{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U6FEYCSC6A2VHBTAEA65XEFWXD","short_pith_number":"pith:U6FEYCSC","schema_version":"1.0","canonical_sha256":"a78a4c0a42f035538660203ddb90b6b8f740ea88b4e9ee3a6654cc2ee14c1771","source":{"kind":"arxiv","id":"2408.09656","version":2},"attestation_state":"computed","paper":{"title":"A Comparison of Large Language Model and Human Performance on Random Number Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Rachel M. Harrison","submitted_at":"2024-08-19T02:34:15Z","abstract_excerpt":"Random Number Generation Tasks (RNGTs) are used in psychology for examining how humans generate sequences devoid of predictable patterns. By adapting an existing human RNGT for an LLM-compatible environment, this preliminary study tests whether ChatGPT-3.5, a large language model (LLM) trained on human-generated text, exhibits human-like cognitive biases when generating random number sequences. Initial findings indicate that ChatGPT-3.5 more effectively avoids repetitive and sequential patterns compared to humans, with notably lower repeat frequencies and adjacent number frequencies. Continued"},"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":"2408.09656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T02:34:15Z","cross_cats_sorted":["cs.CL","q-bio.NC"],"title_canon_sha256":"69ff9937cf28b6f858fc788cea832f89d44b0aad4b96a141c9dd89776cccae2a","abstract_canon_sha256":"9faeec6c4fecd213fe91658e946b7277d97eb00f7efe7891adfafb93393270f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:07.031616Z","signature_b64":"awFEgwFIrd4QIN+Yla+wgIUYe6vCIGPlhei6wOru6QMTsqakC3Ny8g0Gvdre1OnF1Jpgtpf/J8DSQPCkhYDABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a78a4c0a42f035538660203ddb90b6b8f740ea88b4e9ee3a6654cc2ee14c1771","last_reissued_at":"2026-07-05T08:57:07.031154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:07.031154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparison of Large Language Model and Human Performance on Random Number Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Rachel M. Harrison","submitted_at":"2024-08-19T02:34:15Z","abstract_excerpt":"Random Number Generation Tasks (RNGTs) are used in psychology for examining how humans generate sequences devoid of predictable patterns. By adapting an existing human RNGT for an LLM-compatible environment, this preliminary study tests whether ChatGPT-3.5, a large language model (LLM) trained on human-generated text, exhibits human-like cognitive biases when generating random number sequences. Initial findings indicate that ChatGPT-3.5 more effectively avoids repetitive and sequential patterns compared to humans, with notably lower repeat frequencies and adjacent number frequencies. Continued"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09656","kind":"arxiv","version":2},"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/2408.09656/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":"2408.09656","created_at":"2026-07-05T08:57:07.031217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09656v2","created_at":"2026-07-05T08:57:07.031217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09656","created_at":"2026-07-05T08:57:07.031217+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6FEYCSC6A2V","created_at":"2026-07-05T08:57:07.031217+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6FEYCSC6A2VHBTA","created_at":"2026-07-05T08:57:07.031217+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6FEYCSC","created_at":"2026-07-05T08:57:07.031217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03330","citing_title":"FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD","json":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD.json","graph_json":"https://pith.science/api/pith-number/U6FEYCSC6A2VHBTAEA65XEFWXD/graph.json","events_json":"https://pith.science/api/pith-number/U6FEYCSC6A2VHBTAEA65XEFWXD/events.json","paper":"https://pith.science/paper/U6FEYCSC"},"agent_actions":{"view_html":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD","download_json":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD.json","view_paper":"https://pith.science/paper/U6FEYCSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09656&json=true","fetch_graph":"https://pith.science/api/pith-number/U6FEYCSC6A2VHBTAEA65XEFWXD/graph.json","fetch_events":"https://pith.science/api/pith-number/U6FEYCSC6A2VHBTAEA65XEFWXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD/action/storage_attestation","attest_author":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD/action/author_attestation","sign_citation":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD/action/citation_signature","submit_replication":"https://pith.science/pith/U6FEYCSC6A2VHBTAEA65XEFWXD/action/replication_record"}},"created_at":"2026-07-05T08:57:07.031217+00:00","updated_at":"2026-07-05T08:57:07.031217+00:00"}