{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7CIIIAOK6Y6LGAFC3INIJSVDJN","short_pith_number":"pith:7CIIIAOK","schema_version":"1.0","canonical_sha256":"f8908401caf63cb300a2da1a84caa34b7b59ae5f3564e02663532b0982315a9b","source":{"kind":"arxiv","id":"2404.04817","version":1},"attestation_state":"computed","paper":{"title":"FRACTAL: Fine-Grained Scoring from Aggregate Text Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aravindan Raghuveer, Priyanka Agrawal, Rishi Saket, Yukti Makhija","submitted_at":"2024-04-07T05:54:28Z","abstract_excerpt":"Large language models (LLMs) are being increasingly tuned to power complex generation tasks such as writing, fact-seeking, querying and reasoning. Traditionally, human or model feedback for evaluating and further tuning LLM performance has been provided at the response level, enabling faster and more cost-effective assessments. However, recent works (Amplayo et al. [2022], Wu et al. [2023]) indicate that sentence-level labels may provide more accurate and interpretable feedback for LLM optimization. In this work, we introduce methods to disaggregate response-level labels into sentence-level (p"},"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":"2404.04817","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-07T05:54:28Z","cross_cats_sorted":[],"title_canon_sha256":"0f44e3616b3aad2fff0741cb8f7726091743691bd73b47d943a0f60ef52288fe","abstract_canon_sha256":"8118627b9a676e66f20160cd883b9262df62e9af01b74d3a68ecc8cae13ed727"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:22.232672Z","signature_b64":"r/W/tB/i9sSKGf14GMw+naJQcWOfwz+iMmTG89YIcm7OsriWpq33qRR74jhxWh37qbVPgCNRMzufHFFSe/ajCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8908401caf63cb300a2da1a84caa34b7b59ae5f3564e02663532b0982315a9b","last_reissued_at":"2026-07-05T08:05:22.232242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:22.232242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRACTAL: Fine-Grained Scoring from Aggregate Text Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aravindan Raghuveer, Priyanka Agrawal, Rishi Saket, Yukti Makhija","submitted_at":"2024-04-07T05:54:28Z","abstract_excerpt":"Large language models (LLMs) are being increasingly tuned to power complex generation tasks such as writing, fact-seeking, querying and reasoning. Traditionally, human or model feedback for evaluating and further tuning LLM performance has been provided at the response level, enabling faster and more cost-effective assessments. However, recent works (Amplayo et al. [2022], Wu et al. [2023]) indicate that sentence-level labels may provide more accurate and interpretable feedback for LLM optimization. In this work, we introduce methods to disaggregate response-level labels into sentence-level (p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04817","kind":"arxiv","version":1},"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/2404.04817/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":"2404.04817","created_at":"2026-07-05T08:05:22.232300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04817v1","created_at":"2026-07-05T08:05:22.232300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04817","created_at":"2026-07-05T08:05:22.232300+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CIIIAOK6Y6L","created_at":"2026-07-05T08:05:22.232300+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CIIIAOK6Y6LGAFC","created_at":"2026-07-05T08:05:22.232300+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CIIIAOK","created_at":"2026-07-05T08:05:22.232300+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/7CIIIAOK6Y6LGAFC3INIJSVDJN","json":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN.json","graph_json":"https://pith.science/api/pith-number/7CIIIAOK6Y6LGAFC3INIJSVDJN/graph.json","events_json":"https://pith.science/api/pith-number/7CIIIAOK6Y6LGAFC3INIJSVDJN/events.json","paper":"https://pith.science/paper/7CIIIAOK"},"agent_actions":{"view_html":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN","download_json":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN.json","view_paper":"https://pith.science/paper/7CIIIAOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04817&json=true","fetch_graph":"https://pith.science/api/pith-number/7CIIIAOK6Y6LGAFC3INIJSVDJN/graph.json","fetch_events":"https://pith.science/api/pith-number/7CIIIAOK6Y6LGAFC3INIJSVDJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN/action/storage_attestation","attest_author":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN/action/author_attestation","sign_citation":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN/action/citation_signature","submit_replication":"https://pith.science/pith/7CIIIAOK6Y6LGAFC3INIJSVDJN/action/replication_record"}},"created_at":"2026-07-05T08:05:22.232300+00:00","updated_at":"2026-07-05T08:05:22.232300+00:00"}