{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KJUHOKWB7UI7ATLOBLQF4WU5QF","short_pith_number":"pith:KJUHOKWB","canonical_record":{"source":{"id":"2412.16783","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T21:40:31Z","cross_cats_sorted":[],"title_canon_sha256":"214b47276b4b68b87d18a1edd8f4e7dc472609626644b481adb7e331b3170a79","abstract_canon_sha256":"06115d51e914509b71492d52122f545bb33dfc70482b085a58e63746e00daa2b"},"schema_version":"1.0"},"canonical_sha256":"5268772ac1fd11f04d6e0ae05e5a9d815db3565429b3943a01571d563b17a88c","source":{"kind":"arxiv","id":"2412.16783","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16783","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16783v3","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16783","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"KJUHOKWB7UI7","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"KJUHOKWB7UI7ATLO","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"KJUHOKWB","created_at":"2026-07-01T00:17:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KJUHOKWB7UI7ATLOBLQF4WU5QF","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16783","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T21:40:31Z","cross_cats_sorted":[],"title_canon_sha256":"214b47276b4b68b87d18a1edd8f4e7dc472609626644b481adb7e331b3170a79","abstract_canon_sha256":"06115d51e914509b71492d52122f545bb33dfc70482b085a58e63746e00daa2b"},"schema_version":"1.0"},"canonical_sha256":"5268772ac1fd11f04d6e0ae05e5a9d815db3565429b3943a01571d563b17a88c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:07.690481Z","signature_b64":"c478tVjwSCmmger3ubIlQlpvV4vrkfk/nnA1fLnTNQWV8W4JvM4AjovN5Br4AcnMckP43MvfDxiRbTnfq+zjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5268772ac1fd11f04d6e0ae05e5a9d815db3565429b3943a01571d563b17a88c","last_reissued_at":"2026-07-01T00:17:07.689978Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:07.689978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16783","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":"2026-07-01T00:17:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F16MwFwkSwylu3wttiawt2X6//rAp4VtipL/M8t5BJllh583zACgjyVhHLf92XkkVXyeTo6brBl0Qba5bhXqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:28:22.727443Z"},"content_sha256":"6fb1636fe2e9a371f794ab9a2ab05c337f89906cebc6bfc64818a5d5d48c0963","schema_version":"1.0","event_id":"sha256:6fb1636fe2e9a371f794ab9a2ab05c337f89906cebc6bfc64818a5d5d48c0963"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KJUHOKWB7UI7ATLOBLQF4WU5QF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gianluca Demartini, Leon Fr\\\"ohling, Pietro Bernardelle, Stefano Civelli","submitted_at":"2024-12-21T21:40:31Z","abstract_excerpt":"As increasingly capable large language models (LLMs) emerge, researchers have begun exploring their potential for subjective tasks. While recent work demonstrates that LLMs can be aligned with diverse human perspectives, evaluating this alignment on downstream tasks (e.g., hate speech detection) remains challenging due to the use of inconsistent datasets across studies. To address this issue, in this resource paper we propose a two-step framework: we (1) introduce SubData, an open-source Python library designed for standardizing heterogeneous datasets to evaluate LLMs perspective alignment; an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16783","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/2412.16783/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":"2026-07-01T00:17:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2U6zSnPrlrnIYvgP5Rk4rsseh8xZ6EU3/z7mZSMwegL4KiIHykWXW3Ub/v73SpLJgbNL1Bl51y8HoYgwO7IBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:28:22.727817Z"},"content_sha256":"10fa38aa5d53eca3b524ddb9e5c8b3a72e5e465b3733a9fb9978a5a4876aaaa1","schema_version":"1.0","event_id":"sha256:10fa38aa5d53eca3b524ddb9e5c8b3a72e5e465b3733a9fb9978a5a4876aaaa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJUHOKWB7UI7ATLOBLQF4WU5QF/bundle.json","state_url":"https://pith.science/pith/KJUHOKWB7UI7ATLOBLQF4WU5QF