{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I2U3UEJ5JJ6PKJLEDJH7TL5IN4","short_pith_number":"pith:I2U3UEJ5","schema_version":"1.0","canonical_sha256":"46a9ba113d4a7cf525641a4ff9afa86f2283cd7d1ff604ceee412af0b49b0dc7","source":{"kind":"arxiv","id":"2607.27914","version":1},"attestation_state":"computed","paper":{"title":"Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Kohei Terashima, Takumi Shioda, Tatsuo Nagai","submitted_at":"2026-07-30T09:28:37Z","abstract_excerpt":"Multi-zone variable-air-volume control must balance thermal comfort, indoor air quality, and electricity use across several continuous actuators. Model predictive control and reinforcement learning are widely studied, but deployment typically requires building-specific modeling or training, limiting scalability. We first test whether a frontier reasoning model (an LLM trained to use additional inference-time computation) can achieve competitive VAV control from text without building-specific training. With that capability established, we then test whether TD3-guided reinforcement fine-tuning ("},"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":"2607.27914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T09:28:37Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"7b1ac97003f8c570ae0e3b0c0c2188ec656ddd8c7907f53420a7fa378dddaa36","abstract_canon_sha256":"fadfc292c22cca6a4e8930b11dcc48d0319e0c9eeb927d6717ed2979872c2d54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46a9ba113d4a7cf525641a4ff9afa86f2283cd7d1ff604ceee412af0b49b0dc7","last_reissued_at":"2026-07-31T01:34:47.334488Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:34:47.334488Z"},"graph_snapshot":{"paper":{"title":"Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Kohei Terashima, Takumi Shioda, Tatsuo Nagai","submitted_at":"2026-07-30T09:28:37Z","abstract_excerpt":"Multi-zone variable-air-volume control must balance thermal comfort, indoor air quality, and electricity use across several continuous actuators. Model predictive control and reinforcement learning are widely studied, but deployment typically requires building-specific modeling or training, limiting scalability. We first test whether a frontier reasoning model (an LLM trained to use additional inference-time computation) can achieve competitive VAV control from text without building-specific training. With that capability established, we then test whether TD3-guided reinforcement fine-tuning ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27914","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/2607.27914/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":"2607.27914","created_at":"2026-07-31T01:34:47.337624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27914v1","created_at":"2026-07-31T01:34:47.337624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27914","created_at":"2026-07-31T01:34:47.337624+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2U3UEJ5JJ6P","created_at":"2026-07-31T01:34:47.337624+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2U3UEJ5JJ6PKJLE","created_at":"2026-07-31T01:34:47.337624+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2U3UEJ5","created_at":"2026-07-31T01:34:47.337624+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/I2U3UEJ5JJ6PKJLEDJH7TL5IN4","json":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4.json","graph_json":"https://pith.science/api/pith-number/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/graph.json","events_json":"https://pith.science/api/pith-number/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/events.json","paper":"https://pith.science/paper/I2U3UEJ5"},"agent_actions":{"view_html":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4","download_json":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4.json","view_paper":"https://pith.science/paper/I2U3UEJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27914&json=true","fetch_graph":"https://pith.science/api/pith-number/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/graph.json","fetch_events":"https://pith.science/api/pith-number/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/action/storage_attestation","attest_author":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/action/author_attestation","sign_citation":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/action/citation_signature","submit_replication":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/action/replication_record"}},"created_at":"2026-07-31T01:34:47.337624+00:00","updated_at":"2026-07-31T01:34:47.337624+00:00"}