{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5NIAEC456C63SLK2QZ5L5FZM52","short_pith_number":"pith:5NIAEC45","canonical_record":{"source":{"id":"2501.12698","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T08:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"5531ecd1ff6b04c882880bd9772d58f8699902428352423e67b03fcfb24ec1bf","abstract_canon_sha256":"81239b8c4c2db50a80624d3e103301a0c3e88281a0eba27c1e5cde3bfa69d209"},"schema_version":"1.0"},"canonical_sha256":"eb50020b9df0bdb92d5a867abe972cee80b965daf73958ea0bb7ffb718683fae","source":{"kind":"arxiv","id":"2501.12698","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12698","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12698v2","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12698","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"5NIAEC456C63","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"5NIAEC456C63SLK2","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"5NIAEC45","created_at":"2026-07-05T10:05:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5NIAEC456C63SLK2QZ5L5FZM52","target":"record","payload":{"canonical_record":{"source":{"id":"2501.12698","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T08:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"5531ecd1ff6b04c882880bd9772d58f8699902428352423e67b03fcfb24ec1bf","abstract_canon_sha256":"81239b8c4c2db50a80624d3e103301a0c3e88281a0eba27c1e5cde3bfa69d209"},"schema_version":"1.0"},"canonical_sha256":"eb50020b9df0bdb92d5a867abe972cee80b965daf73958ea0bb7ffb718683fae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:17.018160Z","signature_b64":"mrSkvv0QB27IRAjxox/Y2s15aJulZnkbTyn5tIjNOFGjOojhqt5YfXYwDy4NJZZursmW4EBlqbBY5KlQQKKeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb50020b9df0bdb92d5a867abe972cee80b965daf73958ea0bb7ffb718683fae","last_reissued_at":"2026-07-05T10:05:17.017705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:17.017705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.12698","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FP2PKPlC7Oz1BEJv+X6S6Xt6SORY8eo8sHMeux8RHx5BTy6MZq4DbM4hX5yuR+xLddOtfrIJ08xJBFRygt5HDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:44:15.605295Z"},"content_sha256":"424e559099b9133871ba21b7d613e6c53f305b02ee9f275309ab03935f447519","schema_version":"1.0","event_id":"sha256:424e559099b9133871ba21b7d613e6c53f305b02ee9f275309ab03935f447519"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5NIAEC456C63SLK2QZ5L5FZM52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Dialogue Systems by AI Feedback for Improving Overall Dialogue Impression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Canasai Kruengkrai, Hiroaki Sugiyama, Kai Yoshida, Koichiro Yoshino, Masahiro Mizukami, Seiya Kawano","submitted_at":"2025-01-22T08:14:51Z","abstract_excerpt":"To improve user engagement during conversations with dialogue systems, we must improve individual dialogue responses and dialogue impressions such as consistency, personality, and empathy throughout the entire dialogue. While such dialogue systems have been developing rapidly with the help of large language models (LLMs), reinforcement learning from AI feedback (RLAIF) has attracted attention to align LLM-based dialogue models for such dialogue impressions. In RLAIF, a reward model based on another LLM is used to create a training signal for an LLM-based dialogue model using zero-shot/few-shot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12698","kind":"arxiv","version":2},"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/2501.12698/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":"2026-07-05T10:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bRr81IIa0OgzZ+2tng9TQJQ9g1gFzmsqgP1v/xfn0txhyPSoQfL5dM86Y83tiqJHhGRsJ9GH5IRJWg3MUpz+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:44:15.606202Z"},"content_sha256":"d002015cc8645d66cf87eca0af6dfdfcf11a68d45dad7691d9c23d0efbb0c626","schema_version":"1.0","event_id":"sha256:d002015cc8645d66cf87eca0af6dfdfcf11a68d45dad7691d9c23d0efbb0c626"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NIAEC456C63SLK2QZ5L5FZM52/bundle.json","state_url":"https://pith.science/pith/5NIAEC456C63SLK2QZ5L5FZM52