{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WPQCAMLRMWFQBY2OPGI2FAHDCA","short_pith_number":"pith:WPQCAMLR","canonical_record":{"source":{"id":"2506.04516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T23:41:31Z","cross_cats_sorted":[],"title_canon_sha256":"a7b64477a35680a3476f5a413ac33dcad769940db47b0d47993234e4052ca15f","abstract_canon_sha256":"2a475261adb60bbc4b76f5b44de5451f494ff2b9ea3b074764de94bf2a5400df"},"schema_version":"1.0"},"canonical_sha256":"b3e0203171658b00e34e7991a280e310140cbd9e57ff4972f179d82ebb79aae6","source":{"kind":"arxiv","id":"2506.04516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04516","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04516v1","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04516","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"WPQCAMLRMWFQ","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"WPQCAMLRMWFQBY2O","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"WPQCAMLR","created_at":"2026-07-05T11:16:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WPQCAMLRMWFQBY2OPGI2FAHDCA","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T23:41:31Z","cross_cats_sorted":[],"title_canon_sha256":"a7b64477a35680a3476f5a413ac33dcad769940db47b0d47993234e4052ca15f","abstract_canon_sha256":"2a475261adb60bbc4b76f5b44de5451f494ff2b9ea3b074764de94bf2a5400df"},"schema_version":"1.0"},"canonical_sha256":"b3e0203171658b00e34e7991a280e310140cbd9e57ff4972f179d82ebb79aae6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:15.806655Z","signature_b64":"+LwLOUL+mS/aIJZGqDg/7KgOaJ7aF03C85CO2aasXfal3Vhpt6BhBUi06FsMEf0rCz6NqCEv7Gjmsvl3AMRoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3e0203171658b00e34e7991a280e310140cbd9e57ff4972f179d82ebb79aae6","last_reissued_at":"2026-07-05T11:16:15.806173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:15.806173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04516","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":"2026-07-05T11:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dRee6l3+kgry4r/msRxvL5pNFHj7ohqVFB5rdi+50G6AYY1cw7+Je65eYxMiK+U8RvdY6zcIMot0DYny590WBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:03:25.557381Z"},"content_sha256":"4f83237ecccb8942d348c67601aadef55b36c3dc1178a4ec6f42e886a9381607","schema_version":"1.0","event_id":"sha256:4f83237ecccb8942d348c67601aadef55b36c3dc1178a4ec6f42e886a9381607"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WPQCAMLRMWFQBY2OPGI2FAHDCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DRE: An Effective Dual-Refined Method for Integrating Small and Large Language Models in Open-Domain Dialogue Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohao Yang, Chenghua Lin, Chen Tang, Haoteng Tang, Kun Zhao, Liang Zhan, Siyuan Dai","submitted_at":"2025-06-04T23:41:31Z","abstract_excerpt":"Large Language Models (LLMs) excel at many tasks but struggle with ambiguous scenarios where multiple valid responses exist, often yielding unreliable results. Conversely, Small Language Models (SLMs) demonstrate robustness in such scenarios but are susceptible to misleading or adversarial inputs. We observed that LLMs handle negative examples effectively, while SLMs excel with positive examples. To leverage their complementary strengths, we introduce SLIDE (Small and Large Integrated for Dialogue Evaluation), a method integrating SLMs and LLMs via adaptive weighting. Building on SLIDE, we fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04516","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/2506.04516/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":"2026-07-05T11:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dX/MtI3GO2hm+Iu5uSdO4Q4JQOCO8fim/n3glwo/kePBDyFhAbx1hmEVBq6fxEHUG2nXT+diTOLDhkxIkuRACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:03:25.557763Z"},"content_sha256":"17ac2d1f3b694e2b8849f1c3b6721f2a58b99549d7f66233af7507de27ce7a43","schema_version":"1.0","event_id":"sha256:17ac2d1f3b694e2b8849f1c3b6721f2a58b99549d7f66233af7507de27ce7a43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WPQCAMLRMWFQBY2OPGI2FAHDCA/bundle.json","state_url":"https://pith.science/pith/WPQCAMLRMWFQBY2OPGI2FAHDCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WPQCAMLRMWFQBY2OPGI2FAHDCA/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":"2026-07-09T02:03:25Z","links":{"resolver":"https://pith.science/pith/WPQCAMLRMWFQBY2OPGI2FAHDCA","bundle":"https://pith.science/pith/WPQCAMLRMWFQBY2OPGI2FAHDCA/bundle.json","state":"https://pith.science/pith/WPQCAMLRMWFQBY2OPGI2FAHDCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WPQCAMLRMWFQBY2OPGI2FAHDCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WPQCAMLRMWFQBY2OPGI2FAHDCA","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":"2a475261adb60bbc4b76f5b44de5451f494ff2b9ea3b074764de94bf2a5400df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T23:41:31Z","title_canon_sha256":"a7b64477a35680a3476f5a413ac33dcad769940db47b0d47993234e4052ca15f"},"schema_version":"1.0","source":{"id":"2506.04516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04516","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04516v1","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04516","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"WPQCAMLRMWFQ","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"WPQCAMLRMWFQBY2O","created_at":"2026-07-05T11:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"WPQCAMLR","created_at":"2026-07-05T11:16:15Z"}],"graph_snapshots":[{"event_id":"sha256:17ac2d1f3b694e2b8849f1c3b6721f2a58b99549d7f66233af7507de27ce7a43","target":"graph","created_at":"2026-07-05T11:16:15Z","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/2506.04516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) excel at many tasks but struggle with ambiguous scenarios where multiple valid responses exist, often yielding unreliable results. Conversely, Small Language Models (SLMs) demonstrate robustness in such scenarios but are susceptible to misleading or adversarial inputs. We observed that LLMs handle negative examples effectively, while SLMs excel with positive examples. To leverage their complementary strengths, we introduce SLIDE (Small and Large Integrated for Dialogue Evaluation), a method integrating SLMs and LLMs via adaptive weighting. Building on SLIDE, we fur","authors_text":"Bohao Yang, Chenghua Lin, Chen Tang, Haoteng Tang, Kun Zhao, Liang Zhan, Siyuan Dai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T23:41:31Z","title":"DRE: An Effective Dual-Refined Method for Integrating Small and Large Language Models in Open-Domain Dialogue Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04516","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":"sha256:4f83237ecccb8942d348c67601aadef55b36c3dc1178a4ec6f42e886a9381607","target":"record","created_at":"2026-07-05T11:16:15Z","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":"2a475261adb60bbc4b76f5b44de5451f494ff2b9ea3b074764de94bf2a5400df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T23:41:31Z","title_canon_sha256":"a7b64477a35680a3476f5a413ac33dcad769940db47b0d47993234e4052ca15f"},"schema_version":"1.0","source":{"id":"2506.04516","kind":"arxiv","version":1}},"canonical_sha256":"b3e0203171658b00e34e7991a280e310140cbd9e57ff4972f179d82ebb79aae6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3e0203171658b00e34e7991a280e310140cbd9e57ff4972f179d82ebb79aae6","first_computed_at":"2026-07-05T11:16:15.806173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:15.806173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+LwLOUL+mS/aIJZGqDg/7KgOaJ7aF03C85CO2aasXfal3Vhpt6BhBUi06FsMEf0rCz6NqCEv7Gjmsvl3AMRoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:15.806655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f83237ecccb8942d348c67601aadef55b36c3dc1178a4ec6f42e886a9381607","sha256:17ac2d1f3b694e2b8849f1c3b6721f2a58b99549d7f66233af7507de27ce7a43"],"state_sha256":"3ea5cdebccd6645736d82faf23fb6fc7eba53fe814d75a31e41631e89c1bb8e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPzSIhmnaujOrRnO+lwOuBUil0J9IAWSe6rKeH/J7zTlcMimV9GS2qTAN3bkrrNfS1AbueUQ/rLpBFnHFVyDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:03:25.560202Z","bundle_sha256":"d5661f08f048d0234dfbce9df99aff5dbddf51eea4ed7513df662bbe05c0d9cf"}}