{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DH4U4OCLU767BLBYKR3WCNUYCX","short_pith_number":"pith:DH4U4OCL","canonical_record":{"source":{"id":"2301.13372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T02:31:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e318672c04098842ed7f6d6de59653c69a6a6f0ef92712a3ddd6012337497344","abstract_canon_sha256":"d30dd322ba4ba97e83a819cc02df0017a5340973337f5e4b0cf6dcfc9e48d91d"},"schema_version":"1.0"},"canonical_sha256":"19f94e384ba7fdf0ac38547761369815ee6995889489d0773a2eada76cd0f1e4","source":{"kind":"arxiv","id":"2301.13372","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13372","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13372v1","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13372","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"pith_short_12","alias_value":"DH4U4OCLU767","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"pith_short_16","alias_value":"DH4U4OCLU767BLBY","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"pith_short_8","alias_value":"DH4U4OCL","created_at":"2026-07-05T05:37:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DH4U4OCLU767BLBYKR3WCNUYCX","target":"record","payload":{"canonical_record":{"source":{"id":"2301.13372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T02:31:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e318672c04098842ed7f6d6de59653c69a6a6f0ef92712a3ddd6012337497344","abstract_canon_sha256":"d30dd322ba4ba97e83a819cc02df0017a5340973337f5e4b0cf6dcfc9e48d91d"},"schema_version":"1.0"},"canonical_sha256":"19f94e384ba7fdf0ac38547761369815ee6995889489d0773a2eada76cd0f1e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:14.019190Z","signature_b64":"FI97xxA8jKpu4pyDFdsK8+MQOo8nL1qw2T4kYV0ISEfHlJzf6yu6M9ojvatDs5NWpKgkkAqtsbCzygmfzkHABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f94e384ba7fdf0ac38547761369815ee6995889489d0773a2eada76cd0f1e4","last_reissued_at":"2026-07-05T05:37:14.018751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:14.018751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.13372","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":"2026-07-05T05:37:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pQrO3/lKLpavBVVj5i57knobxirpsoLKNqgbg4XUpTdjJVBAWC97wgoctH9bB1tahqU23LH+Zq+LxrJA9EaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:14:43.220277Z"},"content_sha256":"e37e85bc54b576d3afaf254ac9edc5d76811a25d38ab6a3e18a2eee14e4f0ec1","schema_version":"1.0","event_id":"sha256:e37e85bc54b576d3afaf254ac9edc5d76811a25d38ab6a3e18a2eee14e4f0ec1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DH4U4OCLU767BLBYKR3WCNUYCX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Open-Domain Dialogue Evaluation with a Causal Inference Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cat P. Le, Luke Dai, Marilyn Walker, Michael Johnston, Reza Ghanadan, Yang Liu","submitted_at":"2023-01-31T02:31:42Z","abstract_excerpt":"Effective evaluation methods remain a significant challenge for research on open-domain conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but users often do not provide ratings when asked, and those they give can be highly subjective. Post-hoc ratings by experts are an alternative, but these can be both expensive and complex to collect. Here, we explore the creation of automated methods for predicting both expert and user ratings of open-domain dialogues. We compare four different approaches. First, we train a baseline model using an end-to-end transfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13372","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/2301.13372/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":"2026-07-05T05:37:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4k13m4R4J8qeBJJxx/HNUI0u4GkVNh+R+RWwQl5pxYOpauIT2r3RuVlurVTMZyTJsibeduoZJ8NuuE30PvFLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:14:43.220667Z"},"content_sha256":"c59a12c2224bf4354c0cddcf668c8a170c3350c68b0277e80939e4c13f9e3022","schema_version":"1.0","event_id":"sha256:c59a12c2224bf4354c0cddcf668c8a170c3350c68b0277e80939e4c13f9e3022"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DH4U4OCLU767BLBYKR3WCNUYCX/bundle.