{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QXNQLYG3FEYQWAJWRFYQSLF5GL","short_pith_number":"pith:QXNQLYG3","canonical_record":{"source":{"id":"2204.07359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T07:38:08Z","cross_cats_sorted":[],"title_canon_sha256":"67824803eeedd4aee893928e361a134ca58d986739e3d671f4578b1dfef93571","abstract_canon_sha256":"5297642ddb4e2e978c2441f5d6a78f2d3a63b154e65af18120f0c6e96a245dbc"},"schema_version":"1.0"},"canonical_sha256":"85db05e0db29310b01368971092cbd32cbe16ed7ae3643b0f7dfca00cec2508d","source":{"kind":"arxiv","id":"2204.07359","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07359","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07359v1","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07359","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"QXNQLYG3FEYQ","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"QXNQLYG3FEYQWAJW","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"QXNQLYG3","created_at":"2026-07-05T04:15:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QXNQLYG3FEYQWAJWRFYQSLF5GL","target":"record","payload":{"canonical_record":{"source":{"id":"2204.07359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T07:38:08Z","cross_cats_sorted":[],"title_canon_sha256":"67824803eeedd4aee893928e361a134ca58d986739e3d671f4578b1dfef93571","abstract_canon_sha256":"5297642ddb4e2e978c2441f5d6a78f2d3a63b154e65af18120f0c6e96a245dbc"},"schema_version":"1.0"},"canonical_sha256":"85db05e0db29310b01368971092cbd32cbe16ed7ae3643b0f7dfca00cec2508d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:03.160880Z","signature_b64":"5NjSSVYR7PgiMvYpyhpPA9kddl0S3sQDV9azmk6kdQ55YoUW998fk7VsAueRO7pl9FzNWgZ4E63LtliQ9+7pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85db05e0db29310b01368971092cbd32cbe16ed7ae3643b0f7dfca00cec2508d","last_reissued_at":"2026-07-05T04:15:03.160347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:03.160347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.07359","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":"2026-07-05T04:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVuse1oC5UQCeCyMzinltjixaelB5gQXY/WM8jVc3529k2B3KzAp2hk7Kqh+/0VTbJpuQeF0vvwjGF4lAe8ADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T18:25:22.917197Z"},"content_sha256":"d43a192d6fb46d44a8e48ad854e2806b0132a6cc255821734420c7f6214912f6","schema_version":"1.0","event_id":"sha256:d43a192d6fb46d44a8e48ad854e2806b0132a6cc255821734420c7f6214912f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QXNQLYG3FEYQWAJWRFYQSLF5GL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Revision by On-the-Fly Representation Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Irwin King, Jingjing Li, Michael R. Lyu, Tao Ge, Zichao Li","submitted_at":"2022-04-15T07:38:08Z","abstract_excerpt":"Text revision refers to a family of natural language generation tasks, where the source and target sequences share moderate resemblance in surface form but differentiate in attributes, such as text formality and simplicity. Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems, which rely on large-scale parallel training corpus. In this paper, we present an iterative in-place editing approach for text revision, which requires no parallel data. In this approach, we simply fine-tune a pre-trained Transformer with masked language modeling and attribute c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07359","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/2204.07359/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":"2026-07-05T04:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2tWWkw6o+RTDtp+jycZGFLoDxqldxLACvwMHlSRTWvOFwa1oV7TiJf+dvpo+qmwiHYa+xY0Ztkfp55KCsOUiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T18:25:22.917581Z"},"content_sha256":"964fbe0fc12cdcc38e2e420523cad258e00b3dd567f7bf7174f6432f9a3e0e99","schema_version":"1.0","event_id":"sha256:964fbe0fc12cdcc38e2e420523cad258e00b3dd567f7bf7174f6432f9a3e0e99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXNQLYG3FEYQWAJWRFYQSLF5GL/bundle.json","state_url":"https://pith.science/pith/QXNQLYG3FEYQWAJWRFYQSLF5GL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXNQLYG3FEYQWAJWRFYQSLF5GL/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":"2026-07-21T18:25:22Z","links":{"resolver":"https://pith.science/pith/QXNQLYG3FEYQWAJWRFYQSLF5GL","bundle":"https://pith.science/pith/QXNQLYG3FEYQWAJWRFYQSLF5GL/bundle.json","state":"https://pith.science/pith/QXNQLYG3FEYQWAJWRFYQSLF5GL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXNQLYG3FEYQWAJWRFYQSLF5GL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QXNQLYG3FEYQWAJWRFYQSLF5GL","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":"5297642ddb4e2e978c2441f5d6a78f2d3a63b154e65af18120f0c6e96a245dbc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T07:38:08Z","title_canon_sha256":"67824803eeedd4aee893928e361a134ca58d986739e3d671f4578b1dfef93571"},"schema_version":"1.0","source":{"id":"2204.07359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07359","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07359v1","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07359","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"QXNQLYG3FEYQ","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"QXNQLYG3FEYQWAJW","created_at":"2026-07-05T04:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"QXNQLYG3","created_at":"2026-07-05T04:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:964fbe0fc12cdcc38e2e420523cad258e00b3dd567f7bf7174f6432f9a3e0e99","target":"graph","created_at":"2026-07-05T04:15:03Z","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/2204.07359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text revision refers to a family of natural language generation tasks, where the source and target sequences share moderate resemblance in surface form but differentiate in attributes, such as text formality and simplicity. Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems, which rely on large-scale parallel training corpus. In this paper, we present an iterative in-place editing approach for text revision, which requires no parallel data. In this approach, we simply fine-tune a pre-trained Transformer with masked language modeling and attribute c","authors_text":"Irwin King, Jingjing Li, Michael R. Lyu, Tao Ge, Zichao Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T07:38:08Z","title":"Text Revision by On-the-Fly Representation Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07359","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:d43a192d6fb46d44a8e48ad854e2806b0132a6cc255821734420c7f6214912f6","target":"record","created_at":"2026-07-05T04:15:03Z","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":"5297642ddb4e2e978c2441f5d6a78f2d3a63b154e65af18120f0c6e96a245dbc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T07:38:08Z","title_canon_sha256":"67824803eeedd4aee893928e361a134ca58d986739e3d671f4578b1dfef93571"},"schema_version":"1.0","source":{"id":"2204.07359","kind":"arxiv","version":1}},"canonical_sha256":"85db05e0db29310b01368971092cbd32cbe16ed7ae3643b0f7dfca00cec2508d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85db05e0db29310b01368971092cbd32cbe16ed7ae3643b0f7dfca00cec2508d","first_computed_at":"2026-07-05T04:15:03.160347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:03.160347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5NjSSVYR7PgiMvYpyhpPA9kddl0S3sQDV9azmk6kdQ55YoUW998fk7VsAueRO7pl9FzNWgZ4E63LtliQ9+7pBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:03.160880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d43a192d6fb46d44a8e48ad854e2806b0132a6cc255821734420c7f6214912f6","sha256:964fbe0fc12cdcc38e2e420523cad258e00b3dd567f7bf7174f6432f9a3e0e99"],"state_sha256":"bb5dd04269f7864114bbdf41e1cb89af0e0716a06a456ddb94d082f04d4e9d24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EDPxecJmiTgW6gGa6WkELfFyqLhNPNpeD818A/vdsDGDgdjbfKjDdkzB/T66LnK+dD6OXLLp2YeDrF18PSBpCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T18:25:22.919867Z","bundle_sha256":"02fd439f40df09c4c59a7c67e22188767a05da288e91a2eeb186de1efe28a4ec"}}