{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:U3JBUC6YQTQAVJY4F236MXUI5S","short_pith_number":"pith:U3JBUC6Y","canonical_record":{"source":{"id":"1511.08099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-25T15:48:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd671c222c887a1fe737f90f0b5c5dac250da358be48f9cef3c312433d32aa12","abstract_canon_sha256":"99ad4b979e9e3c85668df0d2cf71c048f61e3f4ea95b6e6474779625eddc5612"},"schema_version":"1.0"},"canonical_sha256":"a6d21a0bd884e00aa71c2eb7e65e88ec987115ca1dd15afbb1e2c9e359f2b9c7","source":{"kind":"arxiv","id":"1511.08099","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.08099","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"arxiv_version","alias_value":"1511.08099v1","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08099","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"pith_short_12","alias_value":"U3JBUC6YQTQA","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"U3JBUC6YQTQAVJY4","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"U3JBUC6Y","created_at":"2026-05-18T12:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:U3JBUC6YQTQAVJY4F236MXUI5S","target":"record","payload":{"canonical_record":{"source":{"id":"1511.08099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-25T15:48:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd671c222c887a1fe737f90f0b5c5dac250da358be48f9cef3c312433d32aa12","abstract_canon_sha256":"99ad4b979e9e3c85668df0d2cf71c048f61e3f4ea95b6e6474779625eddc5612"},"schema_version":"1.0"},"canonical_sha256":"a6d21a0bd884e00aa71c2eb7e65e88ec987115ca1dd15afbb1e2c9e359f2b9c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:56.693995Z","signature_b64":"ZTP7prmfbG0qeDpPSqHNnZp30ih1gAmF55gYtszdzIbf+RXvzVbReTLIQPctv4OR3mtdMcwvSrNvtrdcdFVMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6d21a0bd884e00aa71c2eb7e65e88ec987115ca1dd15afbb1e2c9e359f2b9c7","last_reissued_at":"2026-05-18T01:25:56.693234Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:56.693234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.08099","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":"2026-05-18T01:25:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XJtbVhyM0Xt6VKqFzdiSmiGuaQ/DwqB6U4HpxQy/vv6xK4+BYl6WwGsA6PECkjgopIhN76lv7quIfSBPAKHTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T23:30:00.983157Z"},"content_sha256":"c73f755244ddd5391410017cd9ccc98c2f507ee3c54870534b1a854a176fdeea","schema_version":"1.0","event_id":"sha256:c73f755244ddd5391410017cd9ccc98c2f507ee3c54870534b1a854a176fdeea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:U3JBUC6YQTQAVJY4F236MXUI5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Strategic Dialogue Management via Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Heriberto Cuay\\'ahuitl, Oliver Lemon, Simon Keizer","submitted_at":"2015-11-25T15:48:59Z","abstract_excerpt":"Artificially intelligent agents equipped with strategic skills that can negotiate during their interactions with other natural or artificial agents are still underdeveloped. This paper describes a successful application of Deep Reinforcement Learning (DRL) for training intelligent agents with strategic conversational skills, in a situated dialogue setting. Previous studies have modelled the behaviour of strategic agents using supervised learning and traditional reinforcement learning techniques, the latter using tabular representations or learning with linear function approximation. In this st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08099","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":""},"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":"2026-05-18T01:25:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8F6AGYulIkqZSLUtJ+r1wmrmfz5CSm7ckgKLAGK2EyrBd9ZMi60Rz0iFd5DaTNSfluSfRUbbvcDkC3sgfYjBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T23:30:00.983772Z"},"content_sha256":"18055491c1d0a50e32c08924a5db319112931e40a6e46103b5411d92d3a9130c","schema_version":"1.0","event_id":"sha256:18055491c1d0a50e32c08924a5db319112931e40a6e46103b5411d92d3a9130c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3JBUC6YQTQAVJY4F236MXUI5S/bundle.json","state_url":