{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RMYE6REXLCSVGCUFLDKNM2MKQN","short_pith_number":"pith:RMYE6REX","schema_version":"1.0","canonical_sha256":"8b304f449758a5530a8558d4d6698a83471e10d983a8edbe6954e2ac3c96b397","source":{"kind":"arxiv","id":"2505.20088","version":2},"attestation_state":"computed","paper":{"title":"Multi-Domain Explainability of Preferences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liat Ein-Dor, Nitay Calderon, Roi Reichart","submitted_at":"2025-05-26T15:01:56Z","abstract_excerpt":"Preference mechanisms, such as human preference, LLM-as-a-Judge (LaaJ), and reward models, are central to aligning and evaluating large language models (LLMs). Yet, the underlying concepts that drive these preferences remain poorly understood. In this work, we propose a fully automated method for generating local and global concept-based explanations of preferences across multiple domains. Our method utilizes an LLM to identify concepts that distinguish between chosen and rejected responses, and to represent them with concept-based vectors. To model the relationships between concepts and prefe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.20088","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:01:56Z","cross_cats_sorted":[],"title_canon_sha256":"f4c5b3c2eb896b70a338b9452358773339c938f489052f55cb6de943f04257db","abstract_canon_sha256":"4909011ed0c6546fe3a5ccd28a193ab05a81287ccabaa9c86f946ce26184ff44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:46.861692Z","signature_b64":"Wry0bjV2iKdWf5Nyi601aJ+JUxUxOMRPsuRUgnyovKIx3B0fbLw/2uTqMVI+YQZtf0vbd2i9UOBeUfJoeAmECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b304f449758a5530a8558d4d6698a83471e10d983a8edbe6954e2ac3c96b397","last_reissued_at":"2026-07-05T11:11:46.861170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:46.861170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Domain Explainability of Preferences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liat Ein-Dor, Nitay Calderon, Roi Reichart","submitted_at":"2025-05-26T15:01:56Z","abstract_excerpt":"Preference mechanisms, such as human preference, LLM-as-a-Judge (LaaJ), and reward models, are central to aligning and evaluating large language models (LLMs). Yet, the underlying concepts that drive these preferences remain poorly understood. In this work, we propose a fully automated method for generating local and global concept-based explanations of preferences across multiple domains. Our method utilizes an LLM to identify concepts that distinguish between chosen and rejected responses, and to represent them with concept-based vectors. To model the relationships between concepts and prefe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20088","kind":"arxiv","version":2},"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/2505.20088/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.20088","created_at":"2026-07-05T11:11:46.861231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20088v2","created_at":"2026-07-05T11:11:46.861231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20088","created_at":"2026-07-05T11:11:46.861231+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMYE6REXLCSV","created_at":"2026-07-05T11:11:46.861231+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMYE6REXLCSVGCUF","created_at":"2026-07-05T11:11:46.861231+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMYE6REX","created_at":"2026-07-05T11:11:46.861231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN","json":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN.json","graph_json":"https://pith.science/api/pith-number/RMYE6REXLCSVGCUFLDKNM2MKQN/graph.json","events_json":"https://pith.science/api/pith-number/RMYE6REXLCSVGCUFLDKNM2MKQN/events.json","paper":"https://pith.science/paper/RMYE6REX"},"agent_actions":{"view_html":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN","download_json":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN.json","view_paper":"https://pith.science/paper/RMYE6REX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20088&json=true","fetch_graph":"https://pith.science/api/pith-number/RMYE6REXLCSVGCUFLDKNM2MKQN/graph.json","fetch_events":"https://pith.science/api/pith-number/RMYE6REXLCSVGCUFLDKNM2MKQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN/action/storage_attestation","attest_author":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN/action/author_attestation","sign_citation":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN/action/citation_signature","submit_replication":"https://pith.science/pith/RMYE6REXLCSVGCUFLDKNM2MKQN/action/replication_record"}},"created_at":"2026-07-05T11:11:46.861231+00:00","updated_at":"2026-07-05T11:11:46.861231+00:00"}