{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T44PWJWFIRGQP7MDIGZH52DQTI","short_pith_number":"pith:T44PWJWF","schema_version":"1.0","canonical_sha256":"9f38fb26c5444d07fd8341b27ee8709a2810beb8ed7f7fd0e117a4d1600a09aa","source":{"kind":"arxiv","id":"2311.09528","version":1},"attestation_state":"computed","paper":{"title":"HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aidan Swope, Daniel Egert, Jane Polak Scowcroft, Jiaqi Zeng, Makesh Narsimhan Sreedhar, Neel Kant, Oleksii Kuchaiev, Olivier Delalleau, Virginia Adams, Yi Dong, Zhilin Wang","submitted_at":"2023-11-16T03:13:29Z","abstract_excerpt":"Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally learn to model dataset artifacts (e.g. preferring longer but unhelpful responses only due to their length). To alleviate this problem, we collect HelpSteer, a multi-attribute helpfulness dataset annotated for the various aspects that make responses helpful. Specifically, our 37k-sample dataset has annotations for correctness, coherence, complexity, and verbosity in addition to overall helpfulness of responses. Training "},"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":"2311.09528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T03:13:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5c65361a7dd343dae6612abdb317b9f0b89c0a81aa2225067748336d9750355f","abstract_canon_sha256":"f20479b9ea0dd5d6cf5f18dada16ac120b6fc87325be3108e86943c8ec6106fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:29.336232Z","signature_b64":"g6dpGlgurGYCKSVL2VrqVaWnrTsYCVWYPh6rHTrTQeMhJwSQAqoSuRoWi+fjQLJpakB5LUsI/Rck+shWqAOGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f38fb26c5444d07fd8341b27ee8709a2810beb8ed7f7fd0e117a4d1600a09aa","last_reissued_at":"2026-07-05T07:13:29.335746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:29.335746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aidan Swope, Daniel Egert, Jane Polak Scowcroft, Jiaqi Zeng, Makesh Narsimhan Sreedhar, Neel Kant, Oleksii Kuchaiev, Olivier Delalleau, Virginia Adams, Yi Dong, Zhilin Wang","submitted_at":"2023-11-16T03:13:29Z","abstract_excerpt":"Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally learn to model dataset artifacts (e.g. preferring longer but unhelpful responses only due to their length). To alleviate this problem, we collect HelpSteer, a multi-attribute helpfulness dataset annotated for the various aspects that make responses helpful. Specifically, our 37k-sample dataset has annotations for correctness, coherence, complexity, and verbosity in addition to overall helpfulness of responses. Training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09528","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/2311.09528/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":"2311.09528","created_at":"2026-07-05T07:13:29.335803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09528v1","created_at":"2026-07-05T07:13:29.335803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09528","created_at":"2026-07-05T07:13:29.335803+00:00"},{"alias_kind":"pith_short_12","alias_value":"T44PWJWFIRGQ","created_at":"2026-07-05T07:13:29.335803+00:00"},{"alias_kind":"pith_short_16","alias_value":"T44PWJWFIRGQP7MD","created_at":"2026-07-05T07:13:29.335803+00:00"},{"alias_kind":"pith_short_8","alias_value":"T44PWJWF","created_at":"2026-07-05T07:13:29.335803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30076","citing_title":"UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06387","citing_title":"How Humans Help LLMs: Assessing and Incentivizing Human Preference Annotators","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10666","citing_title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19134","citing_title":"Incentivizing High-Quality Human Annotations with Golden Questions","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18113","citing_title":"VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11679","citing_title":"Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11679","citing_title":"Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":247,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI","json":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI.json","graph_json":"https://pith.science/api/pith-number/T44PWJWFIRGQP7MDIGZH52DQTI/graph.json","events_json":"https://pith.science/api/pith-number/T44PWJWFIRGQP7MDIGZH52DQTI/events.json","paper":"https://pith.science/paper/T44PWJWF"},"agent_actions":{"view_html":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI","download_json":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI.json","view_paper":"https://pith.science/paper/T44PWJWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09528&json=true","fetch_graph":"https://pith.science/api/pith-number/T44PWJWFIRGQP7MDIGZH52DQTI/graph.json","fetch_events":"https://pith.science/api/pith-number/T44PWJWFIRGQP7MDIGZH52DQTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI/action/storage_attestation","attest_author":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI/action/author_attestation","sign_citation":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI/action/citation_signature","submit_replication":"https://pith.science/pith/T44PWJWFIRGQP7MDIGZH52DQTI/action/replication_record"}},"created_at":"2026-07-05T07:13:29.335803+00:00","updated_at":"2026-07-05T07:13:29.335803+00:00"}