{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QFXCIYVRWWUFM67QVHAA7ILGED","short_pith_number":"pith:QFXCIYVR","schema_version":"1.0","canonical_sha256":"816e2462b1b5a8567bf0a9c00fa16620f6232bfb1f393f4abb50260232563e92","source":{"kind":"arxiv","id":"2501.03475","version":1},"attestation_state":"computed","paper":{"title":"Reading with Intent -- Neutralizing Intent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adar Avsian, Benjamin Reichman, Larry Heck","submitted_at":"2025-01-07T02:33:25Z","abstract_excerpt":"Queries to large language models (LLMs) can be divided into two parts: the instruction/question and the accompanying context. The context for retrieval-augmented generation (RAG) systems in most benchmarks comes from Wikipedia or Wikipedia-like texts which are written in a neutral and factual tone. However, when RAG systems retrieve internet-based content, they encounter text with diverse tones and linguistic styles, introducing challenges for downstream tasks. The Reading with Intent task addresses this issue by evaluating how varying tones in context passages affect model performance. Buildi"},"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":"2501.03475","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T02:33:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1c97b80c7a7402f4ea934bbc1d373e558b17c0cf19ccdf7cf56a2a292a045bd9","abstract_canon_sha256":"a7aa959aa772a30f58a1276751b0635e1cdccda3855a111c4dd38edb797db40b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:55.369506Z","signature_b64":"Apabc2/mdwZvy7zbKzitcypjbWGXoJeCapwob0UKjOlhN7wYTdS70qeY6oYKqLN+QGyQbRDEeSATA/OQD91eAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"816e2462b1b5a8567bf0a9c00fa16620f6232bfb1f393f4abb50260232563e92","last_reissued_at":"2026-07-05T09:57:55.368999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:55.368999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reading with Intent -- Neutralizing Intent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adar Avsian, Benjamin Reichman, Larry Heck","submitted_at":"2025-01-07T02:33:25Z","abstract_excerpt":"Queries to large language models (LLMs) can be divided into two parts: the instruction/question and the accompanying context. The context for retrieval-augmented generation (RAG) systems in most benchmarks comes from Wikipedia or Wikipedia-like texts which are written in a neutral and factual tone. However, when RAG systems retrieve internet-based content, they encounter text with diverse tones and linguistic styles, introducing challenges for downstream tasks. The Reading with Intent task addresses this issue by evaluating how varying tones in context passages affect model performance. Buildi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03475","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/2501.03475/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":"2501.03475","created_at":"2026-07-05T09:57:55.369054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03475v1","created_at":"2026-07-05T09:57:55.369054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03475","created_at":"2026-07-05T09:57:55.369054+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFXCIYVRWWUF","created_at":"2026-07-05T09:57:55.369054+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFXCIYVRWWUFM67Q","created_at":"2026-07-05T09:57:55.369054+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFXCIYVR","created_at":"2026-07-05T09:57:55.369054+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/QFXCIYVRWWUFM67QVHAA7ILGED","json":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED.json","graph_json":"https://pith.science/api/pith-number/QFXCIYVRWWUFM67QVHAA7ILGED/graph.json","events_json":"https://pith.science/api/pith-number/QFXCIYVRWWUFM67QVHAA7ILGED/events.json","paper":"https://pith.science/paper/QFXCIYVR"},"agent_actions":{"view_html":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED","download_json":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED.json","view_paper":"https://pith.science/paper/QFXCIYVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03475&json=true","fetch_graph":"https://pith.science/api/pith-number/QFXCIYVRWWUFM67QVHAA7ILGED/graph.json","fetch_events":"https://pith.science/api/pith-number/QFXCIYVRWWUFM67QVHAA7ILGED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED/action/storage_attestation","attest_author":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED/action/author_attestation","sign_citation":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED/action/citation_signature","submit_replication":"https://pith.science/pith/QFXCIYVRWWUFM67QVHAA7ILGED/action/replication_record"}},"created_at":"2026-07-05T09:57:55.369054+00:00","updated_at":"2026-07-05T09:57:55.369054+00:00"}