{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DPHWVMUPOKU7SLZC5P36TT7ENJ","short_pith_number":"pith:DPHWVMUP","schema_version":"1.0","canonical_sha256":"1bcf6ab28f72a9f92f22ebf7e9cfe46a475a09e3dc2b5d296fd056f98a93534b","source":{"kind":"arxiv","id":"2605.15604","version":1},"attestation_state":"computed","paper":{"title":"VSPO: Vector-Steered Policy Optimization for Behavioral Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiasi Chen, Kai Yang, Samet Oymak, Weijia Zhang, Xuechen Zhang, Zijian Huang","submitted_at":"2026-05-15T04:31:06Z","abstract_excerpt":"Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level of technical expertise in its response. In practice, a base model may exhibit a desired behavior very rarely or not at all. Thus, endowing the model with a target behavior creates a sparse behavioral reward bottleneck. To address such multi-objective problems, we introduce Vector-Steered Policy Optimization (VSPO) which employs a steering vector associated with the target behavior to control the behavior intensity o"},"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":"2605.15604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:31:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"79b499d67af693cdab2fecee0cd6f73e1d6a61e475a3dd39e291364cbb9e04f9","abstract_canon_sha256":"2be40433f7db3fd2753586b02aee02a0c92d2e11527149d55a7a4e7362af5003"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:07.680602Z","signature_b64":"qTftyzZVXSHSLJeXY7eINNID+sLkFQ9j9HA3/8yKQln2nmNLt7Wz/xFBPPrHxpzsdwLpgi/oCCn4gvgczSC2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bcf6ab28f72a9f92f22ebf7e9cfe46a475a09e3dc2b5d296fd056f98a93534b","last_reissued_at":"2026-05-20T00:01:07.679708Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:07.679708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VSPO: Vector-Steered Policy Optimization for Behavioral Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiasi Chen, Kai Yang, Samet Oymak, Weijia Zhang, Xuechen Zhang, Zijian Huang","submitted_at":"2026-05-15T04:31:06Z","abstract_excerpt":"Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level of technical expertise in its response. In practice, a base model may exhibit a desired behavior very rarely or not at all. Thus, endowing the model with a target behavior creates a sparse behavioral reward bottleneck. To address such multi-objective problems, we introduce Vector-Steered Policy Optimization (VSPO) which employs a steering vector associated with the target behavior to control the behavior intensity o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15604","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/2605.15604/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.893810Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.051794Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ea6fbca167b0ef150213a5db91d0a713360b7ff8ed8c8e5c704a370bca9ea70a"},"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":"2605.15604","created_at":"2026-05-20T00:01:07.679851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15604v1","created_at":"2026-05-20T00:01:07.679851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15604","created_at":"2026-05-20T00:01:07.679851+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPHWVMUPOKU7","created_at":"2026-05-20T00:01:07.679851+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPHWVMUPOKU7SLZC","created_at":"2026-05-20T00:01:07.679851+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPHWVMUP","created_at":"2026-05-20T00:01:07.679851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ","json":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ.json","graph_json":"https://pith.science/api/pith-number/DPHWVMUPOKU7SLZC5P36TT7ENJ/graph.json","events_json":"https://pith.science/api/pith-number/DPHWVMUPOKU7SLZC5P36TT7ENJ/events.json","paper":"https://pith.science/paper/DPHWVMUP"},"agent_actions":{"view_html":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ","download_json":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ.json","view_paper":"https://pith.science/paper/DPHWVMUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15604&json=true","fetch_graph":"https://pith.science/api/pith-number/DPHWVMUPOKU7SLZC5P36TT7ENJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DPHWVMUPOKU7SLZC5P36TT7ENJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ/action/storage_attestation","attest_author":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ/action/author_attestation","sign_citation":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ/action/citation_signature","submit_replication":"https://pith.science/pith/DPHWVMUPOKU7SLZC5P36TT7ENJ/action/replication_record"}},"created_at":"2026-05-20T00:01:07.679851+00:00","updated_at":"2026-05-20T00:01:07.679851+00:00"}