{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LCNFAEUP7RMGTQOKOBRI4BOGIK","short_pith_number":"pith:LCNFAEUP","schema_version":"1.0","canonical_sha256":"589a50128ffc5869c1ca70628e05c642b2e31cc8f46fbc44f4320b1d3c6e70aa","source":{"kind":"arxiv","id":"2503.10814","version":1},"attestation_state":"computed","paper":{"title":"Thinking Machines: A Survey of LLM based Reasoning Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asif Ekbal, Dibyanayan Bandyopadhyay, Soham Bhattacharjee","submitted_at":"2025-03-13T19:03:41Z","abstract_excerpt":"Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General Intelligence) race. However, on closer inspection, Valmeekam et al. (2024); Zecevic et al. (2023); Wu et al. (2024) highlight a significant gap between their language proficiency and reasoning abilities. Reasoning in LLMs and Vision Language Models (VLMs) aims to bridge this gap by enabling these models to think and re-evaluate their actions and responses. Reasoning is an essential capability for complex problem-solv"},"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":"2503.10814","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T19:03:41Z","cross_cats_sorted":[],"title_canon_sha256":"45e458859c802e81f61ee7d4678fac649cccb168197473ad62c440da3aca2f6e","abstract_canon_sha256":"8f174e50b1620c93523b2109211e729204deb42cd56ccc3e2d0dd0cde8db8ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:06.193576Z","signature_b64":"cpAz1hClqwdwS7inMBw0e8JI559MYXe1csnhCtdmUGQdRTYMVqM48EpJ9wRJyWNOkz1piQB1VIWJRjwchL56AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"589a50128ffc5869c1ca70628e05c642b2e31cc8f46fbc44f4320b1d3c6e70aa","last_reissued_at":"2026-07-05T10:31:06.193063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:06.193063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thinking Machines: A Survey of LLM based Reasoning Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asif Ekbal, Dibyanayan Bandyopadhyay, Soham Bhattacharjee","submitted_at":"2025-03-13T19:03:41Z","abstract_excerpt":"Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General Intelligence) race. However, on closer inspection, Valmeekam et al. (2024); Zecevic et al. (2023); Wu et al. (2024) highlight a significant gap between their language proficiency and reasoning abilities. Reasoning in LLMs and Vision Language Models (VLMs) aims to bridge this gap by enabling these models to think and re-evaluate their actions and responses. Reasoning is an essential capability for complex problem-solv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10814","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/2503.10814/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":"2503.10814","created_at":"2026-07-05T10:31:06.193126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10814v1","created_at":"2026-07-05T10:31:06.193126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10814","created_at":"2026-07-05T10:31:06.193126+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCNFAEUP7RMG","created_at":"2026-07-05T10:31:06.193126+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCNFAEUP7RMGTQOK","created_at":"2026-07-05T10:31:06.193126+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCNFAEUP","created_at":"2026-07-05T10:31:06.193126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.17321","citing_title":"Neuro-Symbolic Control with Large Language Models for Language-Guided Spatial Tasks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02881","citing_title":"One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08905","citing_title":"StaRPO: Stability-Augmented Reinforcement Policy Optimization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12201","citing_title":"AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK","json":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK.json","graph_json":"https://pith.science/api/pith-number/LCNFAEUP7RMGTQOKOBRI4BOGIK/graph.json","events_json":"https://pith.science/api/pith-number/LCNFAEUP7RMGTQOKOBRI4BOGIK/events.json","paper":"https://pith.science/paper/LCNFAEUP"},"agent_actions":{"view_html":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK","download_json":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK.json","view_paper":"https://pith.science/paper/LCNFAEUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10814&json=true","fetch_graph":"https://pith.science/api/pith-number/LCNFAEUP7RMGTQOKOBRI4BOGIK/graph.json","fetch_events":"https://pith.science/api/pith-number/LCNFAEUP7RMGTQOKOBRI4BOGIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK/action/storage_attestation","attest_author":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK/action/author_attestation","sign_citation":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK/action/citation_signature","submit_replication":"https://pith.science/pith/LCNFAEUP7RMGTQOKOBRI4BOGIK/action/replication_record"}},"created_at":"2026-07-05T10:31:06.193126+00:00","updated_at":"2026-07-05T10:31:06.193126+00:00"}