{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QYL75GOVWDPTUZYY6EAZIMNKTA","short_pith_number":"pith:QYL75GOV","schema_version":"1.0","canonical_sha256":"8617fe99d5b0df3a6718f1019431aa9829af809f73faf9be760582ca85c85a43","source":{"kind":"arxiv","id":"2503.03040","version":2},"attestation_state":"computed","paper":{"title":"SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Navdeep Jaitly, Yizhe Zhang","submitted_at":"2025-03-04T22:45:24Z","abstract_excerpt":"Recent advances in large language models have demonstrated impressive capabilities in task-oriented applications, yet building emotionally intelligent chatbots that can engage in natural, strategic conversations remains a challenge. We present a novel approach called SAGE that uses latent variables to control long-horizon behavior in dialogue generation. At the core of our method is the State-Action Chain (SAC), which augments standard language model fine-tuning by introducing latent variables that encapsulate emotional states and conversational strategies between dialogue turns. During infere"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.03040","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T22:45:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02c19c1ea066f394cc80e439094ea2caf07ec7cc2a6ee1c73423b3933c92f57e","abstract_canon_sha256":"cfbfb11970baf8a05e745ddff98babf7f9b1cf702127020c5aa74a1e1967e0b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:56.069432Z","signature_b64":"0BwSW6SdPTi2yP3ycraJtEihnZ5kq8HFYYH3Yd/cl6ac8ymf+7I40CsvHR2PSFBsbrYIVrk+Nk+wvjRGP1WlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8617fe99d5b0df3a6718f1019431aa9829af809f73faf9be760582ca85c85a43","last_reissued_at":"2026-07-05T11:29:56.068984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:56.068984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Navdeep Jaitly, Yizhe Zhang","submitted_at":"2025-03-04T22:45:24Z","abstract_excerpt":"Recent advances in large language models have demonstrated impressive capabilities in task-oriented applications, yet building emotionally intelligent chatbots that can engage in natural, strategic conversations remains a challenge. We present a novel approach called SAGE that uses latent variables to control long-horizon behavior in dialogue generation. At the core of our method is the State-Action Chain (SAC), which augments standard language model fine-tuning by introducing latent variables that encapsulate emotional states and conversational strategies between dialogue turns. During infere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03040","kind":"arxiv","version":2},"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/2503.03040/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.03040","created_at":"2026-07-05T11:29:56.069054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03040v2","created_at":"2026-07-05T11:29:56.069054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03040","created_at":"2026-07-05T11:29:56.069054+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYL75GOVWDPT","created_at":"2026-07-05T11:29:56.069054+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYL75GOVWDPTUZYY","created_at":"2026-07-05T11:29:56.069054+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYL75GOV","created_at":"2026-07-05T11:29:56.069054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00078","citing_title":"ChipChat: Low-Latency Cascaded Conversational Agent in MLX","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA","json":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA.json","graph_json":"https://pith.science/api/pith-number/QYL75GOVWDPTUZYY6EAZIMNKTA/graph.json","events_json":"https://pith.science/api/pith-number/QYL75GOVWDPTUZYY6EAZIMNKTA/events.json","paper":"https://pith.science/paper/QYL75GOV"},"agent_actions":{"view_html":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA","download_json":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA.json","view_paper":"https://pith.science/paper/QYL75GOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03040&json=true","fetch_graph":"https://pith.science/api/pith-number/QYL75GOVWDPTUZYY6EAZIMNKTA/graph.json","fetch_events":"https://pith.science/api/pith-number/QYL75GOVWDPTUZYY6EAZIMNKTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA/action/storage_attestation","attest_author":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA/action/author_attestation","sign_citation":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA/action/citation_signature","submit_replication":"https://pith.science/pith/QYL75GOVWDPTUZYY6EAZIMNKTA/action/replication_record"}},"created_at":"2026-07-05T11:29:56.069054+00:00","updated_at":"2026-07-05T11:29:56.069054+00:00"}