{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GDFK5FBK5UQEVPEJVNIEKOVIXL","short_pith_number":"pith:GDFK5FBK","schema_version":"1.0","canonical_sha256":"30caae942aed204abc89ab50453aa8bace47d8ab5c115e19fca74bc8bde37657","source":{"kind":"arxiv","id":"2301.10297","version":1},"attestation_state":"computed","paper":{"title":"Large language models can segment narrative events similarly to humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.CL","authors_text":"Kenneth A. Norman, Manoj Kumar, Mariya Toneva, Sebastian Michelmann","submitted_at":"2023-01-24T20:34:37Z","abstract_excerpt":"Humans perceive discrete events such as \"restaurant visits\" and \"train rides\" in their continuous experience. One important prerequisite for studying human event perception is the ability of researchers to quantify when one event ends and another begins. Typically, this information is derived by aggregating behavioral annotations from several observers. Here we present an alternative computational approach where event boundaries are derived using a large language model, GPT-3, instead of using human annotations. We demonstrate that GPT-3 can segment continuous narrative text into events. GPT-3"},"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":"2301.10297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-24T20:34:37Z","cross_cats_sorted":["q-bio.NC"],"title_canon_sha256":"224f904624ecb0e50fe0b4e0e7367a3286a90e86b66a07a1bd7c324b29be6d76","abstract_canon_sha256":"e80d70e84754a8c43d02f8e8c413f969b246ba225c4613d7be8f9fb896242f8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:49.537768Z","signature_b64":"jfbGkeXQfgMO9iJi6LcWzil/ovJO7yBIzrzYLZ6wt0ENxuefv26xdludTF07vaUV3Lad/hUw1Jru9SrpqGfnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30caae942aed204abc89ab50453aa8bace47d8ab5c115e19fca74bc8bde37657","last_reissued_at":"2026-07-05T05:35:49.537290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:49.537290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large language models can segment narrative events similarly to humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.CL","authors_text":"Kenneth A. Norman, Manoj Kumar, Mariya Toneva, Sebastian Michelmann","submitted_at":"2023-01-24T20:34:37Z","abstract_excerpt":"Humans perceive discrete events such as \"restaurant visits\" and \"train rides\" in their continuous experience. One important prerequisite for studying human event perception is the ability of researchers to quantify when one event ends and another begins. Typically, this information is derived by aggregating behavioral annotations from several observers. Here we present an alternative computational approach where event boundaries are derived using a large language model, GPT-3, instead of using human annotations. We demonstrate that GPT-3 can segment continuous narrative text into events. GPT-3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10297","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/2301.10297/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":"2301.10297","created_at":"2026-07-05T05:35:49.537360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10297v1","created_at":"2026-07-05T05:35:49.537360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10297","created_at":"2026-07-05T05:35:49.537360+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDFK5FBK5UQE","created_at":"2026-07-05T05:35:49.537360+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDFK5FBK5UQEVPEJ","created_at":"2026-07-05T05:35:49.537360+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDFK5FBK","created_at":"2026-07-05T05:35:49.537360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.01347","citing_title":"A clinically validated framework for auditing AI chatbot behavior in mental health interactions","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL","json":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL.json","graph_json":"https://pith.science/api/pith-number/GDFK5FBK5UQEVPEJVNIEKOVIXL/graph.json","events_json":"https://pith.science/api/pith-number/GDFK5FBK5UQEVPEJVNIEKOVIXL/events.json","paper":"https://pith.science/paper/GDFK5FBK"},"agent_actions":{"view_html":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL","download_json":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL.json","view_paper":"https://pith.science/paper/GDFK5FBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10297&json=true","fetch_graph":"https://pith.science/api/pith-number/GDFK5FBK5UQEVPEJVNIEKOVIXL/graph.json","fetch_events":"https://pith.science/api/pith-number/GDFK5FBK5UQEVPEJVNIEKOVIXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL/action/storage_attestation","attest_author":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL/action/author_attestation","sign_citation":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL/action/citation_signature","submit_replication":"https://pith.science/pith/GDFK5FBK5UQEVPEJVNIEKOVIXL/action/replication_record"}},"created_at":"2026-07-05T05:35:49.537360+00:00","updated_at":"2026-07-05T05:35:49.537360+00:00"}