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NIAEC456C63SLK2QZ5L5FZM52/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":"2026-08-04T09:44:15Z","links":{"resolver":"https://pith.science/pith/5NIAEC456C63SLK2QZ5L5FZM52","bundle":"https://pith.science/pith/5NIAEC456C63SLK2QZ5L5FZM52/bundle.json","state":"https://pith.science/pith/5NIAEC456C63SLK2QZ5L5FZM52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NIAEC456C63SLK2QZ5L5FZM52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5NIAEC456C63SLK2QZ5L5FZM52","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":"81239b8c4c2db50a80624d3e103301a0c3e88281a0eba27c1e5cde3bfa69d209","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T08:14:51Z","title_canon_sha256":"5531ecd1ff6b04c882880bd9772d58f8699902428352423e67b03fcfb24ec1bf"},"schema_version":"1.0","source":{"id":"2501.12698","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12698","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12698v2","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12698","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"5NIAEC456C63","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"5NIAEC456C63SLK2","created_at":"2026-07-05T10:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"5NIAEC45","created_at":"2026-07-05T10:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:d002015cc8645d66cf87eca0af6dfdfcf11a68d45dad7691d9c23d0efbb0c626","target":"graph","created_at":"2026-07-05T10:05:17Z","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/2501.12698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To improve user engagement during conversations with dialogue systems, we must improve individual dialogue responses and dialogue impressions such as consistency, personality, and empathy throughout the entire dialogue. While such dialogue systems have been developing rapidly with the help of large language models (LLMs), reinforcement learning from AI feedback (RLAIF) has attracted attention to align LLM-based dialogue models for such dialogue impressions. In RLAIF, a reward model based on another LLM is used to create a training signal for an LLM-based dialogue model using zero-shot/few-shot","authors_text":"Canasai Kruengkrai, Hiroaki Sugiyama, Kai Yoshida, Koichiro Yoshino, Masahiro Mizukami, Seiya Kawano","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T08:14:51Z","title":"Training Dialogue Systems by AI Feedback for Improving Overall Dialogue Impression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12698","kind":"arxiv","version":2},"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":"sha256:424e559099b9133871ba21b7d613e6c53f305b02ee9f275309ab03935f447519","target":"record","created_at":"2026-07-05T10:05:17Z","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":"81239b8c4c2db50a80624d3e103301a0c3e88281a0eba27c1e5cde3bfa69d209","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T08:14:51Z","title_canon_sha256":"5531ecd1ff6b04c882880bd9772d58f8699902428352423e67b03fcfb24ec1bf"},"schema_version":"1.0","source":{"id":"2501.12698","kind":"arxiv","version":2}},"canonical_sha256":"eb50020b9df0bdb92d5a867abe972cee80b965daf73958ea0bb7ffb718683fae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb50020b9df0bdb92d5a867abe972cee80b965daf73958ea0bb7ffb718683fae","first_computed_at":"2026-07-05T10:05:17.017705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:17.017705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mrSkvv0QB27IRAjxox/Y2s15aJulZnkbTyn5tIjNOFGjOojhqt5YfXYwDy4NJZZursmW4EBlqbBY5KlQQKKeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:17.018160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12698","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:424e559099b9133871ba21b7d613e6c53f305b02ee9f275309ab03935f447519","sha256:d002015cc8645d66cf87eca0af6dfdfcf11a68d45dad7691d9c23d0efbb0c626"],"state_sha256":"928fa50333d4eee85d09c2f84a6f6a6ad2e26bc913685c8b09eda3381cc149cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R//T/QNukaZkmTzB4cyAFqZWqUa0bn8qLhuIcImx/Hs39+BVGg5VTGF3DLAmMwUG3fZrRq1oRLcAgoteHL58Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:44:15.611763Z","bundle_sha256":"e650dea520b5cd3bb2c8132b860a78baab74a6f6fcdbb07979cc35c70d3282fc"}}