{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GY6DKPRFQS2RVCXRAIRJDLV6AB","short_pith_number":"pith:GY6DKPRF","canonical_record":{"source":{"id":"2303.16445","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-29T04:00:53Z","cross_cats_sorted":[],"title_canon_sha256":"df09c8e34b8de0181163f7069b7ed137207c87cba5715d9ad10ff8492d978748","abstract_canon_sha256":"a802c0f78fa6b2ffca04c5a6b17fbaa16ab2b3f5d24f57e723ff70cbc3d86178"},"schema_version":"1.0"},"canonical_sha256":"363c353e2584b51a8af1022291aebe004e005003bade7264b01e6c4d0af1db0a","source":{"kind":"arxiv","id":"2303.16445","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16445","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16445v3","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16445","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"GY6DKPRFQS2R","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"GY6DKPRFQS2RVCXR","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"GY6DKPRF","created_at":"2026-07-05T07:12:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GY6DKPRFQS2RVCXRAIRJDLV6AB","target":"record","payload":{"canonical_record":{"source":{"id":"2303.16445","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-29T04:00:53Z","cross_cats_sorted":[],"title_canon_sha256":"df09c8e34b8de0181163f7069b7ed137207c87cba5715d9ad10ff8492d978748","abstract_canon_sha256":"a802c0f78fa6b2ffca04c5a6b17fbaa16ab2b3f5d24f57e723ff70cbc3d86178"},"schema_version":"1.0"},"canonical_sha256":"363c353e2584b51a8af1022291aebe004e005003bade7264b01e6c4d0af1db0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:34.275298Z","signature_b64":"zUwEvo6mzvh/snsOYncjyfAqYtP/UND8M0CaA1JhrKvDyKfIEixJ58KsxK1O0ykxPqw5DHz33qnYpcep3FDDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"363c353e2584b51a8af1022291aebe004e005003bade7264b01e6c4d0af1db0a","last_reissued_at":"2026-07-05T07:12:34.274883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:34.274883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.16445","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5eU2niIdNw8zqMIneyy/il0+oZ8kv6R0/mXJGZcjfMxrqpofnlGaiQArV4/54bhribHYRt4UIVL75oO6X0HYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:32:26.880799Z"},"content_sha256":"70020ec920c778acd6e1e28f45c5664cdcd72396b67ab61a1cba758a1d5d1710","schema_version":"1.0","event_id":"sha256:70020ec920c778acd6e1e28f45c5664cdcd72396b67ab61a1cba758a1d5d1710"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GY6DKPRFQS2RVCXRAIRJDLV6AB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Rumshisky, Namrata Shivagunde, Vladislav Lialin","submitted_at":"2023-03-29T04:00:53Z","abstract_excerpt":"Language model probing is often used to test specific capabilities of models. However, conclusions from such studies may be limited when the probing benchmarks are small and lack statistical power. In this work, we introduce new, larger datasets for negation (NEG-1500-SIMP) and role reversal (ROLE-1500) inspired by psycholinguistic studies. We dramatically extend existing NEG-136 and ROLE-88 benchmarks using GPT3, increasing their size from 18 and 44 sentence pairs to 750 each. We also create another version of extended negation dataset (NEG-1500-SIMP-TEMP), created using template-based genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16445","kind":"arxiv","version":3},"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/2303.16445/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"meKlHwTx+FZitZ27o0sv8MXVcb0M+zsdywVJrwxux7dY7AnaaosvfIYuL3Q21djkRCkYc7QPWqUmTxYhKr4WBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:32:26.881172Z"},"content_sha256":"f07a27831d692983195756c3ab91994994a81a66c70c92793e9f4b4c88ffc98c","schema_version":"1.0","event_id":"sha256:f07a27831d692983195756c3ab91994994a81a66c70c92793e9f4b4c88ffc98c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GY6DKPRFQS2RVCXRAIRJDLV6AB/bundle.json","state_url":"https://pith.science/pith/GY6DKPRFQS2RVCXRAIRJDLV6AB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GY6DKPRFQS2RVCXRAIRJDLV6AB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-10T12:32:26Z","links":{"resolver":"https://pith.science/pith/GY6DKPRFQS2RVCXRAIRJDLV6AB","bundle":"https://pith.science/pith/GY6DKPRFQS2RVCXRAIRJDLV6AB/bundle.json","state":"https://pith.science/pith/GY6DKPRFQS2RVCXRAIRJDLV6AB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GY6DKPRFQS2RVCXRAIRJDLV6AB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GY6DKPRFQS2RVCXRAIRJDLV6AB","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":"a802c0f78fa6b2ffca04c5a6b17fbaa16ab2b3f5d24f57e723ff70cbc3d86178","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-29T04:00:53Z","title_canon_sha256":"df09c8e34b8de0181163f7069b7ed137207c87cba5715d9ad10ff8492d978748"},"schema_version":"1.0","source":{"id":"2303.16445","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16445","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16445v3","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16445","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"GY6DKPRFQS2R","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"GY6DKPRFQS2RVCXR","created_at":"2026-07-05T07:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"GY6DKPRF","created_at":"2026-07-05T07:12:34Z"}],"graph_snapshots":[{"event_id":"sha256:f07a27831d692983195756c3ab91994994a81a66c70c92793e9f4b4c88ffc98c","target":"graph","created_at":"2026-07-05T07:12:34Z","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/2303.16445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model probing is often used to test specific capabilities of models. However, conclusions from such studies may be limited when the probing benchmarks are small and lack statistical power. In this work, we introduce new, larger datasets for negation (NEG-1500-SIMP) and role reversal (ROLE-1500) inspired by psycholinguistic studies. We dramatically extend existing NEG-136 and ROLE-88 benchmarks using GPT3, increasing their size from 18 and 44 sentence pairs to 750 each. We also create another version of extended negation dataset (NEG-1500-SIMP-TEMP), created using template-based genera","authors_text":"Anna Rumshisky, Namrata Shivagunde, Vladislav Lialin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-29T04:00:53Z","title":"Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16445","kind":"arxiv","version":3},"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":"sha256:70020ec920c778acd6e1e28f45c5664cdcd72396b67ab61a1cba758a1d5d1710","target":"record","created_at":"2026-07-05T07:12:34Z","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":"a802c0f78fa6b2ffca04c5a6b17fbaa16ab2b3f5d24f57e723ff70cbc3d86178","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-29T04:00:53Z","title_canon_sha256":"df09c8e34b8de0181163f7069b7ed137207c87cba5715d9ad10ff8492d978748"},"schema_version":"1.0","source":{"id":"2303.16445","kind":"arxiv","version":3}},"canonical_sha256":"363c353e2584b51a8af1022291aebe004e005003bade7264b01e6c4d0af1db0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"363c353e2584b51a8af1022291aebe004e005003bade7264b01e6c4d0af1db0a","first_computed_at":"2026-07-05T07:12:34.274883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:34.274883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zUwEvo6mzvh/snsOYncjyfAqYtP/UND8M0CaA1JhrKvDyKfIEixJ58KsxK1O0ykxPqw5DHz33qnYpcep3FDDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:34.275298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16445","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70020ec920c778acd6e1e28f45c5664cdcd72396b67ab61a1cba758a1d5d1710","sha256:f07a27831d692983195756c3ab91994994a81a66c70c92793e9f4b4c88ffc98c"],"state_sha256":"d6c4c1fc92e0f8b41490a6ed26288e788cf2c8245f68b8b21b72093572522dfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xxSU7m062qtE8YwgB+q2ecG8S5/yoysMryyz8RADf/FdgxoArrM578blqrx4zQdwCOJRoHJ4EygnFePzLTlPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T12:32:26.883012Z","bundle_sha256":"0cb344e5624de41cc5369e622d7456d17a1a7c5230e949d5dfd1ddeca74c955b"}}