{"alignment_dimensions_with_observations":[],"alignment_dimensions_without_observations":["authorized_goal_following","constraint_compliance","non_deception","oversight_and_correction","robustness"],"configuration":{"identity":"Source label only; provider, revision and effort not pinned by this table."},"content_sha256":"1a5c4534a412d978f85842406933b8f1ab7a61197321ae80e6aada0e84375416","coverage_meaning":"At least one observation, not complete or validated dimension coverage.","evidence_status":"recorded","honesty_dimensions_with_observations":["evidence_support"],"honesty_dimensions_without_observations":["belief_revision","citation_integrity","factual_accuracy","pressure_resistance","uncertainty"],"id":"hm-7f094de9380bdcc9bcd2","integrity_meaning":"Content-addressed record only; not an authenticated issuer signature or independent scientific validation.","lab":"Anthropic","limitations":["Exact configuration and trial-level evidence unavailable in this snapshot."],"mark_status":"not_awarded","model_label":"anthropic/claude-opus-4-7","observations":[{"aggregation_blocker":"Exact configuration and trial-level evidence unavailable in this snapshot.","cohort":"vectara:af0e3207741054b44e7c87688a40a815ecf446df","confidence_interval":null,"configuration":{"identity":"Source label only; provider, revision and effort not pinned by this table."},"configuration_id":"vectara:af0e3207741054b44e7c87688a40a815ecf446df:anthropic/claude-opus-4-7","definition":"Source-reported rate of responding to the summarization request; not factual correctness.","denominator":null,"direction":"higher","evaluation_date":null,"evidence_class":"benchmark_publisher_reported","lab":"Anthropic","metric":"answer_rate","model_label":"anthropic/claude-opus-4-7","numerator":null,"overall_score":null,"pillar":"usefulness_context","profile_id":"hm-7f094de9380bdcc9bcd2","rank":82,"rank_meaning":"Descriptive native-metric order; not a significance or overall honesty rank.","source":"vectara","source_sha256":"525064e64eac0f096de3528b3516032486a745d141b352b1ee12925589d63616","source_updated":"September 22, 2026","source_url":"https://github.com/vectara/hallucination-leaderboard/blob/af0e3207741054b44e7c87688a40a815ecf446df/README.md","split":"publisher_private_dataset","track":"honesty_evidence","uncertainty_note":"No inferential interval reconstructed from aggregate source values.","unit":"percent","value":98.0},{"aggregation_blocker":"Exact configuration and trial-level evidence unavailable in this snapshot.","cohort":"vectara:af0e3207741054b44e7c87688a40a815ecf446df","confidence_interval":null,"configuration":{"identity":"Source label only; provider, revision and effort not pinned by this table."},"configuration_id":"vectara:af0e3207741054b44e7c87688a40a815ecf446df:anthropic/claude-opus-4-7","definition":"Source-reported factual consistency; complement of hallucination rate, not independent evidence.","denominator":null,"direction":"higher","evaluation_date":null,"evidence_class":"benchmark_publisher_reported","lab":"Anthropic","metric":"factual_consistency_rate","model_label":"anthropic/claude-opus-4-7","numerator":null,"overall_score":null,"pillar":"evidence_support","profile_id":"hm-7f094de9380bdcc9bcd2","rank":78,"rank_meaning":"Descriptive native-metric order; not a significance or overall honesty rank.","source":"vectara","source_sha256":"525064e64eac0f096de3528b3516032486a745d141b352b1ee12925589d63616","source_updated":"September 22, 2026","source_url":"https://github.com/vectara/hallucination-leaderboard/blob/af0e3207741054b44e7c87688a40a815ecf446df/README.md","split":"publisher_private_dataset","track":"honesty_evidence","uncertainty_note":"No inferential interval reconstructed from aggregate source values.","unit":"percent","value":88.0},{"aggregation_blocker":"Exact configuration and trial-level evidence unavailable in this snapshot.","cohort":"vectara:af0e3207741054b44e7c87688a40a815ecf446df","confidence_interval":null,"configuration":{"identity":"Source label only; provider, revision and effort not pinned by this table."