{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BLKURIMSDBKKIY54PBEMNMXKTX","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":"780118b4df8b6e3b68e4fa21755edc59148c5b1d82f72f672a8ffb2fc0dc6faf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-30T06:27:46Z","title_canon_sha256":"4ded85d4a11b72e20f174c629b1ea093463aa63fe046abb8d3633ba99823c773"},"schema_version":"1.0","source":{"id":"2211.16773","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.16773","created_at":"2026-07-05T07:02:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.16773v5","created_at":"2026-07-05T07:02:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16773","created_at":"2026-07-05T07:02:47Z"},{"alias_kind":"pith_short_12","alias_value":"BLKURIMSDBKK","created_at":"2026-07-05T07:02:47Z"},{"alias_kind":"pith_short_16","alias_value":"BLKURIMSDBKKIY54","created_at":"2026-07-05T07:02:47Z"},{"alias_kind":"pith_short_8","alias_value":"BLKURIMS","created_at":"2026-07-05T07:02:47Z"}],"graph_snapshots":[{"event_id":"sha256:f13e417c2722f99a917e0fdad3e6a6134832504812d41cb040fcc34216d7debb","target":"graph","created_at":"2026-07-05T07:02:47Z","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/2211.16773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics. However, RL needs to perform exploration, which can be time-consuming due to the slow auto-regressive sequence generation process. We investigate an approach to create a more efficient RL-based algorithm to improve TOD performance in an offline setting. First, we use a faster generation procedure that samples from independent next-word distributions after training the language model (LM) with supervised learning. We then introduce a fine-grained reward fu","authors_text":"Kun Qian, Qingyang Wu, Xiao Yu, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-30T06:27:46Z","title":"KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16773","kind":"arxiv","version":5},"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:ca93874a961167611323ab241b078681f4922204c88730589fcfb41d569cfef2","target":"record","created_at":"2026-07-05T07:02:47Z","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":"780118b4df8b6e3b68e4fa21755edc59148c5b1d82f72f672a8ffb2fc0dc6faf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-30T06:27:46Z","title_canon_sha256":"4ded85d4a11b72e20f174c629b1ea093463aa63fe046abb8d3633ba99823c773"},"schema_version":"1.0","source":{"id":"2211.16773","kind":"arxiv","version":5}},"canonical_sha256":"0ad548a1921854a463bc7848c6b2ea9dffa8bb2e67656128e0d055f91f652e5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ad548a1921854a463bc7848c6b2ea9dffa8bb2e67656128e0d055f91f652e5f","first_computed_at":"2026-07-05T07:02:47.791997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:47.791997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twDtXZpicCXUMbM6at8DdK9qHnrFOLnpXjX4rp+4kyuU5khnAYiDpuiojGy8LWNXl7Do0xWNcqRJ6iHCweHDDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:47.792583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.16773","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca93874a961167611323ab241b078681f4922204c88730589fcfb41d569cfef2","sha256:f13e417c2722f99a917e0fdad3e6a6134832504812d41cb040fcc34216d7debb"],"state_sha256":"682ffadadb1fd7fc3ffb32bd4bec1b69907acfd3e618f3d3f4be89f8774f6f65"}