{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QG3FMHEK5VXN3VR42RJNTWRMHE","short_pith_number":"pith:QG3FMHEK","schema_version":"1.0","canonical_sha256":"81b6561c8aed6eddd63cd452d9da2c39214c5b28f7c290273a3f8094ad29eb09","source":{"kind":"arxiv","id":"2104.13732","version":2},"attestation_state":"computed","paper":{"title":"A Reinforcement Learning Environment for Polyhedral Optimizations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.DM","cs.PF"],"primary_cat":"cs.LG","authors_text":"Alexander Brauckmann, Andr\\'es Goens, Jeronimo Castrillon","submitted_at":"2021-04-28T12:41:52Z","abstract_excerpt":"The polyhedral model allows a structured way of defining semantics-preserving transformations to improve the performance of a large class of loops. Finding profitable points in this space is a hard problem which is usually approached by heuristics that generalize from domain-expert knowledge. Existing problem formulations in state-of-the-art heuristics depend on the shape of particular loops, making it hard to leverage generic and more powerful optimization techniques from the machine learning domain. In this paper, we propose PolyGym, a shape-agnostic formulation for the space of legal transf"},"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":"2104.13732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-28T12:41:52Z","cross_cats_sorted":["cs.DC","cs.DM","cs.PF"],"title_canon_sha256":"eafb971cc01e50af64bea16ff11031085dbaf7f86bebc642e73f61efb93aa224","abstract_canon_sha256":"3728d6fa5a645f7dc12d5bf2991c546b40eb20afcb575e78715102506253604e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:11.285959Z","signature_b64":"Yf7T8n/stsRDRe2VBZcS77RvImXNY54QkLLAcsb4ZzPAS7Mgm75ip8g3Aex2MFPM1VwI4fSOKUxTf6hgjWsABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b6561c8aed6eddd63cd452d9da2c39214c5b28f7c290273a3f8094ad29eb09","last_reissued_at":"2026-07-05T02:36:11.285506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:11.285506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reinforcement Learning Environment for Polyhedral Optimizations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.DM","cs.PF"],"primary_cat":"cs.LG","authors_text":"Alexander Brauckmann, Andr\\'es Goens, Jeronimo Castrillon","submitted_at":"2021-04-28T12:41:52Z","abstract_excerpt":"The polyhedral model allows a structured way of defining semantics-preserving transformations to improve the performance of a large class of loops. Finding profitable points in this space is a hard problem which is usually approached by heuristics that generalize from domain-expert knowledge. Existing problem formulations in state-of-the-art heuristics depend on the shape of particular loops, making it hard to leverage generic and more powerful optimization techniques from the machine learning domain. In this paper, we propose PolyGym, a shape-agnostic formulation for the space of legal transf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13732","kind":"arxiv","version":2},"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/2104.13732/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":"2104.13732","created_at":"2026-07-05T02:36:11.285571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13732v2","created_at":"2026-07-05T02:36:11.285571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13732","created_at":"2026-07-05T02:36:11.285571+00:00"},{"alias_kind":"pith_short_12","alias_value":"QG3FMHEK5VXN","created_at":"2026-07-05T02:36:11.285571+00:00"},{"alias_kind":"pith_short_16","alias_value":"QG3FMHEK5VXN3VR4","created_at":"2026-07-05T02:36:11.285571+00:00"},{"alias_kind":"pith_short_8","alias_value":"QG3FMHEK","created_at":"2026-07-05T02:36:11.285571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04066","citing_title":"DRIVE: Dynamic Rule Inference and Verified Evaluation for Constraint-Aware Autonomous Driving","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE","json":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE.json","graph_json":"https://pith.science/api/pith-number/QG3FMHEK5VXN3VR42RJNTWRMHE/graph.json","events_json":"https://pith.science/api/pith-number/QG3FMHEK5VXN3VR42RJNTWRMHE/events.json","paper":"https://pith.science/paper/QG3FMHEK"},"agent_actions":{"view_html":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE","download_json":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE.json","view_paper":"https://pith.science/paper/QG3FMHEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13732&json=true","fetch_graph":"https://pith.science/api/pith-number/QG3FMHEK5VXN3VR42RJNTWRMHE/graph.json","fetch_events":"https://pith.science/api/pith-number/QG3FMHEK5VXN3VR42RJNTWRMHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE/action/storage_attestation","attest_author":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE/action/author_attestation","sign_citation":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE/action/citation_signature","submit_replication":"https://pith.science/pith/QG3FMHEK5VXN3VR42RJNTWRMHE/action/replication_record"}},"created_at":"2026-07-05T02:36:11.285571+00:00","updated_at":"2026-07-05T02:36:11.285571+00:00"}