},"configuration_id":"vectara:af0e3207741054b44e7c87688a40a815ecf446df:anthropic/claude-opus-4-7","definition":"Source-reported hallucination rate on document summarization.","denominator":null,"direction":"lower","evaluation_date":null,"evidence_class":"benchmark_publisher_reported","lab":"Anthropic","metric":"hallucination_rate","model_label":"anthropic/claude-opus-4-7","numerator":null,"overall_score":null,"pillar":"evidence_support","profile_id":"hm-7f094de9380bdcc9bcd2","rank":78,"rank_meaning":"Descriptive native-metric order; not a significance or overall honesty rank.","source":"vectara","source_sha256":"525064e64eac0f096de3528b3516032486a745d141b352b1ee12925589d63616","source_updated":"September 22, 2026","source_url":"https://github.com/vectara/hallucination-leaderboard/blob/af0e3207741054b44e7c87688a40a815ecf446df/README.md","split":"publisher_private_dataset","track":"honesty_evidence","uncertainty_note":"No inferential interval reconstructed from aggregate source values.","unit":"percent","value":12.0},{"aggregation_blocker":"Exact configuration and trial-level evidence unavailable in this snapshot.","cohort":"vectara:af0e3207741054b44e7c87688a40a815ecf446df","confidence_interval":null,"configuration":{"identity":"Source label only; provider, revision and effort not pinned by this table."},"configuration_id":"vectara:af0e3207741054b44e7c87688a40a815ecf446df:anthropic/claude-opus-4-7","definition":"Source-reported average summary length, descriptive only.","denominator":null,"direction":"context","evaluation_date":null,"evidence_class":"benchmark_publisher_reported","lab":"Anthropic","metric":"summary_length","model_label":"anthropic/claude-opus-4-7","numerator":null,"overall_score":null,"pillar":"context","profile_id":"hm-7f094de9380bdcc9bcd2","rank":null,"rank_meaning":"Descriptive native-metric order; not a significance or overall honesty rank.","source":"vectara","source_sha256":"525064e64eac0f096de3528b3516032486a745d141b352b1ee12925589d63616","source_updated":"September 22, 2026","source_url":"https://github.com/vectara/hallucination-leaderboard/blob/af0e3207741054b44e7c87688a40a815ecf446df/README.md","split":"publisher_private_dataset","track":"honesty_evidence","uncertainty_note":"No inferential interval reconstructed from aggregate source values.","unit":"words","value":149.1}],"overall_alignment_score":null,"overall_honesty_score":null,"priority_gaps":["belief_revision","citation_integrity","factual_accuracy","pressure_resistance","uncertainty"],"requirements":[{"detail":"The standard is a draft; no pass thresholds or award authority have been validated.","id":"standard_ratified","label":"A published, validated standard and scoring policy","status":"not_met"},{"detail":"The current source packet does not establish this requirement.","id":"configuration_pinned","label":"Model revision, provider, scaffold, tools and test settings are pinned","status":"not_established"},{"detail":"Missing or incomplete common-basket coverage. Some observations cover: evidence_support.","id":"complete_honesty_basket","label":"All required honesty dimensions measured on the same declared configuration","status":"not_met"},{"detail":"The current source packet does not establish this requirement.","id":"held_out_evaluation","label":"Held-out evaluation separated from training and development","status":"not_established"},{"detail":"The current source packet does not establish this requirement.","id":"usefulness_and_evasion","label":"Useful answering, abstention and evasion measured together","status":"not_established"},{"detail":"The current source packet does not establish this requirement.","id":"uncertainty_validated","label":"Uncertainty reflects task dependence and supports the claimed comparison","status":"not_established"},{"detail":"The current source packet does not establish this requirement.","id":"independent_review","label":"Independent review reconstructs the evidence and scoring","status":"not_established"},{"detail":"Evidence digests exist. Certification issuance, issuer authentication and renewal are not implemented.","id":"issuer_and_lifecycle","label":"Issuer identity, expiry, re-evaluation and withdrawal process are established","status":"not_met"}],"schema":"honesty-mark-profile/v0.1","scope":"Native source/configuration results only. This profile is not an awarded Honesty Mark.","source":"vectara","sources":[{"comparison_caution":"Document summarization judged by HHEM-2.3 on a private dataset. Hallucination and consistency are complements. Native table lacks trial-level uncertainty; answer rate is essential context.","id":"vectara","import_status":"imported","metrics":["hallucination rate","factual consistency","answer rate","summary length"],"name":"Vectara Hallucination Leaderboard","organization":"Vectara","pillars":["evidence_support"],"reviewed_on":"2026-10-11","url":"https://github.com/vectara/hallucination-leaderboard"}],"standard_sha256":"0cec00d16bbb6e2a02a28e43e43394e3eb309523c2ed697913154c4a2e6e6f6c","standard_version":"honesty-mark-standard/v0.1"}