{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CIUNC33H3YGUIZDMEQG6YJLUS6","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"577ace85fa09c2fbadfc1a263a81678d8f5e9b085b86516ce559db4e7dc41a5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T19:45:02Z","title_canon_sha256":"b5e76779e904b5df733ab0d9f0aadfe5f5783628f781af7c37e8d3c17f956a6d"},"schema_version":"1.0","source":{"id":"2605.15365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15365","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15365v1","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15365","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"pith_short_12","alias_value":"CIUNC33H3YGU","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"pith_short_16","alias_value":"CIUNC33H3YGUIZDM","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"pith_short_8","alias_value":"CIUNC33H","created_at":"2026-05-20T00:00:54Z"}],"graph_snapshots":[{"event_id":"sha256:86e7f5120795f07f59c6cd48e42bfb38073aa27da12df255cb4f5c5349675746","target":"graph","created_at":"2026-05-20T00:00:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Humans generally resemble greedy sampling more than globally optimal sampling, though more skilled humans are more likely to backtrack and revise -- a non-greedy behavior."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That Sequential Monte Carlo inference applied to large language models provides faithful approximations of both greedy and globally optimal sampling strategies for human-like language production under vocabulary constraints."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Humans produce language more like greedy local choices than globally optimal planning when vocabulary is tightly constrained, with skilled speakers showing more revision."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Humans produce language more like greedy step-by-step choices than global planning when vocabulary is restricted."}],"snapshot_sha256":"54bfe9b5e55ac4eebafe05f544748ad85a037f236adfe7137c677e6c341e10d6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a0929410378ed51adc965098b9045636f973d16837b5ae489172d2e04fedbdbc"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:18.071322Z","status":"completed","version":"1.0.0"},{"findings_count":2,"name":"doi_compliance","ran_at":"2026-05-19T15:40:49.788302Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.191339Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.739903Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15365/integrity.json","findings":[{"audited_at":"2026-05-19T15:40:49.788302Z","detected_arxiv_id":null,"detected_doi":"10.1044/1092-4388(2008/040","detector":"doi_compliance","finding_type":"unresolvable_identifier","note":"Identifier '10.1044/1092-4388(2008/040' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","ref_index":38,"severity":"critical","verdict_class":"cross_source"},{"audited_at":"2026-05-19T15:40:49.788302Z","detected_arxiv_id":null,"detected_doi":"10.1044/1092-4388(2001/051","detector":"doi_compliance","finding_type":"unresolvable_identifier","note":"Identifier '10.1044/1092-4388(2001/051' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","ref_index":39,"severity":"critical","verdict_class":"cross_source"}],"snapshot_sha256":"97f0a8676218f8a7768d440f76a1ef3145a811ba7c2df171defe1d041d7c1d91","summary":{"advisory":0,"by_detector":{"doi_compliance":{"advisory":0,"critical":2,"informational":0,"total":2}},"critical":2,"informational":0}},"paper":{"abstract_excerpt":"Communicating using only a limited vocabulary is a common but challenging cognitive phenomenon, requiring an ideal communicator to plan carefully to optimize for intelligibility while circumventing a constrained lexicon. In this work, we investigate how humans respond to a broad array of questions under variable vocabulary limitations, consisting of only 250 highly frequent words at the most restrictive. We provide theoretically motivated comparisons to greedy and globally optimal sampling algorithms using Sequential Monte Carlo inference with large language models. Humans generally resemble g","authors_text":"Laura Nicolae, Sihan Chen, Thomas Hikaru Clark","cross_cats":[],"headline":"Humans produce language more like greedy step-by-step choices than global planning when vocabulary is restricted.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T19:45:02Z","title":"Greedy or not, here I come: Language production under vocabulary constraints in humans and resource-rational models"},"references":{"count":86,"internal_anchors":2,"resolved_work":86,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Lombrozo, Tania and Wilkenfeld, Daniel A. , editor =. Mechanistic versus Functional Understanding , booktitle =","work_id":"4e66c480-2d1f-41db-a65f-43de5352d0a1","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Adolphs, Svenja and Schmitt, Norbert , year = 2003, journal =. Lexical","work_id":"5dcb9e9d-a2aa-400f-9b5a-d3a5155be314","year":2003},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":", year = 2011, journal =","work_id":"9639d0cc-212d-4ce2-bba1-3a0e4d1f2797","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Beeke, Suzanne , year = 2012, pages =. 13. 13","work_id":"057bdfe7-8678-40f6-946c-7812fffe1aac","year":2012},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bleakley, Hoyt and Chin, Aimee , year = 2004, journal =. Language","work_id":"08766a81-da7a-42e7-a2f5-5a7b567e3310","year":2004}],"snapshot_sha256":"68de71e6ab4fb4f5f63ac0f44f4d560b0d57d7e3c9dec870737d0e356b8b3df5"},"source":{"id":"2605.15365","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:29:14.660106Z","id":"b31a9013-4fad-44d3-af50-fcbfbdcbfdaf","model_set":{"reader":"grok-4.3"},"one_line_summary":"Humans produce language more like greedy local choices than globally optimal planning when vocabulary is tightly constrained, with skilled speakers showing more revision.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Humans produce language more like greedy step-by-step choices than global planning when vocabulary is restricted.","strongest_claim":"Humans generally resemble greedy sampling more than globally optimal sampling, though more skilled humans are more likely to backtrack and revise -- a non-greedy behavior.","weakest_assumption":"That Sequential Monte Carlo inference applied to large language models provides faithful approximations of both greedy and globally optimal sampling strategies for human-like language production under vocabulary constraints."}},"verdict_id":"b31a9013-4fad-44d3-af50-fcbfbdcbfdaf"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:961a101386162f29e1c7e7072e734bff32df837f9db0efc379ef05c52db7df52","target":"record","created_at":"2026-05-20T00:00:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"577ace85fa09c2fbadfc1a263a81678d8f5e9b085b86516ce559db4e7dc41a5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T19:45:02Z","title_canon_sha256":"b5e76779e904b5df733ab0d9f0aadfe5f5783628f781af7c37e8d3c17f956a6d"},"schema_version":"1.0","source":{"id":"2605.15365","kind":"arxiv","version":1}},"canonical_sha256":"1228d16f67de0d44646c240dec2574979b3e1003a8c160982c0e42d3694601b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1228d16f67de0d44646c240dec2574979b3e1003a8c160982c0e42d3694601b0","first_computed_at":"2026-05-20T00:00:54.640454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:54.640454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A9CJif2kdIEYWOdAwSNfgNfZ6y3mlVJ1KKCKdCNPzZ7ti46L5EH7f3HV4VsFjaiLMpDinoTJc9QdlT82HOLlBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:54.641377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15365","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:bac81161b7fbf6de865d089572dc56dcd6d480d7044d06bb75209ea0060c4898","sha256:dc548c9f9369a0d39ec37e14b53814cac45e643a4eed18bb8c11506436588511"]}],"invalid_events":[],"applied_event_ids":["sha256:961a101386162f29e1c7e7072e734bff32df837f9db0efc379ef05c52db7df52","sha256:86e7f5120795f07f59c6cd48e42bfb38073aa27da12df255cb4f5c5349675746"],"state_sha256":"0f0c268b8e38e4bc610c0737670cf313dd28d094e0aa8e11ec5469b1465e59a6"}