{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DPHWVMUPOKU7SLZC5P36TT7ENJ","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":"2be40433f7db3fd2753586b02aee02a0c92d2e11527149d55a7a4e7362af5003","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:31:06Z","title_canon_sha256":"79b499d67af693cdab2fecee0cd6f73e1d6a61e475a3dd39e291364cbb9e04f9"},"schema_version":"1.0","source":{"id":"2605.15604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15604","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15604v1","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15604","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"DPHWVMUPOKU7","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"DPHWVMUPOKU7SLZC","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"DPHWVMUP","created_at":"2026-05-20T00:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:fc39c6603b5287323635a3735ab5a609905a155255312ef5fc3f59dfd04ef914","target":"graph","created_at":"2026-05-20T00:01:07Z","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":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.15604/integrity.json","findings":[],"snapshot_sha256":"ea6fbca167b0ef150213a5db91d0a713360b7ff8ed8c8e5c704a370bca9ea70a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiasi Chen, Kai Yang, Samet Oymak, Weijia Zhang, Xuechen Zhang, Zijian Huang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:31:06Z","title":"VSPO: Vector-Steered Policy Optimization for Behavioral Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15604","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":"sha256:75c44a7672b95c067accc60e2e87225bd87fe54a2d66b76e242620a52d1412f2","target":"record","created_at":"2026-05-20T00:01:07Z","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":"2be40433f7db3fd2753586b02aee02a0c92d2e11527149d55a7a4e7362af5003","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:31:06Z","title_canon_sha256":"79b499d67af693cdab2fecee0cd6f73e1d6a61e475a3dd39e291364cbb9e04f9"},"schema_version":"1.0","source":{"id":"2605.15604","kind":"arxiv","version":1}},"canonical_sha256":"1bcf6ab28f72a9f92f22ebf7e9cfe46a475a09e3dc2b5d296fd056f98a93534b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bcf6ab28f72a9f92f22ebf7e9cfe46a475a09e3dc2b5d296fd056f98a93534b","first_computed_at":"2026-05-20T00:01:07.679708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:07.679708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qTftyzZVXSHSLJeXY7eINNID+sLkFQ9j9HA3/8yKQln2nmNLt7Wz/xFBPPrHxpzsdwLpgi/oCCn4gvgczSC2CA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:07.680602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75c44a7672b95c067accc60e2e87225bd87fe54a2d66b76e242620a52d1412f2","sha256:fc39c6603b5287323635a3735ab5a609905a155255312ef5fc3f59dfd04ef914"],"state_sha256":"8098fd2fe7eceb710979cb10bea9dc933928be7afe5117d125a2508987c695fb"}