{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4MEEAFT2ONZB54Y4OKD25OOXAI","short_pith_number":"pith:4MEEAFT2","canonical_record":{"source":{"id":"1709.05976","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T14:34:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f74cde13c98c2fd1aaa47f5e7a816695447f66a358b40f156bcd8dda3ccbfb02","abstract_canon_sha256":"a6835071fafd6273c7eb83edd217c047a9388e7d92c2c9676c58b870b42cc1dc"},"schema_version":"1.0"},"canonical_sha256":"e30840167a73721ef31c7287aeb9d7020d916e3da87ed0379050d5652223f939","source":{"kind":"arxiv","id":"1709.05976","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.05976","created_at":"2026-05-18T00:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"1709.05976v3","created_at":"2026-05-18T00:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05976","created_at":"2026-05-18T00:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"4MEEAFT2ONZB","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4MEEAFT2ONZB54Y4","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4MEEAFT2","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4MEEAFT2ONZB54Y4OKD25OOXAI","target":"record","payload":{"canonical_record":{"source":{"id":"1709.05976","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T14:34:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f74cde13c98c2fd1aaa47f5e7a816695447f66a358b40f156bcd8dda3ccbfb02","abstract_canon_sha256":"a6835071fafd6273c7eb83edd217c047a9388e7d92c2c9676c58b870b42cc1dc"},"schema_version":"1.0"},"canonical_sha256":"e30840167a73721ef31c7287aeb9d7020d916e3da87ed0379050d5652223f939","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:54.602662Z","signature_b64":"q4luWun1KOqkyIHwpZk7dYkbfCvnotudl++xUQS8ovwcB1/9tw24sj39qV6TN3xJP3vg/dWpRKvMUHJ6WFdWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e30840167a73721ef31c7287aeb9d7020d916e3da87ed0379050d5652223f939","last_reissued_at":"2026-05-18T00:30:54.602109Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:54.602109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.05976","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8Amp0XbqoByJXGhPfh7OjTVxhgedgi1VbJJbAiSA8ks55ZKWghMNne00vgMA/5QebB8Ls/O5YrLsENOa4HWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:14:57.408136Z"},"content_sha256":"5dd4f8e3a0d26efe9050aed59b94a72383c725a0111e79ff7d363df1e43f1788","schema_version":"1.0","event_id":"sha256:5dd4f8e3a0d26efe9050aed59b94a72383c725a0111e79ff7d363df1e43f1788"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4MEEAFT2ONZB54Y4OKD25OOXAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Distributional Semantics for Multi-Label Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Harish Karnick, Nagarajan Natarajan, Piyush Rai, Prateek Jain, Rahul Wadbude, Vivek Gupta","submitted_at":"2017-09-18T14:34:16Z","abstract_excerpt":"We present a novel and scalable label embedding framework for large-scale multi-label learning a.k.a ExMLDS (Extreme Multi-Label Learning using Distributional Semantics). Our approach draws inspiration from ideas rooted in distributional semantics, specifically the Skip Gram Negative Sampling (SGNS) approach, widely used to learn word embeddings for natural language processing tasks. Learning such embeddings can be reduced to a certain matrix factorization. Our approach is novel in that it highlights interesting connections between label embedding methods used for multi-label learning and para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05976","kind":"arxiv","version":3},"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":"2026-05-18T00:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XfO1u+Ywz5orLAx88iN/KVW+B/3KVMiO7cuHwEgY2mOD2LPLHUq9Oty3i1XFfBA9OG+yt5j+ihhv5fetmrjrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:14:57.408497Z"},"content_sha256":"ea9baef6523c4202a30ca7ea8bab07532150e07d3476c7c15bf948ea876ff67c","schema_version":"1.0","event_id":"sha256:ea9baef6523c4202a30ca7ea8bab07532150e07d3476c7c15bf948ea876ff67c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4MEEAFT2ONZB54Y4OKD25OOXAI/bundle.json","state_url":"https://pith.science/pith/4MEEAFT2ONZB54Y4OKD25OOXAