{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LJUBMD6ATN5KV66DOQX2YADK5A","short_pith_number":"pith:LJUBMD6A","canonical_record":{"source":{"id":"2010.05848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T16:53:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0f2c0076d0e3ee5ae06d13f982c20818b73bf597dd80b1064ba75ee173d233a","abstract_canon_sha256":"4ffd5c45aeb3a57f72f7dc2cdd4ba03d0360c9f57fe80f1fec5514bf5716b931"},"schema_version":"1.0"},"canonical_sha256":"5a68160fc09b7aaafbc3742fac006ae811fa6e38df11397b5f3ecfd9a29c1ef2","source":{"kind":"arxiv","id":"2010.05848","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05848","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05848v1","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05848","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"LJUBMD6ATN5K","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"LJUBMD6ATN5KV66D","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"LJUBMD6A","created_at":"2026-07-05T01:42:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LJUBMD6ATN5KV66DOQX2YADK5A","target":"record","payload":{"canonical_record":{"source":{"id":"2010.05848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T16:53:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0f2c0076d0e3ee5ae06d13f982c20818b73bf597dd80b1064ba75ee173d233a","abstract_canon_sha256":"4ffd5c45aeb3a57f72f7dc2cdd4ba03d0360c9f57fe80f1fec5514bf5716b931"},"schema_version":"1.0"},"canonical_sha256":"5a68160fc09b7aaafbc3742fac006ae811fa6e38df11397b5f3ecfd9a29c1ef2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:11.049781Z","signature_b64":"Xu2nMfHMEi0iX07mL77OmR+qtUYAZHnySCmy3XwsOaDfsnifJztbkzM/jCM+esSrt4v65eBR/R61Ui8De1YTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a68160fc09b7aaafbc3742fac006ae811fa6e38df11397b5f3ecfd9a29c1ef2","last_reissued_at":"2026-07-05T01:42:11.049366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:11.049366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.05848","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":"2026-07-05T01:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McW23ajiVKXfBnj2mamzPV/DH+TsM8gqlgzey+C02UEacySlVnQGUJpy+IBTzG6BAh0oHMI43AS0X3XGKUhICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T08:44:09.697482Z"},"content_sha256":"01482155f8d183c7bc18a1a6a78024b01920c91f81059168d46586809058c859","schema_version":"1.0","event_id":"sha256:01482155f8d183c7bc18a1a6a78024b01920c91f81059168d46586809058c859"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LJUBMD6ATN5KV66DOQX2YADK5A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human-centric Dialog Training via Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Agata Lapedriza, Asma Ghandeharioun, Craig Ferguson, Judy Hanwen Shen, Natasha Jaques, Noah Jones, Rosalind Picard, Shixiang Shane Gu","submitted_at":"2020-10-12T16:53:00Z","abstract_excerpt":"How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time, open-ended conversations, which we then use to train and improve the models using offline reinforcement learning (RL). We identify implicit conversational cues including language similarity, elicitation of laughter, sentiment, and more, which indicate positive human feedback, and embed these in multiple reward functions. A well-known challenge is that learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05848","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/2010.05848/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":"2026-07-05T01:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8JveY08jZ1b47xQwCM4mtTmqqA6IsrC0O+1pYm50bhQCUZoksiprNTi5iCWYCTwAfODFVbSLgvzG9MeYs8HuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T08:44:09.698113Z"},"content_sha256":"7a59e3e6209c5937437f5c78c63405928ab4579801ce00553a771be562f5aaba","schema_version":"1.0","event_id":"sha256:7a59e3e6209c5937437f5c78c63405928ab4579801ce00553a771be562f5aaba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJUBMD6ATN5KV66DOQX2YADK5A/bundle.json","state_url":"https://pith.science/pith/LJUBMD6ATN5KV66DOQX2YADK5A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJUBMD6ATN5KV66DOQX2YADK5A/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":"2026-08-23T08:44:09Z","links":{"resolver":"https://pith.science/pith/LJUBMD6ATN5KV66DOQX2YADK5A","bundle":"https://pith.science/pith/LJUBMD6ATN5KV66DOQX2YADK5A/bundle.json","state":"https://pith.science/pith/LJUBMD6ATN5KV66DOQX2YADK5A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJUBMD6ATN5KV66DOQX2YADK5A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LJUBMD6ATN5KV66DOQX2YADK5A","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":"4ffd5c45aeb3a57f72f7dc2cdd4ba03d0360c9f57fe80f1fec5514bf5716b931","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T16:53:00Z","title_canon_sha256":"a0f2c0076d0e3ee5ae06d13f982c20818b73bf597dd80b1064ba75ee173d233a"},"schema_version":"1.0","source":{"id":"2010.05848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05848","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05848v1","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05848","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"LJUBMD6ATN5K","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"LJUBMD6ATN5KV66D","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"LJUBMD6A","created_at":"2026-07-05T01:42:11Z"}],"graph_snapshots":[{"event_id":"sha256:7a59e3e6209c5937437f5c78c63405928ab4579801ce00553a771be562f5aaba","target":"graph","created_at":"2026-07-05T01:42:11Z","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/2010.05848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time, open-ended conversations, which we then use to train and improve the models using offline reinforcement learning (RL). We identify implicit conversational cues including language similarity, elicitation of laughter, sentiment, and more, which indicate positive human feedback, and embed these in multiple reward functions. A well-known challenge is that learning ","authors_text":"Agata Lapedriza, Asma Ghandeharioun, Craig Ferguson, Judy Hanwen Shen, Natasha Jaques, Noah Jones, Rosalind Picard, Shixiang Shane Gu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T16:53:00Z","title":"Human-centric Dialog Training via Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05848","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":"sha256:01482155f8d183c7bc18a1a6a78024b01920c91f81059168d46586809058c859","target":"record","created_at":"2026-07-05T01:42:11Z","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":"4ffd5c45aeb3a57f72f7dc2cdd4ba03d0360c9f57fe80f1fec5514bf5716b931","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T16:53:00Z","title_canon_sha256":"a0f2c0076d0e3ee5ae06d13f982c20818b73bf597dd80b1064ba75ee173d233a"},"schema_version":"1.0","source":{"id":"2010.05848","kind":"arxiv","version":1}},"canonical_sha256":"5a68160fc09b7aaafbc3742fac006ae811fa6e38df11397b5f3ecfd9a29c1ef2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a68160fc09b7aaafbc3742fac006ae811fa6e38df11397b5f3ecfd9a29c1ef2","first_computed_at":"2026-07-05T01:42:11.049366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:11.049366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xu2nMfHMEi0iX07mL77OmR+qtUYAZHnySCmy3XwsOaDfsnifJztbkzM/jCM+esSrt4v65eBR/R61Ui8De1YTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:11.049781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.05848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01482155f8d183c7bc18a1a6a78024b01920c91f81059168d46586809058c859","sha256:7a59e3e6209c5937437f5c78c63405928ab4579801ce00553a771be562f5aaba"],"state_sha256":"b1474348708256080c2c0fcc56beb5b42da257739b93e769f19bf5cfeab26691"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEZBK1IuYwOy7lqmUXFuAD8ILW94kHn+X6Al+6PHf0VJRxFs5dLhbdaExxoxE34gMV4LklvaMXMfaCEKfxs7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T08:44:09.706199Z","bundle_sha256":"3a76d4868073a87ac7ec9634417501c7e0fe5a5aef82cabd0b4d4416b1488a8d"}}