json","state_url":"https://pith.science/pith/DH4U4OCLU767BLBYKR3WCNUYCX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DH4U4OCLU767BLBYKR3WCNUYCX/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":"2026-07-07T04:14:43Z","links":{"resolver":"https://pith.science/pith/DH4U4OCLU767BLBYKR3WCNUYCX","bundle":"https://pith.science/pith/DH4U4OCLU767BLBYKR3WCNUYCX/bundle.json","state":"https://pith.science/pith/DH4U4OCLU767BLBYKR3WCNUYCX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DH4U4OCLU767BLBYKR3WCNUYCX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DH4U4OCLU767BLBYKR3WCNUYCX","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":"d30dd322ba4ba97e83a819cc02df0017a5340973337f5e4b0cf6dcfc9e48d91d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T02:31:42Z","title_canon_sha256":"e318672c04098842ed7f6d6de59653c69a6a6f0ef92712a3ddd6012337497344"},"schema_version":"1.0","source":{"id":"2301.13372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13372","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13372v1","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13372","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"pith_short_12","alias_value":"DH4U4OCLU767","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"pith_short_16","alias_value":"DH4U4OCLU767BLBY","created_at":"2026-07-05T05:37:14Z"},{"alias_kind":"pith_short_8","alias_value":"DH4U4OCL","created_at":"2026-07-05T05:37:14Z"}],"graph_snapshots":[{"event_id":"sha256:c59a12c2224bf4354c0cddcf668c8a170c3350c68b0277e80939e4c13f9e3022","target":"graph","created_at":"2026-07-05T05:37:14Z","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/2301.13372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective evaluation methods remain a significant challenge for research on open-domain conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but users often do not provide ratings when asked, and those they give can be highly subjective. Post-hoc ratings by experts are an alternative, but these can be both expensive and complex to collect. Here, we explore the creation of automated methods for predicting both expert and user ratings of open-domain dialogues. We compare four different approaches. First, we train a baseline model using an end-to-end transfor","authors_text":"Cat P. Le, Luke Dai, Marilyn Walker, Michael Johnston, Reza Ghanadan, Yang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T02:31:42Z","title":"Improving Open-Domain Dialogue Evaluation with a Causal Inference Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13372","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:e37e85bc54b576d3afaf254ac9edc5d76811a25d38ab6a3e18a2eee14e4f0ec1","target":"record","created_at":"2026-07-05T05:37:14Z","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":"d30dd322ba4ba97e83a819cc02df0017a5340973337f5e4b0cf6dcfc9e48d91d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T02:31:42Z","title_canon_sha256":"e318672c04098842ed7f6d6de59653c69a6a6f0ef92712a3ddd6012337497344"},"schema_version":"1.0","source":{"id":"2301.13372","kind":"arxiv","version":1}},"canonical_sha256":"19f94e384ba7fdf0ac38547761369815ee6995889489d0773a2eada76cd0f1e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19f94e384ba7fdf0ac38547761369815ee6995889489d0773a2eada76cd0f1e4","first_computed_at":"2026-07-05T05:37:14.018751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:37:14.018751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FI97xxA8jKpu4pyDFdsK8+MQOo8nL1qw2T4kYV0ISEfHlJzf6yu6M9ojvatDs5NWpKgkkAqtsbCzygmfzkHABw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:37:14.019190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e37e85bc54b576d3afaf254ac9edc5d76811a25d38ab6a3e18a2eee14e4f0ec1","sha256:c59a12c2224bf4354c0cddcf668c8a170c3350c68b0277e80939e4c13f9e3022"],"state_sha256":"58aed9c94032aa780817bd8b5fdbf835595b666791c8ce2ba8c0ea519a870039"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcVfvHc2eyaq8HPDbdH4HOp8zdwKLLZfmkbTk7baTlnzH112g//LSCUYVNF0+9/BMgcXCUg+q0Q1vsew0qf/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:14:43.222574Z","bundle_sha256":"d9f8913bd7e2256b7bccb732794b382d8fe122a9c07156eaffb61991491bd910"}}