{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HGFFHESFTOWFXGZKF2E6UCQHBB","short_pith_number":"pith:HGFFHESF","schema_version":"1.0","canonical_sha256":"398a5392459bac5b9b2a2e89ea0a070849617aa3fb4d7edabb13f053c99bc206","source":{"kind":"arxiv","id":"2303.14310","version":1},"attestation_state":"computed","paper":{"title":"GPT is becoming a Turing machine: Here are some ways to program it","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Jojic, Nebojsa Jojic, Zhen Wang","submitted_at":"2023-03-25T00:43:41Z","abstract_excerpt":"We demonstrate that, through appropriate prompting, GPT-3 family of models can be triggered to perform iterative behaviours necessary to execute (rather than just write or recall) programs that involve loops, including several popular algorithms found in computer science curricula or software developer interviews. We trigger execution and description of Iterations by Regimenting Self-Attention (IRSA) in one (or a combination) of three ways: 1) Using strong repetitive structure in an example of an execution path of a target program for one particular input, 2) Prompting with fragments of execut"},"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":"2303.14310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-25T00:43:41Z","cross_cats_sorted":[],"title_canon_sha256":"f60f13bb32e19015e44e8d09f1fac5fbdd98849b3a4d85752065b0e2d6e3b411","abstract_canon_sha256":"3390b693fe5397529d86f6c7120e675c2d9b1f428502e0e77ceaf09a9c01b052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:39.347971Z","signature_b64":"KYfG1XAflVt4O9Vk50Sqi+vaSFuNQVVhG8nw7XbTAweoivbBL7BJS3mLb1VKFjnmTgwBCNmDNPZwYdQTuE/nAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"398a5392459bac5b9b2a2e89ea0a070849617aa3fb4d7edabb13f053c99bc206","last_reissued_at":"2026-07-05T05:54:39.347629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:39.347629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT is becoming a Turing machine: Here are some ways to program it","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Jojic, Nebojsa Jojic, Zhen Wang","submitted_at":"2023-03-25T00:43:41Z","abstract_excerpt":"We demonstrate that, through appropriate prompting, GPT-3 family of models can be triggered to perform iterative behaviours necessary to execute (rather than just write or recall) programs that involve loops, including several popular algorithms found in computer science curricula or software developer interviews. We trigger execution and description of Iterations by Regimenting Self-Attention (IRSA) in one (or a combination) of three ways: 1) Using strong repetitive structure in an example of an execution path of a target program for one particular input, 2) Prompting with fragments of execut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14310","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/2303.14310/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":"2303.14310","created_at":"2026-07-05T05:54:39.347686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14310v1","created_at":"2026-07-05T05:54:39.347686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14310","created_at":"2026-07-05T05:54:39.347686+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGFFHESFTOWF","created_at":"2026-07-05T05:54:39.347686+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGFFHESFTOWFXGZK","created_at":"2026-07-05T05:54:39.347686+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGFFHESF","created_at":"2026-07-05T05:54:39.347686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.14992","citing_title":"Reasoning with Language Model is Planning with World Model","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10774","citing_title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB","json":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB.json","graph_json":"https://pith.science/api/pith-number/HGFFHESFTOWFXGZKF2E6UCQHBB/graph.json","events_json":"https://pith.science/api/pith-number/HGFFHESFTOWFXGZKF2E6UCQHBB/events.json","paper":"https://pith.science/paper/HGFFHESF"},"agent_actions":{"view_html":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB","download_json":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB.json","view_paper":"https://pith.science/paper/HGFFHESF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14310&json=true","fetch_graph":"https://pith.science/api/pith-number/HGFFHESFTOWFXGZKF2E6UCQHBB/graph.json","fetch_events":"https://pith.science/api/pith-number/HGFFHESFTOWFXGZKF2E6UCQHBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB/action/storage_attestation","attest_author":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB/action/author_attestation","sign_citation":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB/action/citation_signature","submit_replication":"https://pith.science/pith/HGFFHESFTOWFXGZKF2E6UCQHBB/action/replication_record"}},"created_at":"2026-07-05T05:54:39.347686+00:00","updated_at":"2026-07-05T05:54:39.347686+00:00"}