{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OI2CYFMM3TYWZEYEGWEBR65IQF","short_pith_number":"pith:OI2CYFMM","canonical_record":{"source":{"id":"2310.03304","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T04:15:48Z","cross_cats_sorted":[],"title_canon_sha256":"5daacbf794b1c88ca70e1df211379295ac945a929fbd4b5d17bf7acda8f069d2","abstract_canon_sha256":"f2654f2908ee5908c1bb80c8b344bc46cd6f3d70ccaee2fb1d32877b6bc09b6f"},"schema_version":"1.0"},"canonical_sha256":"72342c158cdcf16c9304358818fba88161242ace3c3a29c73cef04642a77c911","source":{"kind":"arxiv","id":"2310.03304","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03304","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03304v5","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03304","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"OI2CYFMM3TYW","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"OI2CYFMM3TYWZEYE","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"OI2CYFMM","created_at":"2026-07-05T09:15:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OI2CYFMM3TYWZEYEGWEBR65IQF","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03304","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T04:15:48Z","cross_cats_sorted":[],"title_canon_sha256":"5daacbf794b1c88ca70e1df211379295ac945a929fbd4b5d17bf7acda8f069d2","abstract_canon_sha256":"f2654f2908ee5908c1bb80c8b344bc46cd6f3d70ccaee2fb1d32877b6bc09b6f"},"schema_version":"1.0"},"canonical_sha256":"72342c158cdcf16c9304358818fba88161242ace3c3a29c73cef04642a77c911","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:27.122783Z","signature_b64":"V23uJR3juiRJ0/I3gbfsygUGZmBZNhI1y+/TSJoaA0n7U8OwepXoM4/4wyt38Gnh5uMwA2gtAzfwzJpf2w1qDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72342c158cdcf16c9304358818fba88161242ace3c3a29c73cef04642a77c911","last_reissued_at":"2026-07-05T09:15:27.122299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:27.122299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03304","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":"2026-07-05T09:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MUP/bAmVA84wDcdDIgpd+yAjPpFcrtEQsWK7Lhf7guWjTcDDMWMH6nqsY9gsF1bKfl52uvcytwqQSTyyBAi7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:04:25.430444Z"},"content_sha256":"71668cc94d4afb98ed7c6343838d6663eb5d69ca2129daa6197241248a099c06","schema_version":"1.0","event_id":"sha256:71668cc94d4afb98ed7c6343838d6663eb5d69ca2129daa6197241248a099c06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OI2CYFMM3TYWZEYEGWEBR65IQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Personalized Alignment for Evaluating Open-ended Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Cohen, Danqing Wang, Hanlin Zhu, Kevin Yang, Lei Li, Xiaomeng Yang, Yuandong Tian","submitted_at":"2023-10-05T04:15:48Z","abstract_excerpt":"Recent research has increasingly focused on evaluating large language models' (LLMs) alignment with diverse human values and preferences, particularly for open-ended tasks like story generation. Traditional evaluation metrics rely heavily on lexical similarity with human-written references, often showing poor correlation with human judgments and failing to account for alignment with the diversity of human preferences. To address these challenges, we introduce PerSE, an interpretable evaluation framework designed to assess alignment with specific human preferences. It is tuned to infer specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03304","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/2310.03304/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":"2026-07-05T09:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0SAdZnoQ2DSXxvQEwx3Fd1TYjDMFlMUT1wTtuLLXMphHg4rVEM42fyYJDPHlRyxCdlGjnrqlWPg13j6MJplDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:04:25.430971Z"},"content_sha256":"8a604b83a272ca3decf354f79de7ddb7ca8d1bc809279f531adbba37c5dfad28","schema_version":"1.0","event_id":"sha256:8a604b83a272ca3decf354f79de7ddb7ca8d1bc809279f531adbba37c5dfad28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OI2CYFMM3TYWZEYEGWEBR65IQF/bundle.json","state_url":"https://pith.science/pith/OI2CYFMM