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4MEEAFT2ONZB54Y4OKD25OOXAI/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":"2026-06-01T16:14:57Z","links":{"resolver":"https://pith.science/pith/4MEEAFT2ONZB54Y4OKD25OOXAI","bundle":"https://pith.science/pith/4MEEAFT2ONZB54Y4OKD25OOXAI/bundle.json","state":"https://pith.science/pith/4MEEAFT2ONZB54Y4OKD25OOXAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4MEEAFT2ONZB54Y4OKD25OOXAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4MEEAFT2ONZB54Y4OKD25OOXAI","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":"a6835071fafd6273c7eb83edd217c047a9388e7d92c2c9676c58b870b42cc1dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T14:34:16Z","title_canon_sha256":"f74cde13c98c2fd1aaa47f5e7a816695447f66a358b40f156bcd8dda3ccbfb02"},"schema_version":"1.0","source":{"id":"1709.05976","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.05976","created_at":"2026-05-18T00:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"1709.05976v3","created_at":"2026-05-18T00:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05976","created_at":"2026-05-18T00:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"4MEEAFT2ONZB","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4MEEAFT2ONZB54Y4","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4MEEAFT2","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:ea9baef6523c4202a30ca7ea8bab07532150e07d3476c7c15bf948ea876ff67c","target":"graph","created_at":"2026-05-18T00:30:54Z","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 present a novel and scalable label embedding framework for large-scale multi-label learning a.k.a ExMLDS (Extreme Multi-Label Learning using Distributional Semantics). Our approach draws inspiration from ideas rooted in distributional semantics, specifically the Skip Gram Negative Sampling (SGNS) approach, widely used to learn word embeddings for natural language processing tasks. Learning such embeddings can be reduced to a certain matrix factorization. Our approach is novel in that it highlights interesting connections between label embedding methods used for multi-label learning and para","authors_text":"Harish Karnick, Nagarajan Natarajan, Piyush Rai, Prateek Jain, Rahul Wadbude, Vivek Gupta","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T14:34:16Z","title":"Leveraging Distributional Semantics for Multi-Label Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05976","kind":"arxiv","version":3},"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":"sha256:5dd4f8e3a0d26efe9050aed59b94a72383c725a0111e79ff7d363df1e43f1788","target":"record","created_at":"2026-05-18T00:30:54Z","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":"a6835071fafd6273c7eb83edd217c047a9388e7d92c2c9676c58b870b42cc1dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T14:34:16Z","title_canon_sha256":"f74cde13c98c2fd1aaa47f5e7a816695447f66a358b40f156bcd8dda3ccbfb02"},"schema_version":"1.0","source":{"id":"1709.05976","kind":"arxiv","version":3}},"canonical_sha256":"e30840167a73721ef31c7287aeb9d7020d916e3da87ed0379050d5652223f939","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e30840167a73721ef31c7287aeb9d7020d916e3da87ed0379050d5652223f939","first_computed_at":"2026-05-18T00:30:54.602109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:54.602109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q4luWun1KOqkyIHwpZk7dYkbfCvnotudl++xUQS8ovwcB1/9tw24sj39qV6TN3xJP3vg/dWpRKvMUHJ6WFdWBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:54.602662Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.05976","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dd4f8e3a0d26efe9050aed59b94a72383c725a0111e79ff7d363df1e43f1788","sha256:ea9baef6523c4202a30ca7ea8bab07532150e07d3476c7c15bf948ea876ff67c"],"state_sha256":"696e889c0c959a6d0fb9c4495a3a2e662088f7f7a84cecd3cd4338182c149ff4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHUDAQ8C7q7HKlQ0qToc+DmguFQSyRBqu37B6CBX7XxjbXopzoB2vA43JI//Y3FxpZVAhaFQGlLU+ICPXlcUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:14:57.410519Z","bundle_sha256":"85a8e68dc80d7515869b2bf98317b25b3f3010eed987a8722c2d2fed9afa017c"}}