{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BQPOX44BUOEYYUWBLB777X5J2D","short_pith_number":"pith:BQPOX44B","schema_version":"1.0","canonical_sha256":"0c1eebf381a3898c52c1587fffdfa9d0f691c71a1639e3d4206da8da9c2ffff6","source":{"kind":"arxiv","id":"2408.05241","version":4},"attestation_state":"computed","paper":{"title":"Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.ET","cs.GT"],"primary_cat":"cs.CL","authors_text":"Babak Heydari, Nunzio Lore, Sepehr Ilami","submitted_at":"2024-08-05T20:49:48Z","abstract_excerpt":"As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in terms of processing power and time. In this paper, we investigate the feasibility of creating smaller, highly-performing specialized algorithms by way of fine-tuning. To do this, we first present a large pre-trained model with 20 unique scenarios that combine different social contexts with games of varying social dilemmas, record its answers, and use them for Q&"},"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":"2408.05241","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T20:49:48Z","cross_cats_sorted":["cs.AI","cs.CY","cs.ET","cs.GT"],"title_canon_sha256":"d92cc9a4b1c4d524bca1e97925e685e5fe1f88d576a592d258c6c42d69f34840","abstract_canon_sha256":"1f99d0edbd93e210209d8cbce8623afc45ca36b92f84c1987637a61f2e5baeea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:54.046306Z","signature_b64":"v97cVRZcxvpELfl83rjZfvjNE77aw5m8lVZVl0Oh/50+Pa9OS5p9d9511VEcthQekrF2qCGELqCLPp84uovfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c1eebf381a3898c52c1587fffdfa9d0f691c71a1639e3d4206da8da9c2ffff6","last_reissued_at":"2026-07-05T09:28:54.045733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:54.045733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.ET","cs.GT"],"primary_cat":"cs.CL","authors_text":"Babak Heydari, Nunzio Lore, Sepehr Ilami","submitted_at":"2024-08-05T20:49:48Z","abstract_excerpt":"As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in terms of processing power and time. In this paper, we investigate the feasibility of creating smaller, highly-performing specialized algorithms by way of fine-tuning. To do this, we first present a large pre-trained model with 20 unique scenarios that combine different social contexts with games of varying social dilemmas, record its answers, and use them for Q&"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05241","kind":"arxiv","version":4},"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/2408.05241/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":"2408.05241","created_at":"2026-07-05T09:28:54.045796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05241v4","created_at":"2026-07-05T09:28:54.045796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05241","created_at":"2026-07-05T09:28:54.045796+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQPOX44BUOEY","created_at":"2026-07-05T09:28:54.045796+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQPOX44BUOEYYUWB","created_at":"2026-07-05T09:28:54.045796+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQPOX44B","created_at":"2026-07-05T09:28:54.045796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.02153","citing_title":"Small Language Models are the Future of Agentic AI","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D","json":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D.json","graph_json":"https://pith.science/api/pith-number/BQPOX44BUOEYYUWBLB777X5J2D/graph.json","events_json":"https://pith.science/api/pith-number/BQPOX44BUOEYYUWBLB777X5J2D/events.json","paper":"https://pith.science/paper/BQPOX44B"},"agent_actions":{"view_html":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D","download_json":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D.json","view_paper":"https://pith.science/paper/BQPOX44B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05241&json=true","fetch_graph":"https://pith.science/api/pith-number/BQPOX44BUOEYYUWBLB777X5J2D/graph.json","fetch_events":"https://pith.science/api/pith-number/BQPOX44BUOEYYUWBLB777X5J2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D/action/storage_attestation","attest_author":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D/action/author_attestation","sign_citation":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D/action/citation_signature","submit_replication":"https://pith.science/pith/BQPOX44BUOEYYUWBLB777X5J2D/action/replication_record"}},"created_at":"2026-07-05T09:28:54.045796+00:00","updated_at":"2026-07-05T09:28:54.045796+00:00"}