{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I2U3UEJ5JJ6PKJLEDJH7TL5IN4","short_pith_number":"pith:I2U3UEJ5","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"},"canonical_sha256":"46a9ba113d4a7cf525641a4ff9afa86f2283cd7d1ff604ceee412af0b49b0dc7","source":{"kind":"arxiv","id":"2607.27914","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27914","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27914v1","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27914","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"I2U3UEJ5JJ6P","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"I2U3UEJ5JJ6PKJLE","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"I2U3UEJ5","created_at":"2026-07-31T01:34:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I2U3UEJ5JJ6PKJLEDJH7TL5IN4","target":"record","payload":{"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"},"canonical_sha256":"46a9ba113d4a7cf525641a4ff9afa86f2283cd7d1ff604ceee412af0b49b0dc7","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"},"source_kind":"arxiv","source_id":"2607.27914","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":"2026-07-31T01:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7hKsSXcOfjiZc7MOZSeFC7t+PS8/882MF1LZ0D5ljQoC128ggGcRWb6Mc+SkUqM3rdn34FOK8gEDK6UnXSNwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:10:58.873217Z"},"content_sha256":"b2461b9a7b05a1f9d87487819434ff9edb0b05ccaaea89b8a770941c18cc31ca","schema_version":"1.0","event_id":"sha256:b2461b9a7b05a1f9d87487819434ff9edb0b05ccaaea89b8a770941c18cc31ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I2U3UEJ5JJ6PKJLEDJH7TL5IN4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxgU8R/df5m4b8ZySE2zQZTcHYRn5OP0PKwBAowbOjRGKbdk/ZrMs1rJxQlIQoEsiJRN3ATfsEyYLMVdOjlwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:10:58.873784Z"},"content_sha256":"ebaaa1ddafe1f029cceba59db4660315ee41cd632a92b076b488f675861604f4","schema_version":"1.0","event_id":"sha256:ebaaa1ddafe1f029cceba59db4660315ee41cd632a92b076b488f675861604f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/bundle.json","state_url":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/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":"2026-08-13T14:10:58Z","links":{"resolver":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4","bundle":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/bundle.json","state":"https://pith.science/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2U3UEJ5JJ6PKJLEDJH7TL5IN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I2U3UEJ5JJ6PKJLEDJH7TL5IN4","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":"fadfc292c22cca6a4e8930b11dcc48d0319e0c9eeb927d6717ed2979872c2d54","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T09:28:37Z","title_canon_sha256":"7b1ac97003f8c570ae0e3b0c0c2188ec656ddd8c7907f53420a7fa378dddaa36"},"schema_version":"1.0","source":{"id":"2607.27914","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27914","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27914v1","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27914","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"I2U3UEJ5JJ6P","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"I2U3UEJ5JJ6PKJLE","created_at":"2026-07-31T01:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"I2U3UEJ5","created_at":"2026-07-31T01:34:47Z"}],"graph_snapshots":[{"event_id":"sha256:ebaaa1ddafe1f029cceba59db4660315ee41cd632a92b076b488f675861604f4","target":"graph","created_at":"2026-07-31T01:34:47Z","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":[],"endpoint":"/pith/2607.27914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 (","authors_text":"Kohei Terashima, Takumi Shioda, Tatsuo Nagai","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T09:28:37Z","title":"Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27914","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:b2461b9a7b05a1f9d87487819434ff9edb0b05ccaaea89b8a770941c18cc31ca","target":"record","created_at":"2026-07-31T01:34:47Z","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":"fadfc292c22cca6a4e8930b11dcc48d0319e0c9eeb927d6717ed2979872c2d54","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T09:28:37Z","title_canon_sha256":"7b1ac97003f8c570ae0e3b0c0c2188ec656ddd8c7907f53420a7fa378dddaa36"},"schema_version":"1.0","source":{"id":"2607.27914","kind":"arxiv","version":1}},"canonical_sha256":"46a9ba113d4a7cf525641a4ff9afa86f2283cd7d1ff604ceee412af0b49b0dc7","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46a9ba113d4a7cf525641a4ff9afa86f2283cd7d1ff604ceee412af0b49b0dc7","first_computed_at":"2026-07-31T01:34:47.334488Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:34:47.334488Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27914","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2461b9a7b05a1f9d87487819434ff9edb0b05ccaaea89b8a770941c18cc31ca","sha256:ebaaa1ddafe1f029cceba59db4660315ee41cd632a92b076b488f675861604f4"],"state_sha256":"0cb691b0686be737ff434adb4f1a92a1f7a97730e1661f811a38889fceba2f7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JzCU3wQhdYq0DN4xGr+s6JTqm/wB5H0Xux1yGkLi30m61chqL707g4dW7Pr14MHFKRWskIqfW9MhS3R2O79fCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T14:10:58.914619Z","bundle_sha256":"607a38396919f464e51e13e5abcdee62b78f4e955dd4c821e7cbc63c1f3c70e3"}}