{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NF3ZRNFAMB3GDTEZ7T5JTCMMCD","short_pith_number":"pith:NF3ZRNFA","canonical_record":{"source":{"id":"1810.07076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T15:27:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82f6ab7115bc8588af2e5cd1831d4a065d0716163e1010ab5c58d86a2945a929","abstract_canon_sha256":"05acf1bee0431dc42b242246cd9c14109659c0d65154764a7d1bce8e88cfeca5"},"schema_version":"1.0"},"canonical_sha256":"697798b4a0607661cc99fcfa99898c10c81489fb08a39668213dc5259fa3ddf7","source":{"kind":"arxiv","id":"1810.07076","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07076","created_at":"2026-05-18T00:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07076v1","created_at":"2026-05-18T00:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07076","created_at":"2026-05-18T00:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"NF3ZRNFAMB3G","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NF3ZRNFAMB3GDTEZ","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NF3ZRNFA","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NF3ZRNFAMB3GDTEZ7T5JTCMMCD","target":"record","payload":{"canonical_record":{"source":{"id":"1810.07076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T15:27:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82f6ab7115bc8588af2e5cd1831d4a065d0716163e1010ab5c58d86a2945a929","abstract_canon_sha256":"05acf1bee0431dc42b242246cd9c14109659c0d65154764a7d1bce8e88cfeca5"},"schema_version":"1.0"},"canonical_sha256":"697798b4a0607661cc99fcfa99898c10c81489fb08a39668213dc5259fa3ddf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:10.525152Z","signature_b64":"uia7AAEESQp3bMQtV03r3CPLwdXzhM0CYOx1Vq40mGBvjAMObi35nhd0PElZdOCeZPV4lXc+8ky/pS7nH6QqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"697798b4a0607661cc99fcfa99898c10c81489fb08a39668213dc5259fa3ddf7","last_reissued_at":"2026-05-18T00:03:10.524628Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:10.524628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.07076","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZRIf9NXGo4iEFYhCKTKg0FSJ08nlZNblnp4BG4FztpBRluwTqacyFEb9PxzG1idrK9v0VuksNJJKjgq0mnWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:19:13.031473Z"},"content_sha256":"6a7ba3aac6a8df0eb1ed9ecca9359329e9183f3962cad01f71a5250c75bc7898","schema_version":"1.0","event_id":"sha256:6a7ba3aac6a8df0eb1ed9ecca9359329e9183f3962cad01f71a5250c75bc7898"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NF3ZRNFAMB3GDTEZ7T5JTCMMCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Negative Mining for Learning with Large Output Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Holtmann-Rice, Felix Yu, Jiecao Chen, Sanjiv Kumar, Sashank J. Reddi, Satyen Kale","submitted_at":"2018-10-16T15:27:31Z","abstract_excerpt":"We consider the problem of retrieving the most relevant labels for a given input when the size of the output space is very large. Retrieval methods are modeled as set-valued classifiers which output a small set of classes for each input, and a mistake is made if the label is not in the output set. Despite its practical importance, a statistically principled, yet practical solution to this problem is largely missing. To this end, we first define a family of surrogate losses and show that they are calibrated and convex under certain conditions on the loss parameters and data distribution, thereb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07076","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WwwNtRV4YYWj1gmuB2OTj+xp3DtrMuWIGYhoyNSggVVDSTnOPLYetzuBvPBSYX+BRkzjloNj9UXsGuR+vxP4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:19:13.031829Z"},"content_sha256":"3b7b392777d685281cdd2ad9e194666a0f905ed077936c85ec6c12a131653170","schema_version":"1.0","event_id":"sha256:3b7b392777d685281cdd2ad9e194666a0f905ed077936c85ec6c12a131653170"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NF3ZRNFAMB3GDTEZ7T5JTCMMCD/bundle.json","state_url":"https://pith.science/pith/NF3ZRNFAMB3GDTEZ7T5JTCMMCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NF3ZRNFAMB3GDTEZ7T5JTCMMCD/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":"2026-05-28T10:19:13Z","links":{"resolver":"https://pith.science/pith/NF3ZRNFAMB3GDTEZ7T5JTCMMCD","bundle":"https://pith.science/pith/NF3ZRNFAMB3GDTEZ7T5JTCMMCD/bundle.json","state":"https://pith.science/pith/NF3ZRNFAMB3GDTEZ7T5JTCMMCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NF3ZRNFAMB3GDTEZ7T5JTCMMCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NF3ZRNFAMB3GDTEZ7T5JTCMMCD","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":"05acf1bee0431dc42b242246cd9c14109659c0d65154764a7d1bce8e88cfeca5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T15:27:31Z","title_canon_sha256":"82f6ab7115bc8588af2e5cd1831d4a065d0716163e1010ab5c58d86a2945a929"},"schema_version":"1.0","source":{"id":"1810.07076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07076","created_at":"2026-05-18T00:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07076v1","created_at":"2026-05-18T00:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07076","created_at":"2026-05-18T00:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"NF3ZRNFAMB3G","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NF3ZRNFAMB3GDTEZ","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NF3ZRNFA","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:3b7b392777d685281cdd2ad9e194666a0f905ed077936c85ec6c12a131653170","target":"graph","created_at":"2026-05-18T00:03:10Z","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":"We consider the problem of retrieving the most relevant labels for a given input when the size of the output space is very large. Retrieval methods are modeled as set-valued classifiers which output a small set of classes for each input, and a mistake is made if the label is not in the output set. Despite its practical importance, a statistically principled, yet practical solution to this problem is largely missing. To this end, we first define a family of surrogate losses and show that they are calibrated and convex under certain conditions on the loss parameters and data distribution, thereb","authors_text":"Dan Holtmann-Rice, Felix Yu, Jiecao Chen, Sanjiv Kumar, Sashank J. Reddi, Satyen Kale","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T15:27:31Z","title":"Stochastic Negative Mining for Learning with Large Output Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07076","kind":"arxiv","version":1},"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":"sha256:6a7ba3aac6a8df0eb1ed9ecca9359329e9183f3962cad01f71a5250c75bc7898","target":"record","created_at":"2026-05-18T00:03:10Z","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":"05acf1bee0431dc42b242246cd9c14109659c0d65154764a7d1bce8e88cfeca5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T15:27:31Z","title_canon_sha256":"82f6ab7115bc8588af2e5cd1831d4a065d0716163e1010ab5c58d86a2945a929"},"schema_version":"1.0","source":{"id":"1810.07076","kind":"arxiv","version":1}},"canonical_sha256":"697798b4a0607661cc99fcfa99898c10c81489fb08a39668213dc5259fa3ddf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"697798b4a0607661cc99fcfa99898c10c81489fb08a39668213dc5259fa3ddf7","first_computed_at":"2026-05-18T00:03:10.524628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:10.524628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uia7AAEESQp3bMQtV03r3CPLwdXzhM0CYOx1Vq40mGBvjAMObi35nhd0PElZdOCeZPV4lXc+8ky/pS7nH6QqBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:10.525152Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.07076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a7ba3aac6a8df0eb1ed9ecca9359329e9183f3962cad01f71a5250c75bc7898","sha256:3b7b392777d685281cdd2ad9e194666a0f905ed077936c85ec6c12a131653170"],"state_sha256":"77bad8f7673bb8cbf7ce20ab970243a3b1cb9575d52da11f15d53d9ec9ac8375"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yd9wMBWg09pOfs490s211Bu/GqyQ1SNzA4nIOPiiAxkqUGz4HYSpAlWaCxAKLbAG7tGo1vzxCCj4ecxHrMr1AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T10:19:13.033876Z","bundle_sha256":"14a0ab8b72c62b28216bc11b5167fb54d590d324460d802e4ee393376148157e"}}