{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MJYS7B4RMN73ZWA67VNL2L7Y46","short_pith_number":"pith:MJYS7B4R","schema_version":"1.0","canonical_sha256":"62712f8791637fbcd81efd5abd2ff8e7894dfb6f387185ec14f7b58f590b7b0c","source":{"kind":"arxiv","id":"1611.07573","version":1},"attestation_state":"computed","paper":{"title":"Relaxed Earth Mover's Distances for Chain- and Tree-connected Spaces and their use as a Loss Function in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Makarand Tapaswi, Manuel Martinez, Monica Haurilet, Rainer Stiefelhagen, Ziad Al-Halah","submitted_at":"2016-11-22T22:54:05Z","abstract_excerpt":"The Earth Mover's Distance (EMD) computes the optimal cost of transforming one distribution into another, given a known transport metric between them. In deep learning, the EMD loss allows us to embed information during training about the output space structure like hierarchical or semantic relations. This helps in achieving better output smoothness and generalization. However EMD is computationally expensive.Moreover, solving EMD optimization problems usually require complex techniques like lasso. These properties limit the applicability of EMD-based approaches in large scale machine learning"},"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":"1611.07573","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-22T22:54:05Z","cross_cats_sorted":[],"title_canon_sha256":"e19165cab6f4de22ec3dbc4b75e955eddf9ef5740cf9cae727b42da2aba2ed27","abstract_canon_sha256":"5da60f3fa4daa498f094ebe4bd59689d0fa51711b3a7674dbcde242740ce0fe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:00.446696Z","signature_b64":"PVlH0nLBkHS/bJBb5PnrgZhLOoKQxwTCxqGf2iPrKgqhJYUYpyIYyEf/xEA2TL+EJZP+2by5X1yPYK1mOm3vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62712f8791637fbcd81efd5abd2ff8e7894dfb6f387185ec14f7b58f590b7b0c","last_reissued_at":"2026-05-18T00:57:00.446174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:00.446174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relaxed Earth Mover's Distances for Chain- and Tree-connected Spaces and their use as a Loss Function in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Makarand Tapaswi, Manuel Martinez, Monica Haurilet, Rainer Stiefelhagen, Ziad Al-Halah","submitted_at":"2016-11-22T22:54:05Z","abstract_excerpt":"The Earth Mover's Distance (EMD) computes the optimal cost of transforming one distribution into another, given a known transport metric between them. In deep learning, the EMD loss allows us to embed information during training about the output space structure like hierarchical or semantic relations. This helps in achieving better output smoothness and generalization. However EMD is computationally expensive.Moreover, solving EMD optimization problems usually require complex techniques like lasso. These properties limit the applicability of EMD-based approaches in large scale machine learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07573","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":"1611.07573","created_at":"2026-05-18T00:57:00.446251+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.07573v1","created_at":"2026-05-18T00:57:00.446251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07573","created_at":"2026-05-18T00:57:00.446251+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJYS7B4RMN73","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJYS7B4RMN73ZWA6","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJYS7B4R","created_at":"2026-05-18T12:30:32.724797+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/MJYS7B4RMN73ZWA67VNL2L7Y46","json":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46.json","graph_json":"https://pith.science/api/pith-number/MJYS7B4RMN73ZWA67VNL2L7Y46/graph.json","events_json":"https://pith.science/api/pith-number/MJYS7B4RMN73ZWA67VNL2L7Y46/events.json","paper":"https://pith.science/paper/MJYS7B4R"},"agent_actions":{"view_html":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46","download_json":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46.json","view_paper":"https://pith.science/paper/MJYS7B4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.07573&json=true","fetch_graph":"https://pith.science/api/pith-number/MJYS7B4RMN73ZWA67VNL2L7Y46/graph.json","fetch_events":"https://pith.science/api/pith-number/MJYS7B4RMN73ZWA67VNL2L7Y46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46/action/storage_attestation","attest_author":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46/action/author_attestation","sign_citation":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46/action/citation_signature","submit_replication":"https://pith.science/pith/MJYS7B4RMN73ZWA67VNL2L7Y46/action/replication_record"}},"created_at":"2026-05-18T00:57:00.446251+00:00","updated_at":"2026-05-18T00:57:00.446251+00:00"}