{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZCYJ2X66LQ6LPU6MTQJ24AVUSE","short_pith_number":"pith:ZCYJ2X66","canonical_record":{"source":{"id":"2403.04963","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T00:19:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f190f56acfd10db9227c403912af44d7212967aceed31f31f81d271a38678980","abstract_canon_sha256":"5c974b789eea754e6e0836e0e443e3048f1fa22d9b6b9f053a6868e4cfc6d8ab"},"schema_version":"1.0"},"canonical_sha256":"c8b09d5fde5c3cb7d3cc9c13ae02b49123de5d3a467271c24ff1397437c06bcd","source":{"kind":"arxiv","id":"2403.04963","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04963","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04963v4","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04963","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZCYJ2X66LQ6L","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZCYJ2X66LQ6LPU6M","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZCYJ2X66","created_at":"2026-07-05T11:35:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZCYJ2X66LQ6LPU6MTQJ24AVUSE","target":"record","payload":{"canonical_record":{"source":{"id":"2403.04963","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T00:19:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f190f56acfd10db9227c403912af44d7212967aceed31f31f81d271a38678980","abstract_canon_sha256":"5c974b789eea754e6e0836e0e443e3048f1fa22d9b6b9f053a6868e4cfc6d8ab"},"schema_version":"1.0"},"canonical_sha256":"c8b09d5fde5c3cb7d3cc9c13ae02b49123de5d3a467271c24ff1397437c06bcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:48.870486Z","signature_b64":"VzWZywR3r4sAGU7J+/NpNc8TO/uvhIfHcF4gamnxGVq5eA6Regr8no3/a652sL1ZD8t/58U1GpCg7+kx8IEMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8b09d5fde5c3cb7d3cc9c13ae02b49123de5d3a467271c24ff1397437c06bcd","last_reissued_at":"2026-07-05T11:35:48.869993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:48.869993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.04963","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:35:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WGA71WTf2G13+uNQHeH1d+YHRPuM8o1ATmZIzFhauqYMEAl+6pSInatvWZy3wFOLWZ2mTzs+fTvdDYoDLyqPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:25:20.528588Z"},"content_sha256":"5ec8d394caaaad7b6edae783f0e5d2172ffcfea33b47eacfe6fd86c7f1999591","schema_version":"1.0","event_id":"sha256:5ec8d394caaaad7b6edae783f0e5d2172ffcfea33b47eacfe6fd86c7f1999591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZCYJ2X66LQ6LPU6MTQJ24AVUSE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Xuanxin Wu, Yuki Arase","submitted_at":"2024-03-08T00:19:24Z","abstract_excerpt":"Recent studies have used both automatic metrics and human evaluations to assess the simplification abilities of LLMs. However, the suitability of existing evaluation methodologies for LLMs remains in question. First, the suitability of current automatic metrics on LLMs' simplification evaluation is still uncertain. Second, current human evaluation approaches in sentence simplification often fall into two extremes: they are either too superficial, failing to offer a clear understanding of the models' performance, or overly detailed, making the annotation process complex and prone to inconsisten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04963","kind":"arxiv","version":4},"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/2403.04963/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":"2026-07-05T11:35:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3zJHrqu58JJQEIWzUO9PZ19TWrOvsCv1HzcGhdhpByLoBHZpaCIR/vYkmMdCRDfuJYeS25GFOgaxOS1MaxfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:25:20.529883Z"},"content_sha256":"daea8f6ff4ce6b86e79de6c863ddf646546ce07102fedaac22df39dfa650eed9","schema_version":"1.0","event_id":"sha256:daea8f6ff4ce6b86e79de6c863ddf646546ce07102fedaac22df39dfa650eed9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZCYJ2X66LQ6LPU6MTQJ24AVUSE/bundle.json","state_url":"https://pith.science/pith/ZCYJ2X66LQ6LPU6MTQJ24AVUSE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZCYJ2X66LQ6LPU6MTQJ24AVUSE/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":"2026-08-18T21:25:20Z","links":{"resolver":"https://pith.science/pith/ZCYJ2X66LQ6LPU6MTQJ24AVUSE","bundle":"https://pith.science/pith/ZCYJ2X66LQ6LPU6MTQJ24AVUSE/bundle.json","state":"https://pith.science/pith/ZCYJ2X66LQ6LPU6MTQJ24AVUSE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZCYJ2X66LQ6LPU6MTQJ24AVUSE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZCYJ2X66LQ6LPU6MTQJ24AVUSE","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":"5c974b789eea754e6e0836e0e443e3048f1fa22d9b6b9f053a6868e4cfc6d8ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T00:19:24Z","title_canon_sha256":"f190f56acfd10db9227c403912af44d7212967aceed31f31f81d271a38678980"},"schema_version":"1.0","source":{"id":"2403.04963","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04963","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04963v4","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04963","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZCYJ2X66LQ6L","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZCYJ2X66LQ6LPU6M","created_at":"2026-07-05T11:35:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZCYJ2X66","created_at":"2026-07-05T11:35:48Z"}],"graph_snapshots":[{"event_id":"sha256:daea8f6ff4ce6b86e79de6c863ddf646546ce07102fedaac22df39dfa650eed9","target":"graph","created_at":"2026-07-05T11:35:48Z","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/2403.04963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have used both automatic metrics and human evaluations to assess the simplification abilities of LLMs. However, the suitability of existing evaluation methodologies for LLMs remains in question. First, the suitability of current automatic metrics on LLMs' simplification evaluation is still uncertain. Second, current human evaluation approaches in sentence simplification often fall into two extremes: they are either too superficial, failing to offer a clear understanding of the models' performance, or overly detailed, making the annotation process complex and prone to inconsisten","authors_text":"Xuanxin Wu, Yuki Arase","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T00:19:24Z","title":"An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04963","kind":"arxiv","version":4},"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":"sha256:5ec8d394caaaad7b6edae783f0e5d2172ffcfea33b47eacfe6fd86c7f1999591","target":"record","created_at":"2026-07-05T11:35:48Z","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":"5c974b789eea754e6e0836e0e443e3048f1fa22d9b6b9f053a6868e4cfc6d8ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T00:19:24Z","title_canon_sha256":"f190f56acfd10db9227c403912af44d7212967aceed31f31f81d271a38678980"},"schema_version":"1.0","source":{"id":"2403.04963","kind":"arxiv","version":4}},"canonical_sha256":"c8b09d5fde5c3cb7d3cc9c13ae02b49123de5d3a467271c24ff1397437c06bcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8b09d5fde5c3cb7d3cc9c13ae02b49123de5d3a467271c24ff1397437c06bcd","first_computed_at":"2026-07-05T11:35:48.869993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:48.869993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VzWZywR3r4sAGU7J+/NpNc8TO/uvhIfHcF4gamnxGVq5eA6Regr8no3/a652sL1ZD8t/58U1GpCg7+kx8IEMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:48.870486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04963","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ec8d394caaaad7b6edae783f0e5d2172ffcfea33b47eacfe6fd86c7f1999591","sha256:daea8f6ff4ce6b86e79de6c863ddf646546ce07102fedaac22df39dfa650eed9"],"state_sha256":"91dea4a414430fb745d1cfd0bfb1cf90b6dcc65c479ad888ddc146a86b317bee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UIodXu5L9tKO2aiApTz+jVs9KWdv5S9aBeT9BrtRxZJsDr54r5z3IykPVP14SCgVlF0sdXWfGaEJgU77qf8+Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:25:20.541828Z","bundle_sha256":"5c3a99126b29d1c9fa13bee0a94e29910fc31ddf30a04cc78acf6ac8ae9b8cb4"}}