{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VDSE62AIWTZCJIIMPPNAMVJH6L","short_pith_number":"pith:VDSE62AI","canonical_record":{"source":{"id":"2308.13139","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T02:32:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f277b7012e66b3434c0b5edb161c7229a9dbd59a2ec7e84bd07485a0cbb72a0","abstract_canon_sha256":"50fe37ab0be522b3ebabbad43cfa93eb62d6a949a8f8ab56990c58866a916513"},"schema_version":"1.0"},"canonical_sha256":"a8e44f6808b4f224a10c7bda065527f2e26c641dee932ae60ff7cfa74968e33f","source":{"kind":"arxiv","id":"2308.13139","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13139","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13139v2","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13139","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"VDSE62AIWTZC","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"VDSE62AIWTZCJIIM","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"VDSE62AI","created_at":"2026-07-05T07:54:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VDSE62AIWTZCJIIMPPNAMVJH6L","target":"record","payload":{"canonical_record":{"source":{"id":"2308.13139","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T02:32:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f277b7012e66b3434c0b5edb161c7229a9dbd59a2ec7e84bd07485a0cbb72a0","abstract_canon_sha256":"50fe37ab0be522b3ebabbad43cfa93eb62d6a949a8f8ab56990c58866a916513"},"schema_version":"1.0"},"canonical_sha256":"a8e44f6808b4f224a10c7bda065527f2e26c641dee932ae60ff7cfa74968e33f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:32.476784Z","signature_b64":"413JrCxxuh108wOSXZ+8qjEER/WvknxPCUfjZdj35jvLrqMD/aBpuqZPkB8n/Tq631kfpA/IYnKIdc1mALofDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8e44f6808b4f224a10c7bda065527f2e26c641dee932ae60ff7cfa74968e33f","last_reissued_at":"2026-07-05T07:54:32.476381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:32.476381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.13139","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":"2026-07-05T07:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pnpkuxfZkMvq2wOO/XdrRYIZ90ZsVIrvSOBinpz34K5ClOYwdqZkqVH0Xk8gjqzdJQkYqVhPkz4atOp+fI8jCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:08:50.970519Z"},"content_sha256":"11ba46b7f42fcdf08f0f3716cda51749f83e01a192ff2a4ed7a20a9114be97da","schema_version":"1.0","event_id":"sha256:11ba46b7f42fcdf08f0f3716cda51749f83e01a192ff2a4ed7a20a9114be97da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VDSE62AIWTZCJIIMPPNAMVJH6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Ye, Rajshekhar Sunderraman, Shihao Ji","submitted_at":"2023-08-25T02:32:36Z","abstract_excerpt":"The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient text-label matching framework for XMC. We observe that the label embeddings generated from the sparse Term Frequency-Inverse Document Frequency(TF-IDF) features have several limitations. We thus propose label2vec to effectively train the semantic dense label embeddings by the Skip-gram model. The dense label embeddings are then used to build a Hierarchical Label Tree"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13139","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.13139/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T07:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"39ewMx17JxrUtyrZeGIbbAE9CumlpJK1Nqtgrq6h0HkGV32RZFOwictXKxJRNgKdG3RpMaVfxpuciLyUHSWkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:08:50.971046Z"},"content_sha256":"0caec670bb81b89ae358b2efdebf6b1a326e263d8992f4bbf4ae6146a2993f09","schema_version":"1.0","event_id":"sha256:0caec670bb81b89ae358b2efdebf6b1a326e263d8992f4bbf4ae6146a2993f09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDSE62AIWTZCJIIMPPNAMVJH6L/bundle.json","state_url":"https://pith.science/pith/VDSE62AIWTZCJIIMPPNAMVJH6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDSE62AIWTZCJIIMPPNAMVJH6L/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":"2026-08-08T03:08:50Z","links":{"resolver":"https://pith.science/pith/VDSE62AIWTZCJIIMPPNAMVJH6L","bundle":"https://pith.science/pith/VDSE62AIWTZCJIIMPPNAMVJH6L/bundle.json","state":"https://pith.science/pith/VDSE62AIWTZCJIIMPPNAMVJH6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDSE62AIWTZCJIIMPPNAMVJH6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VDSE62AIWTZCJIIMPPNAMVJH6L","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":"50fe37ab0be522b3ebabbad43cfa93eb62d6a949a8f8ab56990c58866a916513","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T02:32:36Z","title_canon_sha256":"0f277b7012e66b3434c0b5edb161c7229a9dbd59a2ec7e84bd07485a0cbb72a0"},"schema_version":"1.0","source":{"id":"2308.13139","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13139","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13139v2","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13139","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"VDSE62AIWTZC","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"VDSE62AIWTZCJIIM","created_at":"2026-07-05T07:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"VDSE62AI","created_at":"2026-07-05T07:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:0caec670bb81b89ae358b2efdebf6b1a326e263d8992f4bbf4ae6146a2993f09","target":"graph","created_at":"2026-07-05T07:54:32Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.13139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient text-label matching framework for XMC. We observe that the label embeddings generated from the sparse Term Frequency-Inverse Document Frequency(TF-IDF) features have several limitations. We thus propose label2vec to effectively train the semantic dense label embeddings by the Skip-gram model. The dense label embeddings are then used to build a Hierarchical Label Tree","authors_text":"Hui Ye, Rajshekhar Sunderraman, Shihao Ji","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T02:32:36Z","title":"MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13139","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":"sha256:11ba46b7f42fcdf08f0f3716cda51749f83e01a192ff2a4ed7a20a9114be97da","target":"record","created_at":"2026-07-05T07:54:32Z","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":"50fe37ab0be522b3ebabbad43cfa93eb62d6a949a8f8ab56990c58866a916513","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T02:32:36Z","title_canon_sha256":"0f277b7012e66b3434c0b5edb161c7229a9dbd59a2ec7e84bd07485a0cbb72a0"},"schema_version":"1.0","source":{"id":"2308.13139","kind":"arxiv","version":2}},"canonical_sha256":"a8e44f6808b4f224a10c7bda065527f2e26c641dee932ae60ff7cfa74968e33f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8e44f6808b4f224a10c7bda065527f2e26c641dee932ae60ff7cfa74968e33f","first_computed_at":"2026-07-05T07:54:32.476381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:32.476381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"413JrCxxuh108wOSXZ+8qjEER/WvknxPCUfjZdj35jvLrqMD/aBpuqZPkB8n/Tq631kfpA/IYnKIdc1mALofDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:32.476784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13139","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ba46b7f42fcdf08f0f3716cda51749f83e01a192ff2a4ed7a20a9114be97da","sha256:0caec670bb81b89ae358b2efdebf6b1a326e263d8992f4bbf4ae6146a2993f09"],"state_sha256":"67fdd24760205479a2c8de52a057947cf5030cf0726a9cd0e4785d33cce4e5e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8R4tOJnpTsE2s1Va/mrxjNGEomvTLlNYevyOIBkwN747QaBEdJN3j9uVbt9FQDnosAAoHqd6cI0MThqNATZYCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:08:50.975357Z","bundle_sha256":"48f2303d60e9477e81fec63c8fb53c74bde66def97f4d1400d40c00b62081b5f"}}