{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HB5AJJODMLK6W6Y5DYP3RA6FGN","short_pith_number":"pith:HB5AJJOD","canonical_record":{"source":{"id":"2605.27914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:41:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad3152153ce880186e2b9b74481faa545c488f2aa6b3df5502534e3b56706711","abstract_canon_sha256":"286afd0aa06e10da7b0a61723d07b582a5354d2856f3800961b59de2854e9f0b"},"schema_version":"1.0"},"canonical_sha256":"387a04a5c362d5eb7b1d1e1fb883c5337727ee50d6a4982bce529bf9d5872038","source":{"kind":"arxiv","id":"2605.27914","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27914","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27914v1","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27914","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"HB5AJJODMLK6","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"HB5AJJODMLK6W6Y5","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"HB5AJJOD","created_at":"2026-05-28T01:04:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HB5AJJODMLK6W6Y5DYP3RA6FGN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:41:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad3152153ce880186e2b9b74481faa545c488f2aa6b3df5502534e3b56706711","abstract_canon_sha256":"286afd0aa06e10da7b0a61723d07b582a5354d2856f3800961b59de2854e9f0b"},"schema_version":"1.0"},"canonical_sha256":"387a04a5c362d5eb7b1d1e1fb883c5337727ee50d6a4982bce529bf9d5872038","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:52.304634Z","signature_b64":"4Sfh9r8S0eWrT9oOVy8I/nVhh+nid1J7tKRcu3VwxMzngxDQGDlOHDq/p1yXA4LEWY4aZNVsT+Om1r0KT8Z6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"387a04a5c362d5eb7b1d1e1fb883c5337727ee50d6a4982bce529bf9d5872038","last_reissued_at":"2026-05-28T01:04:52.304223Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:52.304223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27914","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ed7CrN5BISfiUo4lS5oBr/DwTn+0JbjpUPmE/KjU+gMoAtidlPAfyZ/6yZJToaldoq356lt75JTiiVw5BafBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:42:48.640250Z"},"content_sha256":"5e440d17283b1050edae1d47f1f998ff7dee2d9736bf404ee4585c80bbf834e7","schema_version":"1.0","event_id":"sha256:5e440d17283b1050edae1d47f1f998ff7dee2d9736bf404ee4585c80bbf834e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HB5AJJODMLK6W6Y5DYP3RA6FGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junchen Wan, Lei Wang, Yao Liu, Yuming (Rapheal) Huang","submitted_at":"2026-05-27T03:41:11Z","abstract_excerpt":"Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing the target's training cohort cannot independently verify it. Anchoring validity to a single human-rater consensus does not extend to capabilities where humans themselves disagree.\n  We propose a replication-first paradigm: instead of anchoring on one rater group, we certify the instrument via four orthogonal properties -- reliability across K runs, cross-inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27914","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/2605.27914/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9PpBqRQZpocCrj+YQZlUv3h0KY3/uQNoYZaUQ0c4+SC3ELMT9Mk+5epBfO3+dpYXYO31khpYMufU8fOym1y2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:42:48.640653Z"},"content_sha256":"891e577f7630af618d2b64ca1ba6908f358dd21f2b7aea6c7a3c19321309a370","schema_version":"1.0","event_id":"sha256:891e577f7630af618d2b64ca1ba6908f358dd21f2b7aea6c7a3c19321309a370"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HB5AJJODMLK6W6Y5DYP3RA6FGN/bundle.json","state_url":"https://pith.science/pith/HB5AJJODMLK6W6Y5DYP3RA6FGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HB5AJJODMLK6W6Y5DYP3RA6FGN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T14:42:48Z","links":{"resolver":"https://pith.science/pith/HB5AJJODMLK6W6Y5DYP3RA6FGN","bundle":"https://pith.science/pith/HB5AJJODMLK6W6Y5DYP3RA6FGN/bundle.json","state":"https://pith.science/pith/HB5AJJODMLK6W6Y5DYP3RA6FGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HB5AJJODMLK6W6Y5DYP3RA6FGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HB5AJJODMLK6W6Y5DYP3RA6FGN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"286afd0aa06e10da7b0a61723d07b582a5354d2856f3800961b59de2854e9f0b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:41:11Z","title_canon_sha256":"ad3152153ce880186e2b9b74481faa545c488f2aa6b3df5502534e3b56706711"},"schema_version":"1.0","source":{"id":"2605.27914","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27914","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27914v1","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27914","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"HB5AJJODMLK6","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"HB5AJJODMLK6W6Y5","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"HB5AJJOD","created_at":"2026-05-28T01:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:891e577f7630af618d2b64ca1ba6908f358dd21f2b7aea6c7a3c19321309a370","target":"graph","created_at":"2026-05-28T01:04:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.27914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing the target's training cohort cannot independently verify it. Anchoring validity to a single human-rater consensus does not extend to capabilities where humans themselves disagree.\n  We propose a replication-first paradigm: instead of anchoring on one rater group, we certify the instrument via four orthogonal properties -- reliability across K runs, cross-inst","authors_text":"Junchen Wan, Lei Wang, Yao Liu, Yuming (Rapheal) Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:41:11Z","title":"Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27914","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5e440d17283b1050edae1d47f1f998ff7dee2d9736bf404ee4585c80bbf834e7","target":"record","created_at":"2026-05-28T01:04:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"286afd0aa06e10da7b0a61723d07b582a5354d2856f3800961b59de2854e9f0b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:41:11Z","title_canon_sha256":"ad3152153ce880186e2b9b74481faa545c488f2aa6b3df5502534e3b56706711"},"schema_version":"1.0","source":{"id":"2605.27914","kind":"arxiv","version":1}},"canonical_sha256":"387a04a5c362d5eb7b1d1e1fb883c5337727ee50d6a4982bce529bf9d5872038","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"387a04a5c362d5eb7b1d1e1fb883c5337727ee50d6a4982bce529bf9d5872038","first_computed_at":"2026-05-28T01:04:52.304223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:52.304223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Sfh9r8S0eWrT9oOVy8I/nVhh+nid1J7tKRcu3VwxMzngxDQGDlOHDq/p1yXA4LEWY4aZNVsT+Om1r0KT8Z6Bw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:52.304634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27914","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e440d17283b1050edae1d47f1f998ff7dee2d9736bf404ee4585c80bbf834e7","sha256:891e577f7630af618d2b64ca1ba6908f358dd21f2b7aea6c7a3c19321309a370"],"state_sha256":"2dc3a2b51fb5ffae8c0051f3bd86c8fa5ed597ff930925e2b1523de7d51b33b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3kPJOUycw1R/cBDVposlxsJRpYKQ2c3vpmWNMsrwbd6Ci39dIICYwQEFt9Wun+8vhPa2/Nr8SS1rh6rLdQ3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T14:42:48.642694Z","bundle_sha256":"42084387a848caf03f5ed9caa01335966e924fc24f1d48896f2ea06e3d2d44b8"}}