{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PHFIUFBOOI4NI6BJXD4535SCF4","short_pith_number":"pith:PHFIUFBO","schema_version":"1.0","canonical_sha256":"79ca8a142e7238d47829b8f9ddf6422f018b39c0531c483c252fb0ea8a8aff8d","source":{"kind":"arxiv","id":"2505.03771","version":3},"attestation_state":"computed","paper":{"title":"OneDSE: Metric-Conditioned Inverse Modeling and Active Search for Sample-Efficient DSE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AR","authors_text":"Akshat Ramachandran, Danny Samuel, Jeff Nye, Ritik Raj, Shashank Nemawarkar, Tushar Krishna","submitted_at":"2025-04-29T19:19:52Z","abstract_excerpt":"We identify two key challenges in prior CPU design space exploration (DSE) approaches: (a) short-horizon prediction is forward-only: modeling PPA metrics from design parameters while designers start from metric targets, and (b) long-horizon exploration is slow: evaluating thousands of candidates on cycle-accurate simulators. This work presents OneDSE, which unifies short-horizon design prediction and long-horizon design optimization through Metric-conditioned INverse Design (MIND) and a Surrogate-Assisted Inverse Loop (SAIL). First, OneDSE-MIND inverts the prevailing recipe: conditioned on the"},"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":"2505.03771","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-04-29T19:19:52Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"3f12eb98b5a0500cc24851d6c3dbe23810b422cbb295ca09b6009f12fbd60627","abstract_canon_sha256":"5e5234e7d84888cf1187267cb0aea8c05d8a1f02fa3af719a18c9a15927e9c6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-19T00:26:08.404766Z","signature_b64":"7O76tpVHIPcOADgOqrYbIgRIrDfPt1WXia2C9AtcTSTwyDyYBmnRFcPDHmR6jC4xPvKt9EjeLbU51TyPwiZ2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79ca8a142e7238d47829b8f9ddf6422f018b39c0531c483c252fb0ea8a8aff8d","last_reissued_at":"2026-08-19T00:26:08.402106Z","signature_status":"signed_v1","first_computed_at":"2026-08-19T00:26:08.402106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OneDSE: Metric-Conditioned Inverse Modeling and Active Search for Sample-Efficient DSE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AR","authors_text":"Akshat Ramachandran, Danny Samuel, Jeff Nye, Ritik Raj, Shashank Nemawarkar, Tushar Krishna","submitted_at":"2025-04-29T19:19:52Z","abstract_excerpt":"We identify two key challenges in prior CPU design space exploration (DSE) approaches: (a) short-horizon prediction is forward-only: modeling PPA metrics from design parameters while designers start from metric targets, and (b) long-horizon exploration is slow: evaluating thousands of candidates on cycle-accurate simulators. This work presents OneDSE, which unifies short-horizon design prediction and long-horizon design optimization through Metric-conditioned INverse Design (MIND) and a Surrogate-Assisted Inverse Loop (SAIL). First, OneDSE-MIND inverts the prevailing recipe: conditioned on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03771","kind":"arxiv","version":3},"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/2505.03771/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":"2505.03771","created_at":"2026-08-19T00:26:08.402978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03771v3","created_at":"2026-08-19T00:26:08.402978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03771","created_at":"2026-08-19T00:26:08.402978+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHFIUFBOOI4N","created_at":"2026-08-19T00:26:08.402978+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHFIUFBOOI4NI6BJ","created_at":"2026-08-19T00:26:08.402978+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHFIUFBO","created_at":"2026-08-19T00:26:08.402978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01041","citing_title":"On the Limits of Machine-Learned Ranking for Modern Microarchitectural Policies","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4","json":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4.json","graph_json":"https://pith.science/api/pith-number/PHFIUFBOOI4NI6BJXD4535SCF4/graph.json","events_json":"https://pith.science/api/pith-number/PHFIUFBOOI4NI6BJXD4535SCF4/events.json","paper":"https://pith.science/paper/PHFIUFBO"},"agent_actions":{"view_html":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4","download_json":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4.json","view_paper":"https://pith.science/paper/PHFIUFBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03771&json=true","fetch_graph":"https://pith.science/api/pith-number/PHFIUFBOOI4NI6BJXD4535SCF4/graph.json","fetch_events":"https://pith.science/api/pith-number/PHFIUFBOOI4NI6BJXD4535SCF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4/action/storage_attestation","attest_author":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4/action/author_attestation","sign_citation":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4/action/citation_signature","submit_replication":"https://pith.science/pith/PHFIUFBOOI4NI6BJXD4535SCF4/action/replication_record"}},"created_at":"2026-08-19T00:26:08.402978+00:00","updated_at":"2026-08-19T00:26:08.402978+00:00"}