{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7UDAQK3XJ4RC27L3TSO7WRTVIG","short_pith_number":"pith:7UDAQK3X","schema_version":"1.0","canonical_sha256":"fd06082b774f222d7d7b9c9dfb467541a7575580e7e06cb918e2876f027db2af","source":{"kind":"arxiv","id":"2506.13192","version":1},"attestation_state":"computed","paper":{"title":"Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bangyi Wu, Junzhao Jin, Liwei Li, Meiru Zhang, Shang Xiao, Xintong Tang, Yang Zheng, Zihan Zhao","submitted_at":"2025-06-16T07:59:51Z","abstract_excerpt":"Large language models (LLMs) are often constrained by rigid reasoning processes, limiting their ability to generate creative and diverse responses. To address this, a novel framework called LADDER is proposed, combining Chain-of-Thought (CoT) reasoning, Mixture of Experts (MoE) models, and multi-dimensional up/down-sampling strategies which breaks the limitations of traditional LLMs. First, CoT reasoning guides the model through multi-step logical reasoning, expanding the semantic space and breaking the rigidity of thought. Next, MoE distributes the reasoning tasks across multiple expert modul"},"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":"2506.13192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T07:59:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80e1f089baed02fccca1b3094681aa585b6ccf0fef36c055631ece4656187cee","abstract_canon_sha256":"5add27716c5a2f9b77a67de5b788051e8a75c4be1ab90d9d264c3f9f41a7d91d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:06.580837Z","signature_b64":"VGxrgkzgi91Lw+YRAJcPuhq3mRFv+BJUU1QPcL1kq2odUczyWZZFXqakkPyeW+KexQ1/4HUHe/JyxtjL2mSFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd06082b774f222d7d7b9c9dfb467541a7575580e7e06cb918e2876f027db2af","last_reissued_at":"2026-07-05T11:22:06.580341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:06.580341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bangyi Wu, Junzhao Jin, Liwei Li, Meiru Zhang, Shang Xiao, Xintong Tang, Yang Zheng, Zihan Zhao","submitted_at":"2025-06-16T07:59:51Z","abstract_excerpt":"Large language models (LLMs) are often constrained by rigid reasoning processes, limiting their ability to generate creative and diverse responses. To address this, a novel framework called LADDER is proposed, combining Chain-of-Thought (CoT) reasoning, Mixture of Experts (MoE) models, and multi-dimensional up/down-sampling strategies which breaks the limitations of traditional LLMs. First, CoT reasoning guides the model through multi-step logical reasoning, expanding the semantic space and breaking the rigidity of thought. Next, MoE distributes the reasoning tasks across multiple expert modul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13192","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/2506.13192/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":"2506.13192","created_at":"2026-07-05T11:22:06.580403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13192v1","created_at":"2026-07-05T11:22:06.580403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13192","created_at":"2026-07-05T11:22:06.580403+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UDAQK3XJ4RC","created_at":"2026-07-05T11:22:06.580403+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UDAQK3XJ4RC27L3","created_at":"2026-07-05T11:22:06.580403+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UDAQK3X","created_at":"2026-07-05T11:22:06.580403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG","json":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG.json","graph_json":"https://pith.science/api/pith-number/7UDAQK3XJ4RC27L3TSO7WRTVIG/graph.json","events_json":"https://pith.science/api/pith-number/7UDAQK3XJ4RC27L3TSO7WRTVIG/events.json","paper":"https://pith.science/paper/7UDAQK3X"},"agent_actions":{"view_html":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG","download_json":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG.json","view_paper":"https://pith.science/paper/7UDAQK3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13192&json=true","fetch_graph":"https://pith.science/api/pith-number/7UDAQK3XJ4RC27L3TSO7WRTVIG/graph.json","fetch_events":"https://pith.science/api/pith-number/7UDAQK3XJ4RC27L3TSO7WRTVIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG/action/storage_attestation","attest_author":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG/action/author_attestation","sign_citation":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG/action/citation_signature","submit_replication":"https://pith.science/pith/7UDAQK3XJ4RC27L3TSO7WRTVIG/action/replication_record"}},"created_at":"2026-07-05T11:22:06.580403+00:00","updated_at":"2026-07-05T11:22:06.580403+00:00"}