{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GGCSNKYDINHCFW3SCTN3FSAETC","short_pith_number":"pith:GGCSNKYD","canonical_record":{"source":{"id":"2407.18416","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T22:24:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ad657cc9bae754ba57b59ca87997f16566739927dd002eb347d72419d1068d1e","abstract_canon_sha256":"36396f13013f81cffc8aa31a3ddc2090b22ea16c9196f2a72dd698cfd9f5240e"},"schema_version":"1.0"},"canonical_sha256":"318526ab03434e22db7214dbb2c80498add578365cc7ee0a17e5b9771f65a878","source":{"kind":"arxiv","id":"2407.18416","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18416","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18416v5","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18416","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"GGCSNKYDINHC","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"GGCSNKYDINHCFW3S","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"GGCSNKYD","created_at":"2026-07-05T12:05:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GGCSNKYDINHCFW3SCTN3FSAETC","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18416","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T22:24:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ad657cc9bae754ba57b59ca87997f16566739927dd002eb347d72419d1068d1e","abstract_canon_sha256":"36396f13013f81cffc8aa31a3ddc2090b22ea16c9196f2a72dd698cfd9f5240e"},"schema_version":"1.0"},"canonical_sha256":"318526ab03434e22db7214dbb2c80498add578365cc7ee0a17e5b9771f65a878","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:09.411712Z","signature_b64":"iyrk7L4OqQfbAl3SHFhyv/EcepPX9M4pm/4RLuYu+U2Hn7ZtWWxqm0DyYUORvlC1TlVYFmRiTjD+eVGtgKtKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"318526ab03434e22db7214dbb2c80498add578365cc7ee0a17e5b9771f65a878","last_reissued_at":"2026-07-05T12:05:09.411131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:09.411131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18416","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXf4qxwwlAJzJCnXwu71ZMDz+zshgmkqHoRwGugZ7kubylkWbGL93hUzQ/M82vx5Sexbf3URbC0J/IqJxK2GCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:11:40.169722Z"},"content_sha256":"c3bbfe7c6b94443c4a7f48c0e6c497dc8463ac7ff3673449462df8b7b9cf3fe4","schema_version":"1.0","event_id":"sha256:c3bbfe7c6b94443c4a7f48c0e6c497dc8463ac7ff3673449462df8b7b9cf3fe4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GGCSNKYDINHCFW3SCTN3FSAETC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PersonaGym: Evaluating Persona Agents and LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ameet Deshpande, Ashwin Kalyan, Henry Peng Zou, Karthik Narasimhan, Shreyas Chaudhari, Tanmay Rajpurohit, Vinay Samuel, Vishvak Murahari, Yue Zhou","submitted_at":"2024-07-25T22:24:45Z","abstract_excerpt":"Persona agents, which are LLM agents conditioned to act according to an assigned persona, enable contextually rich and user aligned interactions across domains like education and healthcare. However, evaluating how faithfully these agents adhere to their personas remains a significant challenge, particularly in free-form settings that demand consistency across diverse, persona-relevant environments. We introduce PersonaGym, the first dynamic evaluation framework for persona agents, and PersonaScore, a human-aligned automatic metric grounded in decision theory that enables comprehensive large-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18416","kind":"arxiv","version":5},"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/2407.18416/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":"2026-07-05T12:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BpLj6NNWhCla/kw9upVQXCKfycPNDGyeG63vweiSU1xsBwEmaAPTbD4EQxbcVLN1zJ4BSZ6Yrmof/nUU27vKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:11:40.170324Z"},"content_sha256":"0bc5d993e5236b78c98c666adecebc4ba71b37b032824a01209345bd95d5151f","schema_version":"1.0","event_id":"sha256:0bc5d993e5236b78c98c666adecebc4ba71b37b032824a01209345bd95d5151f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/bundle.json","state_url":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGCSNKYDINHCFW3SCTN3FSAETC/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":"2026-07-09T03:11:40Z","links":{"resolver":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC","bundle":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/bundle.json","state":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGCSNKYDINHCFW3SCTN3FSAETC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GGCSNKYDINHCFW3SCTN3FSAETC","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":"36396f13013f81cffc8aa31a3ddc2090b22ea16c9196f2a72dd698cfd9f5240e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T22:24:45Z","title_canon_sha256":"ad657cc9bae754ba57b59ca87997f16566739927dd002eb347d72419d1068d1e"},"schema_version":"1.0","source":{"id":"2407.18416","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18416","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18416v5","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18416","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"GGCSNKYDINHC","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"GGCSNKYDINHCFW3S","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"GGCSNKYD","created_at":"2026-07-05T12:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:0bc5d993e5236b78c98c666adecebc4ba71b37b032824a01209345bd95d5151f","target":"graph","created_at":"2026-07-05T12:05:09Z","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/2407.18416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Persona agents, which are LLM agents conditioned to act according to an assigned persona, enable contextually rich and user aligned interactions across domains like education and healthcare. However, evaluating how faithfully these agents adhere to their personas remains a significant challenge, particularly in free-form settings that demand consistency across diverse, persona-relevant environments. We introduce PersonaGym, the first dynamic evaluation framework for persona agents, and PersonaScore, a human-aligned automatic metric grounded in decision theory that enables comprehensive large-s","authors_text":"Ameet Deshpande, Ashwin Kalyan, Henry Peng Zou, Karthik Narasimhan, Shreyas Chaudhari, Tanmay Rajpurohit, Vinay Samuel, Vishvak Murahari, Yue Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T22:24:45Z","title":"PersonaGym: Evaluating Persona Agents and LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18416","kind":"arxiv","version":5},"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:c3bbfe7c6b94443c4a7f48c0e6c497dc8463ac7ff3673449462df8b7b9cf3fe4","target":"record","created_at":"2026-07-05T12:05:09Z","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":"36396f13013f81cffc8aa31a3ddc2090b22ea16c9196f2a72dd698cfd9f5240e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T22:24:45Z","title_canon_sha256":"ad657cc9bae754ba57b59ca87997f16566739927dd002eb347d72419d1068d1e"},"schema_version":"1.0","source":{"id":"2407.18416","kind":"arxiv","version":5}},"canonical_sha256":"318526ab03434e22db7214dbb2c80498add578365cc7ee0a17e5b9771f65a878","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"318526ab03434e22db7214dbb2c80498add578365cc7ee0a17e5b9771f65a878","first_computed_at":"2026-07-05T12:05:09.411131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:09.411131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iyrk7L4OqQfbAl3SHFhyv/EcepPX9M4pm/4RLuYu+U2Hn7ZtWWxqm0DyYUORvlC1TlVYFmRiTjD+eVGtgKtKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:09.411712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18416","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3bbfe7c6b94443c4a7f48c0e6c497dc8463ac7ff3673449462df8b7b9cf3fe4","sha256:0bc5d993e5236b78c98c666adecebc4ba71b37b032824a01209345bd95d5151f"],"state_sha256":"6e0f3d5776e019ffa6a19a97ef77d266420f929f8fb423881827aaa1b6c122ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTMJfInFGgyBwVuhyYQn7TDIxVRJ6GTWQul5WqzuODhxkyIHkfHp41H279PPJCkuT1hEHPAoC/oD5obdYNsyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:11:40.173270Z","bundle_sha256":"6e86d63d763acdd06c85cc33228e484a74b0743c33629cea7e3bec378d2ada91"}}