{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SBCN7S7QJMK7VQUKJLOV6ZXOJ4","short_pith_number":"pith:SBCN7S7Q","schema_version":"1.0","canonical_sha256":"9044dfcbf04b15fac28a4add5f66ee4f16d049ce5ec2a706861fc11bdd65cf9b","source":{"kind":"arxiv","id":"2506.18831","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"A PID controller dynamically adjusts activation steering to cut redundant chain-of-thought steps in large language models.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aryasomayajula Ram Bharadwaj","submitted_at":"2025-06-23T16:47:19Z","abstract_excerpt":"Reasoning LLMs trained with long chain-of-thought often overthink: they spend tokens on redundant reflection and transitions that inflate cost without improving accuracy. Static activation steering (e.g.\\ SEAL) suppresses such content with a fixed vector, but applies the same strength regardless of how redundant the current chunk actually is. We describe PID-steering, a training-free, decoding-time method that modulates the steering strength with a PID controller driven by a lightweight chunk-level redundancy classifier. On a subset of GSM8K with DeepSeek-R1-Distill-Qwen-1.5B, the method impro"},"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":"2506.18831","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T16:47:19Z","cross_cats_sorted":[],"title_canon_sha256":"7db8783bc4159567b641a053d982b9d11196df000807f69ab69f90f1a67f6c86","abstract_canon_sha256":"b795235b91fe6efe961c64431f2ab871a01e03250abc48ef1198fb77424b5d43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:49.750442Z","signature_b64":"MFcSbAr4iP/QAMmP9cdTlsprTnbChaPSYWhQzQml7aDYpMcM2rjmcS0E3H7XZXk/IsOVG7t8k7YoasNIhszUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9044dfcbf04b15fac28a4add5f66ee4f16d049ce5ec2a706861fc11bdd65cf9b","last_reissued_at":"2026-06-19T16:09:49.750009Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:49.750009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"A PID controller dynamically adjusts activation steering to cut redundant chain-of-thought steps in large language models.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aryasomayajula Ram Bharadwaj","submitted_at":"2025-06-23T16:47:19Z","abstract_excerpt":"Reasoning LLMs trained with long chain-of-thought often overthink: they spend tokens on redundant reflection and transitions that inflate cost without improving accuracy. Static activation steering (e.g.\\ SEAL) suppresses such content with a fixed vector, but applies the same strength regardless of how redundant the current chunk actually is. We describe PID-steering, a training-free, decoding-time method that modulates the steering strength with a PID controller driven by a lightweight chunk-level redundancy classifier. On a subset of GSM8K with DeepSeek-R1-Distill-Qwen-1.5B, the method impro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental evaluation on GSM8K demonstrates that STUPID achieves a 6% improvement in accuracy while reducing token usage by 32%, outperforming static steering baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The chunk-level classifier reliably detects redundant reasoning patterns in real time and that its redundancy probability can be used as a stable error signal for the PID controller without introducing new failure modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"STU-PID combines a chunk-level redundancy classifier with a PID controller to dynamically modulate activation steering in LLMs, yielding 6% higher accuracy and 32% fewer tokens on GSM8K compared to static baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A PID controller dynamically adjusts activation steering to cut redundant chain-of-thought steps in large language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"adf579ab6265be845723eebbf1e5633bb3c17822e9240c62dbd92d57011e0312"},"source":{"id":"2506.18831","kind":"arxiv","version":3},"verdict":{"id":"15efd949-bac2-45fa-a367-4828f769767a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T07:52:07.170603Z","strongest_claim":"Experimental evaluation on GSM8K demonstrates that STUPID achieves a 6% improvement in accuracy while reducing token usage by 32%, outperforming static steering baselines.","one_line_summary":"STU-PID combines a chunk-level redundancy classifier with a PID controller to dynamically modulate activation steering in LLMs, yielding 6% higher accuracy and 32% fewer tokens on GSM8K compared to static baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The chunk-level classifier reliably detects redundant reasoning patterns in real time and that its redundancy probability can be used as a stable error signal for the PID controller without introducing new failure modes.","pith_extraction_headline":"A PID controller dynamically adjusts activation steering to cut redundant chain-of-thought steps in large language models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.18831/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":"2506.18831","created_at":"2026-06-19T16:09:49.750064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18831v3","created_at":"2026-06-19T16:09:49.750064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18831","created_at":"2026-06-19T16:09:49.750064+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBCN7S7QJMK7","created_at":"2026-06-19T16:09:49.750064+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBCN7S7QJMK7VQUK","created_at":"2026-06-19T16:09:49.750064+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBCN7S7Q","created_at":"2026-06-19T16:09:49.750064+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/SBCN7S7QJMK7VQUKJLOV6ZXOJ4","json":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4.json","graph_json":"https://pith.science/api/pith-number/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/graph.json","events_json":"https://pith.science/api/pith-number/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/events.json","paper":"https://pith.science/paper/SBCN7S7Q"},"agent_actions":{"view_html":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4","download_json":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4.json","view_paper":"https://pith.science/paper/SBCN7S7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18831&json=true","fetch_graph":"https://pith.science/api/pith-number/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/action/storage_attestation","attest_author":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/action/author_attestation","sign_citation":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/action/citation_signature","submit_replication":"https://pith.science/pith/SBCN7S7QJMK7VQUKJLOV6ZXOJ4/action/replication_record"}},"created_at":"2026-06-19T16:09:49.750064+00:00","updated_at":"2026-06-19T16:09:49.750064+00:00"}