{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ECHMLO6VRVYPOSZJWWRT3ANLTZ","short_pith_number":"pith:ECHMLO6V","schema_version":"1.0","canonical_sha256":"208ec5bbd58d70f74b29b5a33d81ab9e6f917ddff29caae188cf07ffb7b4abe0","source":{"kind":"arxiv","id":"2503.09357","version":1},"attestation_state":"computed","paper":{"title":"Automatic Operator-level Parallelism Planning for Distributed Deep Learning -- A Mixed-Integer Programming Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.DM"],"primary_cat":"cs.LG","authors_text":"Bowen Pang, Kai Li, Ruifeng She, Tao Zhong, Zehua Liu","submitted_at":"2025-03-12T13:00:29Z","abstract_excerpt":"As the artificial intelligence community advances into the era of large models with billions of parameters, distributed training and inference have become essential. While various parallelism strategies-data, model, sequence, and pipeline-have been successfully implemented for popular neural networks on main-stream hardware, optimizing the distributed deployment schedule requires extensive expertise and manual effort. Further more, while existing frameworks with most simple chain-like structures, they struggle with complex non-linear architectures. Mixture-of-experts and multi-modal models fea"},"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":"2503.09357","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T13:00:29Z","cross_cats_sorted":["cs.AI","cs.DC","cs.DM"],"title_canon_sha256":"17dc53bebb85ea07250d62e6c7fe22e99ecc2b88a16779cec4274a2c817ede18","abstract_canon_sha256":"517f385867564cbca13076d385819e6bca1baca7d4fa4fcb4d27fa335536c33d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:54.694207Z","signature_b64":"tUs5UsKSTLH8JlP22il0TW3FkCh2iXcn1/JXcb1K6Zau3laCKJcNCC72ty9o7igkMcRT0p/HOKPYCRcfbY+JDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"208ec5bbd58d70f74b29b5a33d81ab9e6f917ddff29caae188cf07ffb7b4abe0","last_reissued_at":"2026-07-05T10:29:54.693604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:54.693604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Operator-level Parallelism Planning for Distributed Deep Learning -- A Mixed-Integer Programming Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.DM"],"primary_cat":"cs.LG","authors_text":"Bowen Pang, Kai Li, Ruifeng She, Tao Zhong, Zehua Liu","submitted_at":"2025-03-12T13:00:29Z","abstract_excerpt":"As the artificial intelligence community advances into the era of large models with billions of parameters, distributed training and inference have become essential. While various parallelism strategies-data, model, sequence, and pipeline-have been successfully implemented for popular neural networks on main-stream hardware, optimizing the distributed deployment schedule requires extensive expertise and manual effort. Further more, while existing frameworks with most simple chain-like structures, they struggle with complex non-linear architectures. Mixture-of-experts and multi-modal models fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09357","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.09357/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":"2503.09357","created_at":"2026-07-05T10:29:54.693690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09357v1","created_at":"2026-07-05T10:29:54.693690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09357","created_at":"2026-07-05T10:29:54.693690+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECHMLO6VRVYP","created_at":"2026-07-05T10:29:54.693690+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECHMLO6VRVYPOSZJ","created_at":"2026-07-05T10:29:54.693690+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECHMLO6V","created_at":"2026-07-05T10:29:54.693690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19654","citing_title":"FEPLB: Exploiting Copy Engines for Nearly Free MoE Load Balancing in Distributed Training","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ","json":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ.json","graph_json":"https://pith.science/api/pith-number/ECHMLO6VRVYPOSZJWWRT3ANLTZ/graph.json","events_json":"https://pith.science/api/pith-number/ECHMLO6VRVYPOSZJWWRT3ANLTZ/events.json","paper":"https://pith.science/paper/ECHMLO6V"},"agent_actions":{"view_html":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ","download_json":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ.json","view_paper":"https://pith.science/paper/ECHMLO6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09357&json=true","fetch_graph":"https://pith.science/api/pith-number/ECHMLO6VRVYPOSZJWWRT3ANLTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ECHMLO6VRVYPOSZJWWRT3ANLTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ/action/storage_attestation","attest_author":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ/action/author_attestation","sign_citation":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ/action/citation_signature","submit_replication":"https://pith.science/pith/ECHMLO6VRVYPOSZJWWRT3ANLTZ/action/replication_record"}},"created_at":"2026-07-05T10:29:54.693690+00:00","updated_at":"2026-07-05T10:29:54.693690+00:00"}