{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LHH7Z2IMG7JEB5YODBDVRH4J2Z","short_pith_number":"pith:LHH7Z2IM","canonical_record":{"source":{"id":"2310.13856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T23:19:35Z","cross_cats_sorted":[],"title_canon_sha256":"9657cf81a03ed515ee72d743558ee9457c02d4ef0305adf807e5e1c0e3633b5e","abstract_canon_sha256":"64034be6ef5645da4c369dad780d6fb25d4c6fbd91e7595f2be5cbd5bc992a6d"},"schema_version":"1.0"},"canonical_sha256":"59cffce90c37d240f70e1847589f89d669a45da3869b85d15031ed99e64928d6","source":{"kind":"arxiv","id":"2310.13856","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13856","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13856v1","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13856","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"LHH7Z2IMG7JE","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"LHH7Z2IMG7JEB5YO","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"LHH7Z2IM","created_at":"2026-07-05T07:03:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LHH7Z2IMG7JEB5YODBDVRH4J2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T23:19:35Z","cross_cats_sorted":[],"title_canon_sha256":"9657cf81a03ed515ee72d743558ee9457c02d4ef0305adf807e5e1c0e3633b5e","abstract_canon_sha256":"64034be6ef5645da4c369dad780d6fb25d4c6fbd91e7595f2be5cbd5bc992a6d"},"schema_version":"1.0"},"canonical_sha256":"59cffce90c37d240f70e1847589f89d669a45da3869b85d15031ed99e64928d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:35.796946Z","signature_b64":"kX9fJWEKpZmb/Chz4z9SnKbq7DV4PLOymgglkRqfomBYP1Eo+z55VXfQU9eajrrUWaISR5HTOF9Yz8GLeggtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59cffce90c37d240f70e1847589f89d669a45da3869b85d15031ed99e64928d6","last_reissued_at":"2026-07-05T07:03:35.796535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:35.796535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13856","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/pLzOlzNuJ79uydoRvPQbQ2CXC53iLFSltUexDqgbCU1ug+M9/J7vgjzln5UweJnKFESa+yJW7AmtY039P9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:42:58.812374Z"},"content_sha256":"b2ef96931dde125bfb4fa53b56ba7f16d464f0d71e25400fdc5daa79aa434f3b","schema_version":"1.0","event_id":"sha256:b2ef96931dde125bfb4fa53b56ba7f16d464f0d71e25400fdc5daa79aa434f3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LHH7Z2IMG7JEB5YODBDVRH4J2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implications of Annotation Artifacts in Edge Probing Test Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jushaan Kalra, Sagnik Ray Choudhury","submitted_at":"2023-10-20T23:19:35Z","abstract_excerpt":"Edge probing tests are classification tasks that test for grammatical knowledge encoded in token representations coming from contextual encoders such as large language models (LLMs). Many LLM encoders have shown high performance in EP tests, leading to conjectures about their ability to encode linguistic knowledge. However, a large body of research claims that the tests necessarily do not measure the LLM's capacity to encode knowledge, but rather reflect the classifiers' ability to learn the problem. Much of this criticism stems from the fact that often the classifiers have very similar accura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13856","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/2310.13856/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":"2026-07-05T07:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smcZou/AjflYYgkKjFAcS+Yk57tW8l7b8TismXlJTvcbTYukqnTZCuyr6XvllNoAPyOvuffmjJzo3QER0NZnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:42:58.812962Z"},"content_sha256":"7939888ed0c1e250e949e54a200017fc890cb66e5b5cdc14a906318367509c61","schema_version":"1.0","event_id":"sha256:7939888ed0c1e250e949e54a200017fc890cb66e5b5cdc14a906318367509c61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHH7Z2IMG7JEB5YODBDVRH4J2Z/bundle.json","state_url":"https://pith.science/pith/LHH7Z2IMG7JEB5YODBDVRH4J2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHH7Z2IMG7JEB5YODBDVRH4J2Z/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":"2026-07-05T15:42:58Z","links":{"resolver":"https://pith.science/pith/LHH7Z2IMG7JEB5YODBDVRH4J2Z","bundle":"https://pith.science/pith/LHH7Z2IMG7JEB5YODBDVRH4J2Z/bundle.json","state":"https://pith.science/pith/LHH7Z2IMG7JEB5YODBDVRH4J2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHH7Z2IMG7JEB5YODBDVRH4J2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LHH7Z2IMG7JEB5YODBDVRH4J2Z","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":"64034be6ef5645da4c369dad780d6fb25d4c6fbd91e7595f2be5cbd5bc992a6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T23:19:35Z","title_canon_sha256":"9657cf81a03ed515ee72d743558ee9457c02d4ef0305adf807e5e1c0e3633b5e"},"schema_version":"1.0","source":{"id":"2310.13856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13856","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13856v1","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13856","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"LHH7Z2IMG7JE","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"LHH7Z2IMG7JEB5YO","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"LHH7Z2IM","created_at":"2026-07-05T07:03:35Z"}],"graph_snapshots":[{"event_id":"sha256:7939888ed0c1e250e949e54a200017fc890cb66e5b5cdc14a906318367509c61","target":"graph","created_at":"2026-07-05T07:03:35Z","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/2310.13856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Edge probing tests are classification tasks that test for grammatical knowledge encoded in token representations coming from contextual encoders such as large language models (LLMs). Many LLM encoders have shown high performance in EP tests, leading to conjectures about their ability to encode linguistic knowledge. However, a large body of research claims that the tests necessarily do not measure the LLM's capacity to encode knowledge, but rather reflect the classifiers' ability to learn the problem. Much of this criticism stems from the fact that often the classifiers have very similar accura","authors_text":"Jushaan Kalra, Sagnik Ray Choudhury","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T23:19:35Z","title":"Implications of Annotation Artifacts in Edge Probing Test Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13856","kind":"arxiv","version":1},"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:b2ef96931dde125bfb4fa53b56ba7f16d464f0d71e25400fdc5daa79aa434f3b","target":"record","created_at":"2026-07-05T07:03:35Z","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":"64034be6ef5645da4c369dad780d6fb25d4c6fbd91e7595f2be5cbd5bc992a6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T23:19:35Z","title_canon_sha256":"9657cf81a03ed515ee72d743558ee9457c02d4ef0305adf807e5e1c0e3633b5e"},"schema_version":"1.0","source":{"id":"2310.13856","kind":"arxiv","version":1}},"canonical_sha256":"59cffce90c37d240f70e1847589f89d669a45da3869b85d15031ed99e64928d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59cffce90c37d240f70e1847589f89d669a45da3869b85d15031ed99e64928d6","first_computed_at":"2026-07-05T07:03:35.796535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:35.796535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kX9fJWEKpZmb/Chz4z9SnKbq7DV4PLOymgglkRqfomBYP1Eo+z55VXfQU9eajrrUWaISR5HTOF9Yz8GLeggtDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:35.796946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13856","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2ef96931dde125bfb4fa53b56ba7f16d464f0d71e25400fdc5daa79aa434f3b","sha256:7939888ed0c1e250e949e54a200017fc890cb66e5b5cdc14a906318367509c61"],"state_sha256":"f71eec1e366ef914233dd2b11770c0009157f02bfabc2fa02e6dbbf64a8becdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qoWwEkIUzNMh2DsmbHVh+pPSaXE/QYQw4zXYSK+57967U4jr7UBzM7HlUId7s+zI8Cc0qV+sOSagzGwkm8ZoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:42:58.815100Z","bundle_sha256":"e4b36dd6441885ce438fce5eab41c824e2076fa6e28d4330f70fe9cf0abc96dc"}}