{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6OSD447BEGEKN7ZY4AWB4XG5CW","short_pith_number":"pith:6OSD447B","schema_version":"1.0","canonical_sha256":"f3a43e73e12188a6ff38e02c1e5cdd15995858f92a61456146865ea6386d58df","source":{"kind":"arxiv","id":"1812.09737","version":1},"attestation_state":"computed","paper":{"title":"End-to-end Learning for Graph Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bjoern Andres, Jie Song, Michael Black, Otmar Hilliges, Siyu Tang","submitted_at":"2018-12-23T16:21:08Z","abstract_excerpt":"We propose a novel end-to-end trainable framework for the graph decomposition problem. The minimum cost multicut problem is first converted to an unconstrained binary cubic formulation where cycle consistency constraints are incorporated into the objective function. The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials. The parameters of a standard Neural Network and the fully differentiable CRF are op"},"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":"1812.09737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-23T16:21:08Z","cross_cats_sorted":[],"title_canon_sha256":"16b30d44c8b0eba4f789834ea0a40af3f44e844568a822f0091d604c0899e97c","abstract_canon_sha256":"2fe2b809117b13d83fe6829a90e676b151af307c7c482df5c00232ec17a512c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:26.938827Z","signature_b64":"Zgfdj0wCl2JZSoqekQdHsGcaAP3TvJ/HiybenMhZMe5fr4G+uQy9FvmK+ouQC3Z5gL24GgoIVPa9TV+Z8TSbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3a43e73e12188a6ff38e02c1e5cdd15995858f92a61456146865ea6386d58df","last_reissued_at":"2026-05-17T23:57:26.938076Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:26.938076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Learning for Graph Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bjoern Andres, Jie Song, Michael Black, Otmar Hilliges, Siyu Tang","submitted_at":"2018-12-23T16:21:08Z","abstract_excerpt":"We propose a novel end-to-end trainable framework for the graph decomposition problem. The minimum cost multicut problem is first converted to an unconstrained binary cubic formulation where cycle consistency constraints are incorporated into the objective function. The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials. The parameters of a standard Neural Network and the fully differentiable CRF are op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09737","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":"1812.09737","created_at":"2026-05-17T23:57:26.938203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.09737v1","created_at":"2026-05-17T23:57:26.938203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09737","created_at":"2026-05-17T23:57:26.938203+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OSD447BEGEK","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OSD447BEGEKN7ZY","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OSD447B","created_at":"2026-05-18T12:32:11.075285+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/6OSD447BEGEKN7ZY4AWB4XG5CW","json":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW.json","graph_json":"https://pith.science/api/pith-number/6OSD447BEGEKN7ZY4AWB4XG5CW/graph.json","events_json":"https://pith.science/api/pith-number/6OSD447BEGEKN7ZY4AWB4XG5CW/events.json","paper":"https://pith.science/paper/6OSD447B"},"agent_actions":{"view_html":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW","download_json":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW.json","view_paper":"https://pith.science/paper/6OSD447B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.09737&json=true","fetch_graph":"https://pith.science/api/pith-number/6OSD447BEGEKN7ZY4AWB4XG5CW/graph.json","fetch_events":"https://pith.science/api/pith-number/6OSD447BEGEKN7ZY4AWB4XG5CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW/action/storage_attestation","attest_author":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW/action/author_attestation","sign_citation":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW/action/citation_signature","submit_replication":"https://pith.science/pith/6OSD447BEGEKN7ZY4AWB4XG5CW/action/replication_record"}},"created_at":"2026-05-17T23:57:26.938203+00:00","updated_at":"2026-05-17T23:57:26.938203+00:00"}