{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YYTSWQG2J4ZQML2X356PSV4V55","short_pith_number":"pith:YYTSWQG2","canonical_record":{"source":{"id":"2410.16491","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T20:32:27Z","cross_cats_sorted":[],"title_canon_sha256":"54cb9c374714afff2571be4496d6f782742044fe6d087bcb23e493feacc552b9","abstract_canon_sha256":"1f46d75e308d4a0e390aeb5a11e540cf9faffc3df34d48f5e0afbb4ed2933cc9"},"schema_version":"1.0"},"canonical_sha256":"c6272b40da4f33062f57df7cf95795ef547d79d3a0497cc76f62ae8113949ff0","source":{"kind":"arxiv","id":"2410.16491","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16491","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16491v3","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16491","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"YYTSWQG2J4ZQ","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"pith_short_16","alias_value":"YYTSWQG2J4ZQML2X","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"pith_short_8","alias_value":"YYTSWQG2","created_at":"2026-07-05T11:44:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YYTSWQG2J4ZQML2X356PSV4V55","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16491","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T20:32:27Z","cross_cats_sorted":[],"title_canon_sha256":"54cb9c374714afff2571be4496d6f782742044fe6d087bcb23e493feacc552b9","abstract_canon_sha256":"1f46d75e308d4a0e390aeb5a11e540cf9faffc3df34d48f5e0afbb4ed2933cc9"},"schema_version":"1.0"},"canonical_sha256":"c6272b40da4f33062f57df7cf95795ef547d79d3a0497cc76f62ae8113949ff0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:42.361672Z","signature_b64":"Kgy5fCf8AaDhHypaYXo3Jh59/lIOzCr8FV3SyoRLG0e12fC0xIzhYW72pFltJKILi+vwzWILRwI57H2PtzbOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6272b40da4f33062f57df7cf95795ef547d79d3a0497cc76f62ae8113949ff0","last_reissued_at":"2026-07-05T11:44:42.361091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:42.361091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16491","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":"2026-07-05T11:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h18jQCdw/PT2+3A2MFH7JvbKNwxkn5hglgJhXdoqhi5N2dvuwusZ8kNJDRIlx48rRHpnxuUwCgCaAOmiA23IBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:46:36.380849Z"},"content_sha256":"1648727c3b0214018b8f0476d658ef369e693605788f9343917a3d5dac108bf0","schema_version":"1.0","event_id":"sha256:1648727c3b0214018b8f0476d658ef369e693605788f9343917a3d5dac108bf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YYTSWQG2J4ZQML2X356PSV4V55","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andy Liu, Jiarui Liu, Maarten Sap, Mona Diab, Wenkai Li, Xuhui Zhou","submitted_at":"2024-10-21T20:32:27Z","abstract_excerpt":"In this work, we tackle the challenge of embedding realistic human personality traits into LLMs. Previous approaches have primarily focused on prompt-based methods that describe the behavior associated with the desired personality traits, suffering from realism and validity issues. To address these limitations, we introduce BIG5-CHAT, a large-scale dataset containing 100,000 dialogues designed to ground models in how humans express their personality in language. Leveraging this dataset, we explore Supervised Fine-Tuning and Direct Preference Optimization as training-based methods to align LLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16491","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/2410.16491/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":"2026-07-05T11:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hy3ffz87TazpxDC4A5WjWJDgK0Zor69+LFEyzKeoStvaPtuzqBLrrBOqY2QBJVVjNjQsPloavu/WLQOHAH8jCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:46:36.381335Z"},"content_sha256":"ce83e07252aa2d18d440ed522c4c7feb86bc914179a4590409170c701ff74896","schema_version":"1.0","event_id":"sha256:ce83e07252aa2d18d440ed522c4c7feb86bc914179a4590409170c701ff74896"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/bundle.json","state_url":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYTSWQG2J4ZQML2X356PSV4V55/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":"2026-08-08T11:46:36Z","links":{"resolver":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55","bundle":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/bundle.json","state":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYTSWQG2J4ZQML2X356PSV4V55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YYTSWQG2J4ZQML2X356PSV4V55","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":"1f46d75e308d4a0e390aeb5a11e540cf9faffc3df34d48f5e0afbb4ed2933cc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T20:32:27Z","title_canon_sha256":"54cb9c374714afff2571be4496d6f782742044fe6d087bcb23e493feacc552b9"},"schema_version":"1.0","source":{"id":"2410.16491","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16491","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16491v3","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16491","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"YYTSWQG2J4ZQ","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"pith_short_16","alias_value":"YYTSWQG2J4ZQML2X","created_at":"2026-07-05T11:44:42Z"},{"alias_kind":"pith_short_8","alias_value":"YYTSWQG2","created_at":"2026-07-05T11:44:42Z"}],"graph_snapshots":[{"event_id":"sha256:ce83e07252aa2d18d440ed522c4c7feb86bc914179a4590409170c701ff74896","target":"graph","created_at":"2026-07-05T11:44:42Z","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/2410.16491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we tackle the challenge of embedding realistic human personality traits into LLMs. Previous approaches have primarily focused on prompt-based methods that describe the behavior associated with the desired personality traits, suffering from realism and validity issues. To address these limitations, we introduce BIG5-CHAT, a large-scale dataset containing 100,000 dialogues designed to ground models in how humans express their personality in language. Leveraging this dataset, we explore Supervised Fine-Tuning and Direct Preference Optimization as training-based methods to align LLMs","authors_text":"Andy Liu, Jiarui Liu, Maarten Sap, Mona Diab, Wenkai Li, Xuhui Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T20:32:27Z","title":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16491","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":"sha256:1648727c3b0214018b8f0476d658ef369e693605788f9343917a3d5dac108bf0","target":"record","created_at":"2026-07-05T11:44:42Z","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":"1f46d75e308d4a0e390aeb5a11e540cf9faffc3df34d48f5e0afbb4ed2933cc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T20:32:27Z","title_canon_sha256":"54cb9c374714afff2571be4496d6f782742044fe6d087bcb23e493feacc552b9"},"schema_version":"1.0","source":{"id":"2410.16491","kind":"arxiv","version":3}},"canonical_sha256":"c6272b40da4f33062f57df7cf95795ef547d79d3a0497cc76f62ae8113949ff0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6272b40da4f33062f57df7cf95795ef547d79d3a0497cc76f62ae8113949ff0","first_computed_at":"2026-07-05T11:44:42.361091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:42.361091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kgy5fCf8AaDhHypaYXo3Jh59/lIOzCr8FV3SyoRLG0e12fC0xIzhYW72pFltJKILi+vwzWILRwI57H2PtzbOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:42.361672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16491","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1648727c3b0214018b8f0476d658ef369e693605788f9343917a3d5dac108bf0","sha256:ce83e07252aa2d18d440ed522c4c7feb86bc914179a4590409170c701ff74896"],"state_sha256":"50117d2bdd188ed91bb606498d2b16916f62094ce9e000b252aa8bdfa16d3b50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+BhKbDIK+Uz2r6rjrcB2hr3Dn+W2E5thueIYbQH+nA53i9rrQcRwpw/H9XR/iZdRrwwoRYvxmgIEhkzhEyQoCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:46:36.384442Z","bundle_sha256":"72e01cfa49a0ff95cb85116e2a164ab24f01c3890f24eeb54cdc82a5b9d3a62f"}}