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJUHOKWB7UI7ATLOBLQF4WU5QF/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":"2026-07-02T23:28:22Z","links":{"resolver":"https://pith.science/pith/KJUHOKWB7UI7ATLOBLQF4WU5QF","bundle":"https://pith.science/pith/KJUHOKWB7UI7ATLOBLQF4WU5QF/bundle.json","state":"https://pith.science/pith/KJUHOKWB7UI7ATLOBLQF4WU5QF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJUHOKWB7UI7ATLOBLQF4WU5QF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KJUHOKWB7UI7ATLOBLQF4WU5QF","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":"06115d51e914509b71492d52122f545bb33dfc70482b085a58e63746e00daa2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T21:40:31Z","title_canon_sha256":"214b47276b4b68b87d18a1edd8f4e7dc472609626644b481adb7e331b3170a79"},"schema_version":"1.0","source":{"id":"2412.16783","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16783","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16783v3","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16783","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"KJUHOKWB7UI7","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"KJUHOKWB7UI7ATLO","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"KJUHOKWB","created_at":"2026-07-01T00:17:07Z"}],"graph_snapshots":[{"event_id":"sha256:10fa38aa5d53eca3b524ddb9e5c8b3a72e5e465b3733a9fb9978a5a4876aaaa1","target":"graph","created_at":"2026-07-01T00:17:07Z","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/2412.16783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As increasingly capable large language models (LLMs) emerge, researchers have begun exploring their potential for subjective tasks. While recent work demonstrates that LLMs can be aligned with diverse human perspectives, evaluating this alignment on downstream tasks (e.g., hate speech detection) remains challenging due to the use of inconsistent datasets across studies. To address this issue, in this resource paper we propose a two-step framework: we (1) introduce SubData, an open-source Python library designed for standardizing heterogeneous datasets to evaluate LLMs perspective alignment; an","authors_text":"Gianluca Demartini, Leon Fr\\\"ohling, Pietro Bernardelle, Stefano Civelli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T21:40:31Z","title":"SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16783","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":"sha256:6fb1636fe2e9a371f794ab9a2ab05c337f89906cebc6bfc64818a5d5d48c0963","target":"record","created_at":"2026-07-01T00:17:07Z","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":"06115d51e914509b71492d52122f545bb33dfc70482b085a58e63746e00daa2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T21:40:31Z","title_canon_sha256":"214b47276b4b68b87d18a1edd8f4e7dc472609626644b481adb7e331b3170a79"},"schema_version":"1.0","source":{"id":"2412.16783","kind":"arxiv","version":3}},"canonical_sha256":"5268772ac1fd11f04d6e0ae05e5a9d815db3565429b3943a01571d563b17a88c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5268772ac1fd11f04d6e0ae05e5a9d815db3565429b3943a01571d563b17a88c","first_computed_at":"2026-07-01T00:17:07.689978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T00:17:07.689978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c478tVjwSCmmger3ubIlQlpvV4vrkfk/nnA1fLnTNQWV8W4JvM4AjovN5Br4AcnMckP43MvfDxiRbTnfq+zjDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T00:17:07.690481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16783","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fb1636fe2e9a371f794ab9a2ab05c337f89906cebc6bfc64818a5d5d48c0963","sha256:10fa38aa5d53eca3b524ddb9e5c8b3a72e5e465b3733a9fb9978a5a4876aaaa1"],"state_sha256":"71bef51570e3945af6374a5fd831dff3560f8725f3a6b270358d1396bbff35d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wpalbv9MHkmYSh5Udu92nuoang1isE2PqmgRD4CPWiR18kw9zcg1FeFiLwlExCAmygwdIHianic0I5DDxQ79AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T23:28:22.729882Z","bundle_sha256":"792610509ed9557596327247d8547d2f9a4cbbc2f7bbd209ba75d8db40ea28b4"}}