"https://pith.science/pith/U3JBUC6YQTQAVJY4F236MXUI5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3JBUC6YQTQAVJY4F236MXUI5S/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":"2026-06-10T23:30:00Z","links":{"resolver":"https://pith.science/pith/U3JBUC6YQTQAVJY4F236MXUI5S","bundle":"https://pith.science/pith/U3JBUC6YQTQAVJY4F236MXUI5S/bundle.json","state":"https://pith.science/pith/U3JBUC6YQTQAVJY4F236MXUI5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3JBUC6YQTQAVJY4F236MXUI5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:U3JBUC6YQTQAVJY4F236MXUI5S","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":"99ad4b979e9e3c85668df0d2cf71c048f61e3f4ea95b6e6474779625eddc5612","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-25T15:48:59Z","title_canon_sha256":"fd671c222c887a1fe737f90f0b5c5dac250da358be48f9cef3c312433d32aa12"},"schema_version":"1.0","source":{"id":"1511.08099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.08099","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"arxiv_version","alias_value":"1511.08099v1","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08099","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"pith_short_12","alias_value":"U3JBUC6YQTQA","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"U3JBUC6YQTQAVJY4","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"U3JBUC6Y","created_at":"2026-05-18T12:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:18055491c1d0a50e32c08924a5db319112931e40a6e46103b5411d92d3a9130c","target":"graph","created_at":"2026-05-18T01:25:56Z","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"},"paper":{"abstract_excerpt":"Artificially intelligent agents equipped with strategic skills that can negotiate during their interactions with other natural or artificial agents are still underdeveloped. This paper describes a successful application of Deep Reinforcement Learning (DRL) for training intelligent agents with strategic conversational skills, in a situated dialogue setting. Previous studies have modelled the behaviour of strategic agents using supervised learning and traditional reinforcement learning techniques, the latter using tabular representations or learning with linear function approximation. In this st","authors_text":"Heriberto Cuay\\'ahuitl, Oliver Lemon, Simon Keizer","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-25T15:48:59Z","title":"Strategic Dialogue Management via Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08099","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:c73f755244ddd5391410017cd9ccc98c2f507ee3c54870534b1a854a176fdeea","target":"record","created_at":"2026-05-18T01:25:56Z","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":"99ad4b979e9e3c85668df0d2cf71c048f61e3f4ea95b6e6474779625eddc5612","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-25T15:48:59Z","title_canon_sha256":"fd671c222c887a1fe737f90f0b5c5dac250da358be48f9cef3c312433d32aa12"},"schema_version":"1.0","source":{"id":"1511.08099","kind":"arxiv","version":1}},"canonical_sha256":"a6d21a0bd884e00aa71c2eb7e65e88ec987115ca1dd15afbb1e2c9e359f2b9c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6d21a0bd884e00aa71c2eb7e65e88ec987115ca1dd15afbb1e2c9e359f2b9c7","first_computed_at":"2026-05-18T01:25:56.693234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:56.693234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZTP7prmfbG0qeDpPSqHNnZp30ih1gAmF55gYtszdzIbf+RXvzVbReTLIQPctv4OR3mtdMcwvSrNvtrdcdFVMAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:56.693995Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.08099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c73f755244ddd5391410017cd9ccc98c2f507ee3c54870534b1a854a176fdeea","sha256:18055491c1d0a50e32c08924a5db319112931e40a6e46103b5411d92d3a9130c"],"state_sha256":"e87bfd251fb59e2306d7827119de7db8c3596bcfdaa8142307bad44f3cb5efa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8cWrNhwO6o92I8tGfeyd7raWsqZZLBZsRyPiboY59AD6vsAVEr1AwT/KR4i5RD9CcV45Iy3P43ZDyz+PR9qUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T23:30:00.986931Z","bundle_sha256":"11f6c1c10632f015db48e757fa0cd851c993b669eb04146112910ba25a9d13c8"}}