{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HZGDWEAGZKMDALWEMJRTKJYHJ2","short_pith_number":"pith:HZGDWEAG","canonical_record":{"source":{"id":"2308.01479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T00:10:23Z","cross_cats_sorted":[],"title_canon_sha256":"cfc5ea470289d5d64dec2173cd01c68c15438c697757a56ffd1b1e1fbc858a43","abstract_canon_sha256":"54d224056eed4153c3b7e79862b77cb462393be855341a583cc77a4d924ff1ca"},"schema_version":"1.0"},"canonical_sha256":"3e4c3b1006ca98302ec462633527074e891d399010772cf915141d3a237c2aa7","source":{"kind":"arxiv","id":"2308.01479","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01479","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01479v1","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01479","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"HZGDWEAGZKMD","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"HZGDWEAGZKMDALWE","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"HZGDWEAG","created_at":"2026-07-05T06:37:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HZGDWEAGZKMDALWEMJRTKJYHJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2308.01479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T00:10:23Z","cross_cats_sorted":[],"title_canon_sha256":"cfc5ea470289d5d64dec2173cd01c68c15438c697757a56ffd1b1e1fbc858a43","abstract_canon_sha256":"54d224056eed4153c3b7e79862b77cb462393be855341a583cc77a4d924ff1ca"},"schema_version":"1.0"},"canonical_sha256":"3e4c3b1006ca98302ec462633527074e891d399010772cf915141d3a237c2aa7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:19.101582Z","signature_b64":"GZM0ZSACbG6YkCSY/bVNUZDLdvKo/sn+kz/gGr/XXR5PwnoaGx7/ZbdqedrQqZjmODiJlWyY3Svqd6Us+Y1vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e4c3b1006ca98302ec462633527074e891d399010772cf915141d3a237c2aa7","last_reissued_at":"2026-07-05T06:37:19.101082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:19.101082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.01479","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":"2026-07-05T06:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1xuiW4cAt3MFtCTHdEGs3lzP4fX3TZqL3UugOTpxJBOth9ajb/uTesPHIphWDGIG6gn7BTgf1eMCKe5CeBCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:44.461986Z"},"content_sha256":"d06ec5affd2451827374fcb5c05f79534912428379647fe6fc4ccf2364cf1dd6","schema_version":"1.0","event_id":"sha256:d06ec5affd2451827374fcb5c05f79534912428379647fe6fc4ccf2364cf1dd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HZGDWEAGZKMDALWEMJRTKJYHJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Reinforcement Learning for Communication Strategies in a Task-Initiative Setting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baber Khalid, Matthew Stone","submitted_at":"2023-08-03T00:10:23Z","abstract_excerpt":"Many conversational domains require the system to present nuanced information to users. Such systems must follow up what they say to address clarification questions and repair misunderstandings. In this work, we explore this interactive strategy in a referential communication task. Using simulation, we analyze the communication trade-offs between initial presentation and subsequent followup as a function of user clarification strategy, and compare the performance of several baseline strategies to policies derived by reinforcement learning. We find surprising advantages to coherence-based repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01479","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/2308.01479/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":"2026-07-05T06:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZD41tRwrBALW++gTKXLjl9zdde7lR9nV7f30cn/7/cBFk4FbWM2nQlyEHzykVpGQFRfpGgG7UJqFsHQ3VJa5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:44.462367Z"},"content_sha256":"af9e32d0ea04c7529415aeb2010abf642682ef777ba21e7afaed43d4c859bb87","schema_version":"1.0","event_id":"sha256:af9e32d0ea04c7529415aeb2010abf642682ef777ba21e7afaed43d4c859bb87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZGDWEAGZKMDALWEMJRTKJYHJ2/bundle.json","state_url":"https://pith.science/pith/HZGDWEAGZKMDALWEMJRTKJYHJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZGDWEAGZKMDALWEMJRTKJYHJ2/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":"2026-07-06T18:45:44Z","links":{"resolver":"https://pith.science/pith/HZGDWEAGZKMDALWEMJRTKJYHJ2","bundle":"https://pith.science/pith/HZGDWEAGZKMDALWEMJRTKJYHJ2/bundle.json","state":"https://pith.science/pith/HZGDWEAGZKMDALWEMJRTKJYHJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZGDWEAGZKMDALWEMJRTKJYHJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HZGDWEAGZKMDALWEMJRTKJYHJ2","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":"54d224056eed4153c3b7e79862b77cb462393be855341a583cc77a4d924ff1ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T00:10:23Z","title_canon_sha256":"cfc5ea470289d5d64dec2173cd01c68c15438c697757a56ffd1b1e1fbc858a43"},"schema_version":"1.0","source":{"id":"2308.01479","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01479","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01479v1","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01479","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"HZGDWEAGZKMD","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"HZGDWEAGZKMDALWE","created_at":"2026-07-05T06:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"HZGDWEAG","created_at":"2026-07-05T06:37:19Z"}],"graph_snapshots":[{"event_id":"sha256:af9e32d0ea04c7529415aeb2010abf642682ef777ba21e7afaed43d4c859bb87","target":"graph","created_at":"2026-07-05T06:37:19Z","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/2308.01479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many conversational domains require the system to present nuanced information to users. Such systems must follow up what they say to address clarification questions and repair misunderstandings. In this work, we explore this interactive strategy in a referential communication task. Using simulation, we analyze the communication trade-offs between initial presentation and subsequent followup as a function of user clarification strategy, and compare the performance of several baseline strategies to policies derived by reinforcement learning. We find surprising advantages to coherence-based repre","authors_text":"Baber Khalid, Matthew Stone","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T00:10:23Z","title":"Investigating Reinforcement Learning for Communication Strategies in a Task-Initiative Setting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01479","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:d06ec5affd2451827374fcb5c05f79534912428379647fe6fc4ccf2364cf1dd6","target":"record","created_at":"2026-07-05T06:37:19Z","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":"54d224056eed4153c3b7e79862b77cb462393be855341a583cc77a4d924ff1ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T00:10:23Z","title_canon_sha256":"cfc5ea470289d5d64dec2173cd01c68c15438c697757a56ffd1b1e1fbc858a43"},"schema_version":"1.0","source":{"id":"2308.01479","kind":"arxiv","version":1}},"canonical_sha256":"3e4c3b1006ca98302ec462633527074e891d399010772cf915141d3a237c2aa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e4c3b1006ca98302ec462633527074e891d399010772cf915141d3a237c2aa7","first_computed_at":"2026-07-05T06:37:19.101082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:19.101082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GZM0ZSACbG6YkCSY/bVNUZDLdvKo/sn+kz/gGr/XXR5PwnoaGx7/ZbdqedrQqZjmODiJlWyY3Svqd6Us+Y1vBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:19.101582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01479","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d06ec5affd2451827374fcb5c05f79534912428379647fe6fc4ccf2364cf1dd6","sha256:af9e32d0ea04c7529415aeb2010abf642682ef777ba21e7afaed43d4c859bb87"],"state_sha256":"a9da58fb09956b292a1e1f149c873254839134799edba2a556e24f021c3a41a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0l5bMUQLPRDXZ0wcqumWG7vWkctfYWW2y/fziIXuBJQFwH9JSQlGXSOzsmebIAMxI7KqwYMNdnbWZnMXk35JAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:45:44.464177Z","bundle_sha256":"91bb97e46a3cc8dc945a1da5e988dca7a777dca25a4f4aa15d7db4643c9f4b5a"}}