{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3MSJC6ESEESGF3IIB66IOUPF5Z","short_pith_number":"pith:3MSJC6ES","schema_version":"1.0","canonical_sha256":"db24917892212462ed080fbc8751e5ee4dd5b56e4473a4d05e80d2d2e9f017ee","source":{"kind":"arxiv","id":"2504.09387","version":1},"attestation_state":"computed","paper":{"title":"On Language Models' Sensitivity to Suspicious Coincidences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Kanishka Misra, Kyle Mahowald, Sriram Padmanabhan","submitted_at":"2025-04-13T00:43:06Z","abstract_excerpt":"Humans are sensitive to suspicious coincidences when generalizing inductively over data, as they make assumptions as to how the data was sampled. This results in smaller, more specific hypotheses being favored over more general ones. For instance, when provided the set {Austin, Dallas, Houston}, one is more likely to think that this is sampled from \"Texas Cities\" over \"US Cities\" even though both are compatible. Suspicious coincidence is strongly connected to pragmatic reasoning, and can serve as a testbed to analyze systems on their sensitivity towards the communicative goals of the task (i.e"},"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":"2504.09387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T00:43:06Z","cross_cats_sorted":[],"title_canon_sha256":"3590ed758ef65b16f2e63dade4297df3b0edc0ff80072358dfb356a5dd294923","abstract_canon_sha256":"5ce0c42a5ca4898d0ad6e4d3ed2b157361ab6d1bed4f85b996cc69d8e1c5b5cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:36.419086Z","signature_b64":"QXumFrmYxNTEmsWWigjbXwGcIp0heB++fIfJMfxkoKpfCBtrHJMWfIpPttmcFCOUiHL58RjzcXEn7vk7tj+zAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db24917892212462ed080fbc8751e5ee4dd5b56e4473a4d05e80d2d2e9f017ee","last_reissued_at":"2026-07-05T10:48:36.418612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:36.418612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Language Models' Sensitivity to Suspicious Coincidences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Kanishka Misra, Kyle Mahowald, Sriram Padmanabhan","submitted_at":"2025-04-13T00:43:06Z","abstract_excerpt":"Humans are sensitive to suspicious coincidences when generalizing inductively over data, as they make assumptions as to how the data was sampled. This results in smaller, more specific hypotheses being favored over more general ones. For instance, when provided the set {Austin, Dallas, Houston}, one is more likely to think that this is sampled from \"Texas Cities\" over \"US Cities\" even though both are compatible. Suspicious coincidence is strongly connected to pragmatic reasoning, and can serve as a testbed to analyze systems on their sensitivity towards the communicative goals of the task (i.e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09387","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/2504.09387/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":"2504.09387","created_at":"2026-07-05T10:48:36.418669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09387v1","created_at":"2026-07-05T10:48:36.418669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09387","created_at":"2026-07-05T10:48:36.418669+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MSJC6ESEESG","created_at":"2026-07-05T10:48:36.418669+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MSJC6ESEESGF3II","created_at":"2026-07-05T10:48:36.418669+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MSJC6ES","created_at":"2026-07-05T10:48:36.418669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02556","citing_title":"HERO'S JOURNEY: Testing Complex Rule Induction with Text Games","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05851","citing_title":"Hypothesis generation and updating in large language models","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z","json":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z.json","graph_json":"https://pith.science/api/pith-number/3MSJC6ESEESGF3IIB66IOUPF5Z/graph.json","events_json":"https://pith.science/api/pith-number/3MSJC6ESEESGF3IIB66IOUPF5Z/events.json","paper":"https://pith.science/paper/3MSJC6ES"},"agent_actions":{"view_html":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z","download_json":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z.json","view_paper":"https://pith.science/paper/3MSJC6ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09387&json=true","fetch_graph":"https://pith.science/api/pith-number/3MSJC6ESEESGF3IIB66IOUPF5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/3MSJC6ESEESGF3IIB66IOUPF5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z/action/storage_attestation","attest_author":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z/action/author_attestation","sign_citation":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z/action/citation_signature","submit_replication":"https://pith.science/pith/3MSJC6ESEESGF3IIB66IOUPF5Z/action/replication_record"}},"created_at":"2026-07-05T10:48:36.418669+00:00","updated_at":"2026-07-05T10:48:36.418669+00:00"}