{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:STODHTOKKZKJCRZXLMPHB7XJFL","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":"396fe70c31871f8005f0f51b2f2ee89e1490959b33b0137912bf39417f1fbc2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-12T03:56:59Z","title_canon_sha256":"4ee323a4f3c275d116c96accb44f71dd925414325f564df41ebbd758c452a54c"},"schema_version":"1.0","source":{"id":"2204.05512","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05512","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05512v2","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05512","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"STODHTOKKZKJ","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"STODHTOKKZKJCRZX","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"STODHTOK","created_at":"2026-07-05T04:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:d1ce552a9f3618761ed79e3f32cf4500cfc356ac80cccaa32a1fffb14bcd21c3","target":"graph","created_at":"2026-07-05T04:22:41Z","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/2204.05512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For summarization, human preference is critical to tame outputs of the summarizer in favor of human interests, as ground-truth summaries are scarce and ambiguous. Practical settings require dynamic exchanges between human and AI agent wherein feedback is provided in an online manner, a few at a time. In this paper, we introduce a new framework to train summarization models with preference feedback interactively. By properly leveraging offline data and a novel reward model, we improve the performance regarding ROUGE scores and sample-efficiency. Our experiments on three various datasets confirm","authors_text":"Bao-Sinh Nguyen, Dung Tien Le, Duy-Hung Nguyen, Hung Le, Minh-Tien Nguyen, Nguyen Viet Dung Nghiem, Shahab Sabahi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-12T03:56:59Z","title":"Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05512","kind":"arxiv","version":2},"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":"sha256:24a20b5a3dfad05d08eeda1c6f9b753940cefc1abbbbb0a803e666e60544630d","target":"record","created_at":"2026-07-05T04:22:41Z","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":"396fe70c31871f8005f0f51b2f2ee89e1490959b33b0137912bf39417f1fbc2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-12T03:56:59Z","title_canon_sha256":"4ee323a4f3c275d116c96accb44f71dd925414325f564df41ebbd758c452a54c"},"schema_version":"1.0","source":{"id":"2204.05512","kind":"arxiv","version":2}},"canonical_sha256":"94dc33cdca56549147375b1e70fee92addf080373528633d14b14adf36ffafbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94dc33cdca56549147375b1e70fee92addf080373528633d14b14adf36ffafbc","first_computed_at":"2026-07-05T04:22:41.049630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:41.049630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NhlGipH3oxQnp+BQpPira4s2zuhy7uZ49IZTb2AzHC5h7hGIo4+P5kw5Oa28SX85kMj4Ft4N4SB5JlCB/eq4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:41.050065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05512","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24a20b5a3dfad05d08eeda1c6f9b753940cefc1abbbbb0a803e666e60544630d","sha256:d1ce552a9f3618761ed79e3f32cf4500cfc356ac80cccaa32a1fffb14bcd21c3"],"state_sha256":"d9b77dee9186e3026cb3056f8c1bb7a51084cb43c662bf0719bf7fb7481499ed"}