{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:COZEYJL4JX6N2TZGSCMEULF2DB","short_pith_number":"pith:COZEYJL4","schema_version":"1.0","canonical_sha256":"13b24c257c4dfcdd4f2690984a2cba18454186c4e2aeadf09b6d4b320b0f6390","source":{"kind":"arxiv","id":"2504.15604","version":1},"attestation_state":"computed","paper":{"title":"Exploring Next Token Prediction in Theory of Mind (ToM) Tasks: Comparative Experiments with GPT-2 and LLaMA-2 AI Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Krishna Shinde, Lokesh B. Ramegowda, Nikhil Khandalkar, Pavan Yadav, Rajarshi Das","submitted_at":"2025-04-22T05:52:55Z","abstract_excerpt":"Language models have made significant progress in generating coherent text and predicting next tokens based on input prompts. This study compares the next-token prediction performance of two well-known models: OpenAI's GPT-2 and Meta's Llama-2-7b-chat-hf on Theory of Mind (ToM) tasks. To evaluate their capabilities, we built a dataset from 10 short stories sourced from the Explore ToM Dataset. We enhanced these stories by programmatically inserting additional sentences (infills) using GPT-4, creating variations that introduce different levels of contextual complexity. This setup enables analys"},"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":"2504.15604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T05:52:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3c62db4d990bf064e65d1c11ad0e51cea4ca1cb23fe16300c95e737ee2c499b","abstract_canon_sha256":"6b5a4bad4814aa118e4565eaa1e27890a3c2dc7e650be315bf5dc2ae5f9de5c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:27.264248Z","signature_b64":"uWFslgLawA6qpa4LeFCE62RbrQUwhtE3KpVUnI6Ih/UbovOScvcq4hEqXT001zJNqQuxk6ayoi8qw1nD7OwwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13b24c257c4dfcdd4f2690984a2cba18454186c4e2aeadf09b6d4b320b0f6390","last_reissued_at":"2026-07-05T10:52:27.263735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:27.263735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Next Token Prediction in Theory of Mind (ToM) Tasks: Comparative Experiments with GPT-2 and LLaMA-2 AI Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Krishna Shinde, Lokesh B. Ramegowda, Nikhil Khandalkar, Pavan Yadav, Rajarshi Das","submitted_at":"2025-04-22T05:52:55Z","abstract_excerpt":"Language models have made significant progress in generating coherent text and predicting next tokens based on input prompts. This study compares the next-token prediction performance of two well-known models: OpenAI's GPT-2 and Meta's Llama-2-7b-chat-hf on Theory of Mind (ToM) tasks. To evaluate their capabilities, we built a dataset from 10 short stories sourced from the Explore ToM Dataset. We enhanced these stories by programmatically inserting additional sentences (infills) using GPT-4, creating variations that introduce different levels of contextual complexity. This setup enables analys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15604","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/2504.15604/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":"2504.15604","created_at":"2026-07-05T10:52:27.263799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15604v1","created_at":"2026-07-05T10:52:27.263799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15604","created_at":"2026-07-05T10:52:27.263799+00:00"},{"alias_kind":"pith_short_12","alias_value":"COZEYJL4JX6N","created_at":"2026-07-05T10:52:27.263799+00:00"},{"alias_kind":"pith_short_16","alias_value":"COZEYJL4JX6N2TZG","created_at":"2026-07-05T10:52:27.263799+00:00"},{"alias_kind":"pith_short_8","alias_value":"COZEYJL4","created_at":"2026-07-05T10:52:27.263799+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/COZEYJL4JX6N2TZGSCMEULF2DB","json":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB.json","graph_json":"https://pith.science/api/pith-number/COZEYJL4JX6N2TZGSCMEULF2DB/graph.json","events_json":"https://pith.science/api/pith-number/COZEYJL4JX6N2TZGSCMEULF2DB/events.json","paper":"https://pith.science/paper/COZEYJL4"},"agent_actions":{"view_html":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB","download_json":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB.json","view_paper":"https://pith.science/paper/COZEYJL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15604&json=true","fetch_graph":"https://pith.science/api/pith-number/COZEYJL4JX6N2TZGSCMEULF2DB/graph.json","fetch_events":"https://pith.science/api/pith-number/COZEYJL4JX6N2TZGSCMEULF2DB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB/action/storage_attestation","attest_author":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB/action/author_attestation","sign_citation":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB/action/citation_signature","submit_replication":"https://pith.science/pith/COZEYJL4JX6N2TZGSCMEULF2DB/action/replication_record"}},"created_at":"2026-07-05T10:52:27.263799+00:00","updated_at":"2026-07-05T10:52:27.263799+00:00"}