{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I4UKAJXVHIEEGTES3NEPDLGTHQ","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":"6da5f211420fe1147bd5c91fa1ddd580dc51bb2e842531bd86d7f725d0bc8d29","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T18:55:06Z","title_canon_sha256":"46a0f2c939d5dd5160b3684ecaefec63a3493efb8edccabaad5de334f917d32e"},"schema_version":"1.0","source":{"id":"2402.19465","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19465","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19465v2","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19465","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"I4UKAJXVHIEE","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"I4UKAJXVHIEEGTES","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"I4UKAJXV","created_at":"2026-07-05T09:01:30Z"}],"graph_snapshots":[{"event_id":"sha256:e4acde2f94a4e4fcae60bc9df3bce9a718cad8d99e2bb436797e4572011c6e52","target":"graph","created_at":"2026-07-05T09:01:30Z","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/2402.19465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness. In this paper, to reveal the untapped potential of pre-training, we pioneer the exploration of LLMs' trustworthiness during this period, focusing on five key dimensions: reliability, privacy, toxicity, fairness, and robustness. To begin with, we apply linear probing to LLMs. The high probing accuracy suggests that \\textit{LLMs in early pre-training can already distinguish concepts in each trustworthiness dimension}. ","authors_text":"Chen Qian, Dongrui Liu, Jie Zhang, Jing Shao, Wei Yao, Yong Liu, Yu Qiao, Zhenfei Yin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T18:55:06Z","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19465","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":"sha256:4aaa89702bc7d148ef42e2f5fd7cd1c99f134342bb5c29a0df4d5e81dfe2edd6","target":"record","created_at":"2026-07-05T09:01:30Z","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":"6da5f211420fe1147bd5c91fa1ddd580dc51bb2e842531bd86d7f725d0bc8d29","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T18:55:06Z","title_canon_sha256":"46a0f2c939d5dd5160b3684ecaefec63a3493efb8edccabaad5de334f917d32e"},"schema_version":"1.0","source":{"id":"2402.19465","kind":"arxiv","version":2}},"canonical_sha256":"4728a026f53a08434c92db48f1acd33c12433b374caf767091d97181e69a8698","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4728a026f53a08434c92db48f1acd33c12433b374caf767091d97181e69a8698","first_computed_at":"2026-07-05T09:01:30.529866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:30.529866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a1Jv0xfo/m5biIhOD78b9Lofx6mQM9a4ddGljPSppEps8TsPs1Q4UCjYkNk0Ygh6ficqbeZKPkVFL8kqIDvNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:30.530348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19465","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aaa89702bc7d148ef42e2f5fd7cd1c99f134342bb5c29a0df4d5e81dfe2edd6","sha256:e4acde2f94a4e4fcae60bc9df3bce9a718cad8d99e2bb436797e4572011c6e52"],"state_sha256":"a02e8aa14cbce5d35841ecdaabc2f9a6d77adea37e48daab3f58668f4156d99f"}