{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:65MXASHB3TACD27X4IW6EKEKNH","short_pith_number":"pith:65MXASHB","schema_version":"1.0","canonical_sha256":"f7597048e1dcc021ebf7e22de2288a69e685285786f649f9f23bffdd0294554b","source":{"kind":"arxiv","id":"1106.1925","version":2},"attestation_state":"computed","paper":{"title":"Ranking via Sinkhorn Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Richard S. Zemel, Ryan Prescott Adams","submitted_at":"2011-06-09T21:57:27Z","abstract_excerpt":"It is of increasing importance to develop learning methods for ranking. In contrast to many learning objectives, however, the ranking problem presents difficulties due to the fact that the space of permutations is not smooth. In this paper, we examine the class of rank-linear objective functions, which includes popular metrics such as precision and discounted cumulative gain. In particular, we observe that expectations of these gains are completely characterized by the marginals of the corresponding distribution over permutation matrices. Thus, the expectations of rank-linear objectives can al"},"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":"1106.1925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2011-06-09T21:57:27Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"05edb412789eaaa9f40e3555fb065d050219a7d5ebc7f8679cf53a909b44f254","abstract_canon_sha256":"d6bae270924daa434eee53a4be65a522790f4b560cb1292532004f1893800e5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:20:05.444262Z","signature_b64":"tMmecNu7DpPtH89sspaJsgwtZkinfxzN5udq2EdkQznVPCTbW8ODpvtNgcjTCNY2j7nUx4Oxvi4BBjPUqrfaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7597048e1dcc021ebf7e22de2288a69e685285786f649f9f23bffdd0294554b","last_reissued_at":"2026-05-18T04:20:05.443667Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:20:05.443667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ranking via Sinkhorn Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Richard S. Zemel, Ryan Prescott Adams","submitted_at":"2011-06-09T21:57:27Z","abstract_excerpt":"It is of increasing importance to develop learning methods for ranking. In contrast to many learning objectives, however, the ranking problem presents difficulties due to the fact that the space of permutations is not smooth. In this paper, we examine the class of rank-linear objective functions, which includes popular metrics such as precision and discounted cumulative gain. In particular, we observe that expectations of these gains are completely characterized by the marginals of the corresponding distribution over permutation matrices. Thus, the expectations of rank-linear objectives can al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.1925","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":"1106.1925","created_at":"2026-05-18T04:20:05.443766+00:00"},{"alias_kind":"arxiv_version","alias_value":"1106.1925v2","created_at":"2026-05-18T04:20:05.443766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.1925","created_at":"2026-05-18T04:20:05.443766+00:00"},{"alias_kind":"pith_short_12","alias_value":"65MXASHB3TAC","created_at":"2026-05-18T12:26:22.705136+00:00"},{"alias_kind":"pith_short_16","alias_value":"65MXASHB3TACD27X","created_at":"2026-05-18T12:26:22.705136+00:00"},{"alias_kind":"pith_short_8","alias_value":"65MXASHB","created_at":"2026-05-18T12:26:22.705136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13690","citing_title":"The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05330","citing_title":"Graph Normalization: Fast Binarizing Dynamics for Differentiable MWIS","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH","json":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH.json","graph_json":"https://pith.science/api/pith-number/65MXASHB3TACD27X4IW6EKEKNH/graph.json","events_json":"https://pith.science/api/pith-number/65MXASHB3TACD27X4IW6EKEKNH/events.json","paper":"https://pith.science/paper/65MXASHB"},"agent_actions":{"view_html":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH","download_json":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH.json","view_paper":"https://pith.science/paper/65MXASHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1106.1925&json=true","fetch_graph":"https://pith.science/api/pith-number/65MXASHB3TACD27X4IW6EKEKNH/graph.json","fetch_events":"https://pith.science/api/pith-number/65MXASHB3TACD27X4IW6EKEKNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH/action/storage_attestation","attest_author":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH/action/author_attestation","sign_citation":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH/action/citation_signature","submit_replication":"https://pith.science/pith/65MXASHB3TACD27X4IW6EKEKNH/action/replication_record"}},"created_at":"2026-05-18T04:20:05.443766+00:00","updated_at":"2026-05-18T04:20:05.443766+00:00"}