{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RFYXQ4T35ADQTCTQNPSJZ3FEIC","short_pith_number":"pith:RFYXQ4T3","canonical_record":{"source":{"id":"1811.12776","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-30T13:13:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11e5d0ce67b67e8957ff97eca75048a3905134db17d7cf0cd169f40076a38436","abstract_canon_sha256":"99ed24d193fdf08dc42c5e88e4049d228c4688da05d795c48ea2093744161724"},"schema_version":"1.0"},"canonical_sha256":"897178727be807098a706be49ceca4409f93f4c043945ed26b62dfff674014e4","source":{"kind":"arxiv","id":"1811.12776","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12776","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12776v2","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12776","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"RFYXQ4T35ADQ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RFYXQ4T35ADQTCTQ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RFYXQ4T3","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RFYXQ4T35ADQTCTQNPSJZ3FEIC","target":"record","payload":{"canonical_record":{"source":{"id":"1811.12776","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-30T13:13:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11e5d0ce67b67e8957ff97eca75048a3905134db17d7cf0cd169f40076a38436","abstract_canon_sha256":"99ed24d193fdf08dc42c5e88e4049d228c4688da05d795c48ea2093744161724"},"schema_version":"1.0"},"canonical_sha256":"897178727be807098a706be49ceca4409f93f4c043945ed26b62dfff674014e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:21.903889Z","signature_b64":"RCvgIz62nl9N3rnmhP/4yTjF749UCx1Z71/PmDfckULu+AIM/xxjacIDmvILwA2dobjpDJEB1bSvMlf9imG8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"897178727be807098a706be49ceca4409f93f4c043945ed26b62dfff674014e4","last_reissued_at":"2026-05-17T23:59:21.903433Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:21.903433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.12776","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3wsCuh4YEQNxYVCNWYbqZcnVxt2XgGayqLeAMlwg07evuEAc5TS0d7GxFs4A42nPiokfLAQ9jrSZmpbq+aQpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:04:24.352643Z"},"content_sha256":"29235c64c24582a446eaf4130140f9bfb5a9a3f14c51b27cde1c3f78f800b5bd","schema_version":"1.0","event_id":"sha256:29235c64c24582a446eaf4130140f9bfb5a9a3f14c51b27cde1c3f78f800b5bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RFYXQ4T35ADQTCTQNPSJZ3FEIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning From Weights: A Cost-Sensitive Approach For Ad Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Nikit Begwani, Rahul Agrawal, Shrutendra Harsola","submitted_at":"2018-11-30T13:13:38Z","abstract_excerpt":"Retrieval models such as CLSM is trained on click-through data which treats each clicked query-document pair as equivalent. While training on click-through data is reasonable, this paper argues that it is sub-optimal because of its noisy and long-tail nature (especially for sponsored search). In this paper, we discuss the impact of incorporating or disregarding the long tail pairs in the training set. Also, we propose a weighing based strategy using which we can learn semantic representations for tail pairs without compromising the quality of retrieval. We conducted our experiments on Bing spo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12776","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xyA82N8jZav1vBayhqDrKdknSE2oxOgoKwHtzku/+tB60df8g1s28776cNVg/o7yQ9u9On75CbQZXRiaS1FgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:04:24.352992Z"},"content_sha256":"14c62827e0941f1aaa37cf32946e5c1ae938098e81e47118997b66c74b443c0e","schema_version":"1.0","event_id":"sha256:14c62827e0941f1aaa37cf32946e5c1ae938098e81e47118997b66c74b443c0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/bundle.json","state_url":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T20:04:24Z","links":{"resolver":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC","bundle":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/bundle.json","state":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RFYXQ4T35ADQTCTQNPSJZ3FEIC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"99ed24d193fdf08dc42c5e88e4049d228c4688da05d795c48ea2093744161724","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-30T13:13:38Z","title_canon_sha256":"11e5d0ce67b67e8957ff97eca75048a3905134db17d7cf0cd169f40076a38436"},"schema_version":"1.0","source":{"id":"1811.12776","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12776","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12776v2","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12776","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"RFYXQ4T35ADQ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RFYXQ4T35ADQTCTQ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RFYXQ4T3","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:14c62827e0941f1aaa37cf32946e5c1ae938098e81e47118997b66c74b443c0e","target":"graph","created_at":"2026-05-17T23:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Retrieval models such as CLSM is trained on click-through data which treats each clicked query-document pair as equivalent. While training on click-through data is reasonable, this paper argues that it is sub-optimal because of its noisy and long-tail nature (especially for sponsored search). In this paper, we discuss the impact of incorporating or disregarding the long tail pairs in the training set. Also, we propose a weighing based strategy using which we can learn semantic representations for tail pairs without compromising the quality of retrieval. We conducted our experiments on Bing spo","authors_text":"Nikit Begwani, Rahul Agrawal, Shrutendra Harsola","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-30T13:13:38Z","title":"Learning From Weights: A Cost-Sensitive Approach For Ad Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12776","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:29235c64c24582a446eaf4130140f9bfb5a9a3f14c51b27cde1c3f78f800b5bd","target":"record","created_at":"2026-05-17T23:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"99ed24d193fdf08dc42c5e88e4049d228c4688da05d795c48ea2093744161724","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-30T13:13:38Z","title_canon_sha256":"11e5d0ce67b67e8957ff97eca75048a3905134db17d7cf0cd169f40076a38436"},"schema_version":"1.0","source":{"id":"1811.12776","kind":"arxiv","version":2}},"canonical_sha256":"897178727be807098a706be49ceca4409f93f4c043945ed26b62dfff674014e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"897178727be807098a706be49ceca4409f93f4c043945ed26b62dfff674014e4","first_computed_at":"2026-05-17T23:59:21.903433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:21.903433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RCvgIz62nl9N3rnmhP/4yTjF749UCx1Z71/PmDfckULu+AIM/xxjacIDmvILwA2dobjpDJEB1bSvMlf9imG8DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:21.903889Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.12776","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29235c64c24582a446eaf4130140f9bfb5a9a3f14c51b27cde1c3f78f800b5bd","sha256:14c62827e0941f1aaa37cf32946e5c1ae938098e81e47118997b66c74b443c0e"],"state_sha256":"47a12ac19d5b0824282611f0f5f8ce3ff5eaebe9cf9b8f49c1bfdcddf636c208"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7KJjGEm5mUC9lu8lbBkUQBGYGH7M+xeyRedIULfXN63dcwdGZEO3+A2JdBVmAOufjjXx1KzwvAQohUL+bErCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:04:24.354994Z","bundle_sha256":"ed05181f9d7084aeac359dfa1a1dd16f4c72df7210844749f0cd2dfcef765bd4"}}