{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TLKHEJSBST3Q3GUZSTOCO2PZ2X","short_pith_number":"pith:TLKHEJSB","canonical_record":{"source":{"id":"2210.15893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T04:57:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0bda0cd77f553ea069c6b583038861cdb75ffbfc96e7273dbb44183e2f1b1431","abstract_canon_sha256":"d8bf8d146715184fd2f8eec6b94beb693091e2fc7e925ee6299914343a3b28cf"},"schema_version":"1.0"},"canonical_sha256":"9ad472264194f70d9a9994dc2769f9d5cb4e527e6b110873a02bf0dbaa542ebb","source":{"kind":"arxiv","id":"2210.15893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15893","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15893v1","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15893","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"TLKHEJSBST3Q","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"TLKHEJSBST3Q3GUZ","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"TLKHEJSB","created_at":"2026-07-05T05:11:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TLKHEJSBST3Q3GUZSTOCO2PZ2X","target":"record","payload":{"canonical_record":{"source":{"id":"2210.15893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T04:57:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0bda0cd77f553ea069c6b583038861cdb75ffbfc96e7273dbb44183e2f1b1431","abstract_canon_sha256":"d8bf8d146715184fd2f8eec6b94beb693091e2fc7e925ee6299914343a3b28cf"},"schema_version":"1.0"},"canonical_sha256":"9ad472264194f70d9a9994dc2769f9d5cb4e527e6b110873a02bf0dbaa542ebb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:27.100882Z","signature_b64":"m5KCIN27bFxS2pHXxct3Dw6x+KI7E3dQDiu2kZzxWirBey+K9hJnulwWOkYfghW8me6p6vHCDg5Lbs5fiJIlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ad472264194f70d9a9994dc2769f9d5cb4e527e6b110873a02bf0dbaa542ebb","last_reissued_at":"2026-07-05T05:11:27.100294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:27.100294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.15893","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":"2026-07-05T05:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BB+xN/ce7e+AXg99n49nivXpjG2UvWL5iQJt5ektC7GSV20R9haTbE/Nc+gWHSbXhW6/XedWWQXF2JzNBBZECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:21:07.501283Z"},"content_sha256":"8a3eef4f35380c1df80a3e62692f34409e31b380a76279888089228b4ff311d7","schema_version":"1.0","event_id":"sha256:8a3eef4f35380c1df80a3e62692f34409e31b380a76279888089228b4ff311d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TLKHEJSBST3Q3GUZSTOCO2PZ2X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Emily Dinan, Jason Weston, Jing Xu, Kurt Shuster, Weiyan Shi","submitted_at":"2022-10-28T04:57:21Z","abstract_excerpt":"Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves. However, humans may not always provide explicit signals when the chatbot makes mistakes during interactions. In this work, we propose Juicer, a framework to make use of both binary and free-form textual human feedback. It works by: (i) extending sparse binary feedback by training a satisfaction classifier to label the unlabeled data; and (ii) training a reply corrector to map the bad replies to good ones. We find that augmenting training with model-corrected replies improves the final di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15893","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/2210.15893/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":"2026-07-05T05:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zZguEjWoPkOf6GrzHB2KIPUHxkzBiRON/EbWE8Kfo81Ywh2cbDsqGKgz9mFvMalQ6p2U3dyp4rgHxXpl/NV8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:21:07.501798Z"},"content_sha256":"74dcbc0d34aead513c49d20ec9424ebc400bb0ea1044332daae71fa89e3159c4","schema_version":"1.0","event_id":"sha256:74dcbc0d34aead513c49d20ec9424ebc400bb0ea1044332daae71fa89e3159c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLKHEJSBST3Q3GUZSTOCO2PZ2X/bundle.json","state_url":"https://pith.science/pith/TLKHEJSBST3Q3GUZSTOCO2PZ2X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLKHEJSBST3Q3GUZSTOCO2PZ2X/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":"2026-08-06T02:21:07Z","links":{"resolver":"https://pith.science/pith/TLKHEJSBST3Q3GUZSTOCO2PZ2X","bundle":"https://pith.science/pith/TLKHEJSBST3Q3GUZSTOCO2PZ2X/bundle.json","state":"https://pith.science/pith/TLKHEJSBST3Q3GUZSTOCO2PZ2X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLKHEJSBST3Q3GUZSTOCO2PZ2X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TLKHEJSBST3Q3GUZSTOCO2PZ2X","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":"d8bf8d146715184fd2f8eec6b94beb693091e2fc7e925ee6299914343a3b28cf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T04:57:21Z","title_canon_sha256":"0bda0cd77f553ea069c6b583038861cdb75ffbfc96e7273dbb44183e2f1b1431"},"schema_version":"1.0","source":{"id":"2210.15893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15893","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15893v1","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15893","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"TLKHEJSBST3Q","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"TLKHEJSBST3Q3GUZ","created_at":"2026-07-05T05:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"TLKHEJSB","created_at":"2026-07-05T05:11:27Z"}],"graph_snapshots":[{"event_id":"sha256:74dcbc0d34aead513c49d20ec9424ebc400bb0ea1044332daae71fa89e3159c4","target":"graph","created_at":"2026-07-05T05:11:27Z","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/2210.15893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves. However, humans may not always provide explicit signals when the chatbot makes mistakes during interactions. In this work, we propose Juicer, a framework to make use of both binary and free-form textual human feedback. It works by: (i) extending sparse binary feedback by training a satisfaction classifier to label the unlabeled data; and (ii) training a reply corrector to map the bad replies to good ones. We find that augmenting training with model-corrected replies improves the final di","authors_text":"Emily Dinan, Jason Weston, Jing Xu, Kurt Shuster, Weiyan Shi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T04:57:21Z","title":"When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15893","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":"sha256:8a3eef4f35380c1df80a3e62692f34409e31b380a76279888089228b4ff311d7","target":"record","created_at":"2026-07-05T05:11:27Z","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":"d8bf8d146715184fd2f8eec6b94beb693091e2fc7e925ee6299914343a3b28cf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T04:57:21Z","title_canon_sha256":"0bda0cd77f553ea069c6b583038861cdb75ffbfc96e7273dbb44183e2f1b1431"},"schema_version":"1.0","source":{"id":"2210.15893","kind":"arxiv","version":1}},"canonical_sha256":"9ad472264194f70d9a9994dc2769f9d5cb4e527e6b110873a02bf0dbaa542ebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ad472264194f70d9a9994dc2769f9d5cb4e527e6b110873a02bf0dbaa542ebb","first_computed_at":"2026-07-05T05:11:27.100294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:27.100294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m5KCIN27bFxS2pHXxct3Dw6x+KI7E3dQDiu2kZzxWirBey+K9hJnulwWOkYfghW8me6p6vHCDg5Lbs5fiJIlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:27.100882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.15893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a3eef4f35380c1df80a3e62692f34409e31b380a76279888089228b4ff311d7","sha256:74dcbc0d34aead513c49d20ec9424ebc400bb0ea1044332daae71fa89e3159c4"],"state_sha256":"3e691d6904422f395bdb91e7b2c1ccc9149a8c813697c60a25efd5bae8112e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0l1R1zyaP+Gr5FgMtNdaJ0zcnXAXyRJvKpbW80xeo63xDP10LI71fNDha1FyLQpBEOnaMUNfQ/ZUeEmGcrUADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:21:07.512333Z","bundle_sha256":"ea8acc9a4d7d0ea97105317837996879b802b9794f51bb9d4987bbe07d383b51"}}