{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QRSBL2JQJUEZHVGM67JJL4GUGJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b6d82239daceaad14d0ad6d71a0db9239e152aefda535b6e00eb6cba3576c4e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T02:56:52Z","title_canon_sha256":"4817ef2a72566972d029da0d8d9dd0a7e811efd23bf624dd4cf6b5346acbeaee"},"schema_version":"1.0","source":{"id":"2404.02418","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02418","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02418v2","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02418","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"QRSBL2JQJUEZ","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"pith_short_16","alias_value":"QRSBL2JQJUEZHVGM","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"pith_short_8","alias_value":"QRSBL2JQ","created_at":"2026-07-05T08:49:52Z"}],"graph_snapshots":[{"event_id":"sha256:56c58a2a63c78aa2c4b71a601811de0a208d15bcf99083ba2e8aacbdc016e1d0","target":"graph","created_at":"2026-07-05T08:49:52Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.02418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developmental psychologists have argued about when cognitive capacities such as language understanding or theory of mind emerge. These debates often hinge on the concept of \"task demands\" -- the auxiliary challenges associated with performing a particular evaluation -- that may mask the child's underlying ability. The same issues arise when measuring the capacities of language models (LMs): performance on a task is a function of the model's underlying knowledge, combined with the model's ability to interpret and perform the task given its available resources. Here, we show that for analogical ","authors_text":"Jennifer Hu, Michael C. Frank","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T02:56:52Z","title":"Auxiliary task demands mask the capabilities of smaller language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02418","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:29cdff16cacf4d33e67329d40dfa36b085db2d91ffb89a96a9da54f5da1311aa","target":"record","created_at":"2026-07-05T08:49:52Z","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":"b6d82239daceaad14d0ad6d71a0db9239e152aefda535b6e00eb6cba3576c4e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T02:56:52Z","title_canon_sha256":"4817ef2a72566972d029da0d8d9dd0a7e811efd23bf624dd4cf6b5346acbeaee"},"schema_version":"1.0","source":{"id":"2404.02418","kind":"arxiv","version":2}},"canonical_sha256":"846415e9304d0993d4ccf7d295f0d43257d3f960e31ea70993b996351b0c74e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"846415e9304d0993d4ccf7d295f0d43257d3f960e31ea70993b996351b0c74e3","first_computed_at":"2026-07-05T08:49:52.947645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:52.947645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RFffFXj5QtGkdYqDBwL8d90sOWOal/iFZgrRdoyvyTReBxkvMPxGT9evJjJXc60DpoUAeIxn6Q/M1i74PLsLAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:52.948065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02418","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29cdff16cacf4d33e67329d40dfa36b085db2d91ffb89a96a9da54f5da1311aa","sha256:56c58a2a63c78aa2c4b71a601811de0a208d15bcf99083ba2e8aacbdc016e1d0"],"state_sha256":"1d28d470baf7d866de259a4e8ae5d3accae1f0e91e8bb5dc078ac2d9011bb270"}