{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DXGSRSGYL3TSUXF6SNLHVW33W2","short_pith_number":"pith:DXGSRSGY","schema_version":"1.0","canonical_sha256":"1dcd28c8d85ee72a5cbe93567adb7bb6bbe41cfbbd99491b66e3dbc73845024c","source":{"kind":"arxiv","id":"1903.00614","version":1},"attestation_state":"computed","paper":{"title":"GAP: Generalizable Approximate Graph Partitioning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Goldie, Azade Nazi, Azalia Mirhoseini, Sujith Ravi, Will Hang","submitted_at":"2019-03-02T03:06:00Z","abstract_excerpt":"Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions. Due to its combinatorial nature, many approximate solutions have been developed, including variants of multi-level methods and spectral clustering. We propose GAP, a Generalizable Approximate Partitioning framework that takes a deep learning approach to graph partitioning. We define a differentiable loss function that represents the partitioning objective and use backpropagation to optimize the network parameters. Unlike baselines that redo the optimi"},"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":"1903.00614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-02T03:06:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2a0e925ceca89a93cd8c92478def9a8ee7526f4a34c7cd50e3fe47d4a3fa5a56","abstract_canon_sha256":"3b2953b313f139387fd342e197ba1f4adbaed119ff2feb7329f37cab99cb3202"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:14.009123Z","signature_b64":"NvltzdUCJHxwFLfaiIMYxwJGOMON+KNPYpHgxvEyWo3qHheEBbz+w6wWWSbbcBDa03hc/Mt3ShZ8548cRdOaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dcd28c8d85ee72a5cbe93567adb7bb6bbe41cfbbd99491b66e3dbc73845024c","last_reissued_at":"2026-05-17T23:52:14.008374Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:14.008374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAP: Generalizable Approximate Graph Partitioning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Goldie, Azade Nazi, Azalia Mirhoseini, Sujith Ravi, Will Hang","submitted_at":"2019-03-02T03:06:00Z","abstract_excerpt":"Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions. Due to its combinatorial nature, many approximate solutions have been developed, including variants of multi-level methods and spectral clustering. We propose GAP, a Generalizable Approximate Partitioning framework that takes a deep learning approach to graph partitioning. We define a differentiable loss function that represents the partitioning objective and use backpropagation to optimize the network parameters. Unlike baselines that redo the optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00614","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":""},"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":"1903.00614","created_at":"2026-05-17T23:52:14.008482+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00614v1","created_at":"2026-05-17T23:52:14.008482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00614","created_at":"2026-05-17T23:52:14.008482+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXGSRSGYL3TS","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXGSRSGYL3TSUXF6","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXGSRSGY","created_at":"2026-05-18T12:33:15.570797+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/DXGSRSGYL3TSUXF6SNLHVW33W2","json":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2.json","graph_json":"https://pith.science/api/pith-number/DXGSRSGYL3TSUXF6SNLHVW33W2/graph.json","events_json":"https://pith.science/api/pith-number/DXGSRSGYL3TSUXF6SNLHVW33W2/events.json","paper":"https://pith.science/paper/DXGSRSGY"},"agent_actions":{"view_html":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2","download_json":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2.json","view_paper":"https://pith.science/paper/DXGSRSGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00614&json=true","fetch_graph":"https://pith.science/api/pith-number/DXGSRSGYL3TSUXF6SNLHVW33W2/graph.json","fetch_events":"https://pith.science/api/pith-number/DXGSRSGYL3TSUXF6SNLHVW33W2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2/action/storage_attestation","attest_author":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2/action/author_attestation","sign_citation":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2/action/citation_signature","submit_replication":"https://pith.science/pith/DXGSRSGYL3TSUXF6SNLHVW33W2/action/replication_record"}},"created_at":"2026-05-17T23:52:14.008482+00:00","updated_at":"2026-05-17T23:52:14.008482+00:00"}