3TYWZEYEGWEBR65IQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OI2CYFMM3TYWZEYEGWEBR65IQF/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":"2026-08-04T19:04:25Z","links":{"resolver":"https://pith.science/pith/OI2CYFMM3TYWZEYEGWEBR65IQF","bundle":"https://pith.science/pith/OI2CYFMM3TYWZEYEGWEBR65IQF/bundle.json","state":"https://pith.science/pith/OI2CYFMM3TYWZEYEGWEBR65IQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OI2CYFMM3TYWZEYEGWEBR65IQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OI2CYFMM3TYWZEYEGWEBR65IQF","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":"f2654f2908ee5908c1bb80c8b344bc46cd6f3d70ccaee2fb1d32877b6bc09b6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T04:15:48Z","title_canon_sha256":"5daacbf794b1c88ca70e1df211379295ac945a929fbd4b5d17bf7acda8f069d2"},"schema_version":"1.0","source":{"id":"2310.03304","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03304","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03304v5","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03304","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"OI2CYFMM3TYW","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"OI2CYFMM3TYWZEYE","created_at":"2026-07-05T09:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"OI2CYFMM","created_at":"2026-07-05T09:15:27Z"}],"graph_snapshots":[{"event_id":"sha256:8a604b83a272ca3decf354f79de7ddb7ca8d1bc809279f531adbba37c5dfad28","target":"graph","created_at":"2026-07-05T09:15:27Z","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/2310.03304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has increasingly focused on evaluating large language models' (LLMs) alignment with diverse human values and preferences, particularly for open-ended tasks like story generation. Traditional evaluation metrics rely heavily on lexical similarity with human-written references, often showing poor correlation with human judgments and failing to account for alignment with the diversity of human preferences. To address these challenges, we introduce PerSE, an interpretable evaluation framework designed to assess alignment with specific human preferences. It is tuned to infer specific","authors_text":"Andrew Cohen, Danqing Wang, Hanlin Zhu, Kevin Yang, Lei Li, Xiaomeng Yang, Yuandong Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T04:15:48Z","title":"Learning Personalized Alignment for Evaluating Open-ended Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03304","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":"sha256:71668cc94d4afb98ed7c6343838d6663eb5d69ca2129daa6197241248a099c06","target":"record","created_at":"2026-07-05T09:15:27Z","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":"f2654f2908ee5908c1bb80c8b344bc46cd6f3d70ccaee2fb1d32877b6bc09b6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T04:15:48Z","title_canon_sha256":"5daacbf794b1c88ca70e1df211379295ac945a929fbd4b5d17bf7acda8f069d2"},"schema_version":"1.0","source":{"id":"2310.03304","kind":"arxiv","version":5}},"canonical_sha256":"72342c158cdcf16c9304358818fba88161242ace3c3a29c73cef04642a77c911","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72342c158cdcf16c9304358818fba88161242ace3c3a29c73cef04642a77c911","first_computed_at":"2026-07-05T09:15:27.122299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:27.122299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V23uJR3juiRJ0/I3gbfsygUGZmBZNhI1y+/TSJoaA0n7U8OwepXoM4/4wyt38Gnh5uMwA2gtAzfwzJpf2w1qDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:27.122783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03304","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71668cc94d4afb98ed7c6343838d6663eb5d69ca2129daa6197241248a099c06","sha256:8a604b83a272ca3decf354f79de7ddb7ca8d1bc809279f531adbba37c5dfad28"],"state_sha256":"3ca52bdec4c864178dc9fec5836cba0281b1f7cbe4bd7c2068a7a3d1cb7b4381"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiqkEkB0mqQuojkP2VjAN5IeYq1O2tyev9hdwNMqdQ/EypqyltXS7hcjNCxxOf+H30hTdYyiPPnNvrcqBNmrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:04:25.435021Z","bundle_sha256":"2bcb05e525b44789d421061a4befeea8a6cc841cc272172b1f950006e1f53faa"}}