{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:J5RYOZSI43V2YWPWUPTYMFNVNQ","short_pith_number":"pith:J5RYOZSI","schema_version":"1.0","canonical_sha256":"4f63876648e6ebac59f6a3e78615b56c36ec7d261cc017ffea31c42f49c36bc8","source":{"kind":"arxiv","id":"1408.6804","version":2},"attestation_state":"computed","paper":{"title":"A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs with a Costly max-Oracle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christoph H. Lampert, Neel Shah, Vladimir Kolmogorov","submitted_at":"2014-08-28T18:38:24Z","abstract_excerpt":"Structural support vector machines (SSVMs) are amongst the best performing models for structured computer vision tasks, such as semantic image segmentation or human pose estimation. Training SSVMs, however, is computationally costly, because it requires repeated calls to a structured prediction subroutine (called \\emph{max-oracle}), which has to solve an optimization problem itself, e.g. a graph cut.\n  In this work, we introduce a new algorithm for SSVM training that is more efficient than earlier techniques when the max-oracle is computationally expensive, as it is frequently the case in comp"},"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":"1408.6804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-08-28T18:38:24Z","cross_cats_sorted":[],"title_canon_sha256":"107c4bb95939445bcf33563397a405357c6bb48746208a3032989f5d2d531c74","abstract_canon_sha256":"5b36008970c99c3d987a76678470cffd650d9181099d130ac3e79d55e9f2942b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:34:51.818912Z","signature_b64":"ismSHiP1B5Ce0ltEt3Is6CjdvOXWxKuGf9L07YZArvNpyWbiImZ2LjGZyViVrHcizxIGejVuiTML69WPU2Z9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f63876648e6ebac59f6a3e78615b56c36ec7d261cc017ffea31c42f49c36bc8","last_reissued_at":"2026-05-18T02:34:51.818572Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:34:51.818572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs with a Costly max-Oracle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christoph H. Lampert, Neel Shah, Vladimir Kolmogorov","submitted_at":"2014-08-28T18:38:24Z","abstract_excerpt":"Structural support vector machines (SSVMs) are amongst the best performing models for structured computer vision tasks, such as semantic image segmentation or human pose estimation. Training SSVMs, however, is computationally costly, because it requires repeated calls to a structured prediction subroutine (called \\emph{max-oracle}), which has to solve an optimization problem itself, e.g. a graph cut.\n  In this work, we introduce a new algorithm for SSVM training that is more efficient than earlier techniques when the max-oracle is computationally expensive, as it is frequently the case in comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.6804","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":""},"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":"1408.6804","created_at":"2026-05-18T02:34:51.818627+00:00"},{"alias_kind":"arxiv_version","alias_value":"1408.6804v2","created_at":"2026-05-18T02:34:51.818627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.6804","created_at":"2026-05-18T02:34:51.818627+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5RYOZSI43V2","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5RYOZSI43V2YWPW","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5RYOZSI","created_at":"2026-05-18T12:28:33.132498+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/J5RYOZSI43V2YWPWUPTYMFNVNQ","json":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ.json","graph_json":"https://pith.science/api/pith-number/J5RYOZSI43V2YWPWUPTYMFNVNQ/graph.json","events_json":"https://pith.science/api/pith-number/J5RYOZSI43V2YWPWUPTYMFNVNQ/events.json","paper":"https://pith.science/paper/J5RYOZSI"},"agent_actions":{"view_html":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ","download_json":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ.json","view_paper":"https://pith.science/paper/J5RYOZSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1408.6804&json=true","fetch_graph":"https://pith.science/api/pith-number/J5RYOZSI43V2YWPWUPTYMFNVNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/J5RYOZSI43V2YWPWUPTYMFNVNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ/action/storage_attestation","attest_author":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ/action/author_attestation","sign_citation":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ/action/citation_signature","submit_replication":"https://pith.science/pith/J5RYOZSI43V2YWPWUPTYMFNVNQ/action/replication_record"}},"created_at":"2026-05-18T02:34:51.818627+00:00","updated_at":"2026-05-18T02:34:51.818627+00:00"}