{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:P54LMKURM4J2CBA4ZNACN747RE","short_pith_number":"pith:P54LMKUR","schema_version":"1.0","canonical_sha256":"7f78b62a916713a1041ccb4026ff9f8934fd306d7d40c32de380ae14ddac612d","source":{"kind":"arxiv","id":"1905.02494","version":4},"attestation_state":"computed","paper":{"title":"Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Paliwal, Felix Gimeno, Miles Lubin, Oriol Vinyals, Pushmeet Kohli, Vinod Nair, Yujia Li","submitted_at":"2019-05-07T12:15:06Z","abstract_excerpt":"We present a deep reinforcement learning approach to minimizing the execution cost of neural network computation graphs in an optimizing compiler. Unlike earlier learning-based works that require training the optimizer on the same graph to be optimized, we propose a learning approach that trains an optimizer offline and then generalizes to previously unseen graphs without further training. This allows our approach to produce high-quality execution decisions on real-world TensorFlow graphs in seconds instead of hours. We consider two optimization tasks for computation graphs: minimizing running"},"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":"1905.02494","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-07T12:15:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"09afb894b02133fe871fbd0a65087dc35766b0c07824a67de414ca9b39a6aac9","abstract_canon_sha256":"b575d3b254a22c2a38d1883988c6b18269d56df25a1bd36aed0aa6b4f9ddccde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:11.566408Z","signature_b64":"gJs4jigigRzK1eudrJsHWnqzmCr5X6ou0ifPfqz/QE+zbp6miTDFOo45X7BrSEpf3qKZw7Xs2fQEXLCDIYZ1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f78b62a916713a1041ccb4026ff9f8934fd306d7d40c32de380ae14ddac612d","last_reissued_at":"2026-07-05T00:39:11.565852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:11.565852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Paliwal, Felix Gimeno, Miles Lubin, Oriol Vinyals, Pushmeet Kohli, Vinod Nair, Yujia Li","submitted_at":"2019-05-07T12:15:06Z","abstract_excerpt":"We present a deep reinforcement learning approach to minimizing the execution cost of neural network computation graphs in an optimizing compiler. Unlike earlier learning-based works that require training the optimizer on the same graph to be optimized, we propose a learning approach that trains an optimizer offline and then generalizes to previously unseen graphs without further training. This allows our approach to produce high-quality execution decisions on real-world TensorFlow graphs in seconds instead of hours. We consider two optimization tasks for computation graphs: minimizing running"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02494","kind":"arxiv","version":4},"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/1905.02494/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":"1905.02494","created_at":"2026-07-05T00:39:11.565909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02494v4","created_at":"2026-07-05T00:39:11.565909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02494","created_at":"2026-07-05T00:39:11.565909+00:00"},{"alias_kind":"pith_short_12","alias_value":"P54LMKURM4J2","created_at":"2026-07-05T00:39:11.565909+00:00"},{"alias_kind":"pith_short_16","alias_value":"P54LMKURM4J2CBA4","created_at":"2026-07-05T00:39:11.565909+00:00"},{"alias_kind":"pith_short_8","alias_value":"P54LMKUR","created_at":"2026-07-05T00:39:11.565909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.08879","citing_title":"Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE","json":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE.json","graph_json":"https://pith.science/api/pith-number/P54LMKURM4J2CBA4ZNACN747RE/graph.json","events_json":"https://pith.science/api/pith-number/P54LMKURM4J2CBA4ZNACN747RE/events.json","paper":"https://pith.science/paper/P54LMKUR"},"agent_actions":{"view_html":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE","download_json":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE.json","view_paper":"https://pith.science/paper/P54LMKUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02494&json=true","fetch_graph":"https://pith.science/api/pith-number/P54LMKURM4J2CBA4ZNACN747RE/graph.json","fetch_events":"https://pith.science/api/pith-number/P54LMKURM4J2CBA4ZNACN747RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE/action/storage_attestation","attest_author":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE/action/author_attestation","sign_citation":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE/action/citation_signature","submit_replication":"https://pith.science/pith/P54LMKURM4J2CBA4ZNACN747RE/action/replication_record"}},"created_at":"2026-07-05T00:39:11.565909+00:00","updated_at":"2026-07-05T00:39:11.565909+00:00"}