{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:I5DHJD46URSO4R7UM7DXF2PJKV","short_pith_number":"pith:I5DHJD46","canonical_record":{"source":{"id":"2310.10735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T18:05:54Z","cross_cats_sorted":[],"title_canon_sha256":"fbea2b97969544de6d796d32eb97a6484ceb26e1f76b5e5fbb63cd6980c56e4a","abstract_canon_sha256":"6ef3a478778f2904657a43e3e2400caa6a88d1bed79e83c1440a59601798dd00"},"schema_version":"1.0"},"canonical_sha256":"4746748f9ea464ee47f467c772e9e95564f09f5accf2b40f9cce6bc2b140cf12","source":{"kind":"arxiv","id":"2310.10735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10735","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10735v1","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10735","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"pith_short_12","alias_value":"I5DHJD46URSO","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"pith_short_16","alias_value":"I5DHJD46URSO4R7U","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"pith_short_8","alias_value":"I5DHJD46","created_at":"2026-07-05T07:01:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:I5DHJD46URSO4R7UM7DXF2PJKV","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T18:05:54Z","cross_cats_sorted":[],"title_canon_sha256":"fbea2b97969544de6d796d32eb97a6484ceb26e1f76b5e5fbb63cd6980c56e4a","abstract_canon_sha256":"6ef3a478778f2904657a43e3e2400caa6a88d1bed79e83c1440a59601798dd00"},"schema_version":"1.0"},"canonical_sha256":"4746748f9ea464ee47f467c772e9e95564f09f5accf2b40f9cce6bc2b140cf12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:27.152218Z","signature_b64":"bwyYFfZ5y8zdd+ytGLFXbMlwvzdzab5Tl+iQDelwn3KhWVChkHUgHXZt98SFlGzDl/hOBRw+FnU3lR76gB/3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4746748f9ea464ee47f467c772e9e95564f09f5accf2b40f9cce6bc2b140cf12","last_reissued_at":"2026-07-05T07:01:27.151733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:27.151733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10735","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":"2026-07-05T07:01:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxbIlYh61a0YoDqessc1lvdL4zmcyBO9M+5MnLnvrEA1jo/dpc7cWXsJQ/cJH4nDFgmwixkYBJNvbxTP7AVcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:29:12.544080Z"},"content_sha256":"31a114f89bef1987c9dc63338fe8706dff5d02be41ff2d6d84a63628db9b71ac","schema_version":"1.0","event_id":"sha256:31a114f89bef1987c9dc63338fe8706dff5d02be41ff2d6d84a63628db9b71ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:I5DHJD46URSO4R7UM7DXF2PJKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ryan Shea, Zhou Yu","submitted_at":"2023-10-16T18:05:54Z","abstract_excerpt":"Maintaining a consistent persona is a key quality for any open domain dialogue system. Current state-of-the-art systems do this by training agents with supervised learning or online reinforcement learning (RL). However, systems trained with supervised learning often lack consistency as they are never punished for uttering contradictions. Additional training with RL can alleviate some of these issues, however the training process is expensive. Instead, we propose an offline RL framework to improve the persona consistency of dialogue systems. Our framework allows us to combine the advantages of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10735","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/2310.10735/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":"2026-07-05T07:01:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uCaK35u8OExi2dyJVRMC/uEFHUpvoanofldySL2+0wchF/NjSq9/A8uqP8dIYV66enfh1/GjXg1mZxbuviY7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:29:12.544582Z"},"content_sha256":"59e701f5d1d4664daa8227d077c9c36c2be53daa45deafc6c8be6d32cb1158f4","schema_version":"1.0","event_id":"sha256:59e701f5d1d4664daa8227d077c9c36c2be53daa45deafc6c8be6d32cb1158f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5DHJD46URSO4R7UM7DXF2PJKV/bundle.json","state_url":"https://pith.science/pith/I5DHJD46URSO4R7UM7DXF2PJKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5DHJD46URSO4R7UM7DXF2PJKV/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":"2026-08-16T21:29:12Z","links":{"resolver":"https://pith.science/pith/I5DHJD46URSO4R7UM7DXF2PJKV","bundle":"https://pith.science/pith/I5DHJD46URSO4R7UM7DXF2PJKV/bundle.json","state":"https://pith.science/pith/I5DHJD46URSO4R7UM7DXF2PJKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5DHJD46URSO4R7UM7DXF2PJKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I5DHJD46URSO4R7UM7DXF2PJKV","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":"6ef3a478778f2904657a43e3e2400caa6a88d1bed79e83c1440a59601798dd00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T18:05:54Z","title_canon_sha256":"fbea2b97969544de6d796d32eb97a6484ceb26e1f76b5e5fbb63cd6980c56e4a"},"schema_version":"1.0","source":{"id":"2310.10735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10735","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10735v1","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10735","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"pith_short_12","alias_value":"I5DHJD46URSO","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"pith_short_16","alias_value":"I5DHJD46URSO4R7U","created_at":"2026-07-05T07:01:27Z"},{"alias_kind":"pith_short_8","alias_value":"I5DHJD46","created_at":"2026-07-05T07:01:27Z"}],"graph_snapshots":[{"event_id":"sha256:59e701f5d1d4664daa8227d077c9c36c2be53daa45deafc6c8be6d32cb1158f4","target":"graph","created_at":"2026-07-05T07:01:27Z","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/2310.10735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Maintaining a consistent persona is a key quality for any open domain dialogue system. Current state-of-the-art systems do this by training agents with supervised learning or online reinforcement learning (RL). However, systems trained with supervised learning often lack consistency as they are never punished for uttering contradictions. Additional training with RL can alleviate some of these issues, however the training process is expensive. Instead, we propose an offline RL framework to improve the persona consistency of dialogue systems. Our framework allows us to combine the advantages of ","authors_text":"Ryan Shea, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T18:05:54Z","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10735","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":"sha256:31a114f89bef1987c9dc63338fe8706dff5d02be41ff2d6d84a63628db9b71ac","target":"record","created_at":"2026-07-05T07:01:27Z","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":"6ef3a478778f2904657a43e3e2400caa6a88d1bed79e83c1440a59601798dd00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T18:05:54Z","title_canon_sha256":"fbea2b97969544de6d796d32eb97a6484ceb26e1f76b5e5fbb63cd6980c56e4a"},"schema_version":"1.0","source":{"id":"2310.10735","kind":"arxiv","version":1}},"canonical_sha256":"4746748f9ea464ee47f467c772e9e95564f09f5accf2b40f9cce6bc2b140cf12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4746748f9ea464ee47f467c772e9e95564f09f5accf2b40f9cce6bc2b140cf12","first_computed_at":"2026-07-05T07:01:27.151733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:27.151733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bwyYFfZ5y8zdd+ytGLFXbMlwvzdzab5Tl+iQDelwn3KhWVChkHUgHXZt98SFlGzDl/hOBRw+FnU3lR76gB/3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:27.152218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31a114f89bef1987c9dc63338fe8706dff5d02be41ff2d6d84a63628db9b71ac","sha256:59e701f5d1d4664daa8227d077c9c36c2be53daa45deafc6c8be6d32cb1158f4"],"state_sha256":"7adea628fb29dea2638439677dcacd03faab5aa7d27382072a9b9c0cb57280e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Q/uyr5QRrQCiXcb4XsyA1TlUbN2+bPhmtZz+Aw4PphViBlKK5UkESDoVBdIk0Cy9Z5fxOQfhS/P13s5CAs+Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T21:29:12.549496Z","bundle_sha256":"710b32ced5679d457274bbadc0db93a5758974c811c586dc6ca3838ca5b7517f"}}