10.948493+00:00"},{"alias_kind":"pith_short_12","alias_value":"TF23MJVUXP6K","created_at":"2026-07-05T11:04:10.948493+00:00"},{"alias_kind":"pith_short_16","alias_value":"TF23MJVUXP6K5SOV","created_at":"2026-07-05T11:04:10.948493+00:00"},{"alias_kind":"pith_short_8","alias_value":"TF23MJVU","created_at":"2026-07-05T11:04:10.948493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03102","citing_title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27570","citing_title":"LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17672","citing_title":"Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2","json":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2.json","graph_json":"https://pith.science/api/pith-number/TF23MJVUXP6K5SOV35BI45AZG2/graph.json","events_json":"https://pith.science/api/pith-number/TF23MJVUXP6K5SOV35BI45AZG2/events.json","paper":"https://pith.science/paper/TF23MJVU"},"agent_actions":{"view_html":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2","download_json":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2.json","view_paper":"https://pith.science/paper/TF23MJVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11107&json=true","fetch_graph":"https://pith.science/api/pith-number/TF23MJVUXP6K5SOV35BI45AZG2/graph.json","fetch_events":"https://pith.science/api/pith-number/TF23MJVUXP6K5SOV35BI45AZG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2/action/storage_attestation","attest_author":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2/action/author_attestation","sign_citation":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2/action/citation_signature","submit_replication":"https://pith.science/pith/TF23MJVUXP6K5SOV35BI45AZG2/action/replication_record"}},"created_at":"2026-07-05T11:04:10.948493+00:00","updated_at":"2026-07-05T11:04:10.948493+00:00"}