{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3RM55YVX56VLKRWROMQAUS2GVR","short_pith_number":"pith:3RM55YVX","canonical_record":{"source":{"id":"2204.00958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T23:42:32Z","cross_cats_sorted":[],"title_canon_sha256":"f2669bfdadb97874a5381b1d61c47b81b018ca50eb022bb8e8b3193eb7f47cec","abstract_canon_sha256":"d1daf6271ef8dbc5dd21e0943d071d8c01a9b7dfc1b3333dd7e2d15b4b645d61"},"schema_version":"1.0"},"canonical_sha256":"dc59dee2b7efaab546d173200a4b46ac63cb3fa3c296ef5925c7003f7c26446a","source":{"kind":"arxiv","id":"2204.00958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00958","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00958v1","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00958","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"3RM55YVX56VL","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"3RM55YVX56VLKRWR","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"3RM55YVX","created_at":"2026-07-05T04:11:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3RM55YVX56VLKRWROMQAUS2GVR","target":"record","payload":{"canonical_record":{"source":{"id":"2204.00958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T23:42:32Z","cross_cats_sorted":[],"title_canon_sha256":"f2669bfdadb97874a5381b1d61c47b81b018ca50eb022bb8e8b3193eb7f47cec","abstract_canon_sha256":"d1daf6271ef8dbc5dd21e0943d071d8c01a9b7dfc1b3333dd7e2d15b4b645d61"},"schema_version":"1.0"},"canonical_sha256":"dc59dee2b7efaab546d173200a4b46ac63cb3fa3c296ef5925c7003f7c26446a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:13.697789Z","signature_b64":"X26Csy9CUP2Ew+/0ddkXpFkI8gIGuDar3hzQZamdcue5ng4A2hkktmXyXouJSFSFBonaOxfODCtncQiYXDt8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc59dee2b7efaab546d173200a4b46ac63cb3fa3c296ef5925c7003f7c26446a","last_reissued_at":"2026-07-05T04:11:13.697376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:13.697376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.00958","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":"2026-07-05T04:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QZxNqjtOnuVLoNBq8qfziloeymL1/gi6JnpXi/yNtci8RV6mRknY8bSGKUaXKO7Tb98I2XyyUuHF7tb7zAG3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:57:16.691357Z"},"content_sha256":"b1337a23f108c9505bbd11c717a6ac3dadd4a8578b9d79dc7c82ad32a93b42e4","schema_version":"1.0","event_id":"sha256:b1337a23f108c9505bbd11c717a6ac3dadd4a8578b9d79dc7c82ad32a93b42e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3RM55YVX56VLKRWROMQAUS2GVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Long-tailed Extreme Multi-label Text Classification with Generated Pseudo Label Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donghan Yu, Likun Lei, Ruohong Zhang, Tom Vu, Yau-Shian Wang, Yiming Yang","submitted_at":"2022-04-02T23:42:32Z","abstract_excerpt":"Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarce problem associated with the long tail of rare labels in highly skewed distributions. This paper addresses the challenge of tail label prediction by proposing a novel approach, which combines the effectiveness of a trained bag-of-words (BoW) classifier in generating informative label descriptions under severe data scarce conditions, and the power of neural embedding based retrieval models in mapping input do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00958","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.00958/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":"2026-07-05T04:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3orHcpgZoBeG7f3ye5HlRKtlXCATrG7Jyt40Fx2WNDKa92+XeACTLPfQoZ6UjSz+SyWjGOSyjsplihdeztTvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:57:16.691857Z"},"content_sha256":"1f1fa38c1dff62c2bc9a83cc8c4f6c49948fde3e65a64b1dde15d792f41a0e00","schema_version":"1.0","event_id":"sha256:1f1fa38c1dff62c2bc9a83cc8c4f6c49948fde3e65a64b1dde15d792f41a0e00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RM55YVX56VLKRWROMQAUS2GVR/bundle.json","state_url":"https://pith.science/pith/3RM55YVX56VLKRWROMQAUS2GVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RM55YVX56VLKRWROMQAUS2GVR/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":"2026-08-03T19:57:16Z","links":{"resolver":"https://pith.science/pith/3RM55YVX56VLKRWROMQAUS2GVR","bundle":"https://pith.science/pith/3RM55YVX56VLKRWROMQAUS2GVR/bundle.json","state":"https://pith.science/pith/3RM55YVX56VLKRWROMQAUS2GVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RM55YVX56VLKRWROMQAUS2GVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3RM55YVX56VLKRWROMQAUS2GVR","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":"d1daf6271ef8dbc5dd21e0943d071d8c01a9b7dfc1b3333dd7e2d15b4b645d61","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T23:42:32Z","title_canon_sha256":"f2669bfdadb97874a5381b1d61c47b81b018ca50eb022bb8e8b3193eb7f47cec"},"schema_version":"1.0","source":{"id":"2204.00958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00958","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00958v1","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00958","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"3RM55YVX56VL","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"3RM55YVX56VLKRWR","created_at":"2026-07-05T04:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"3RM55YVX","created_at":"2026-07-05T04:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:1f1fa38c1dff62c2bc9a83cc8c4f6c49948fde3e65a64b1dde15d792f41a0e00","target":"graph","created_at":"2026-07-05T04:11:13Z","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/2204.00958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarce problem associated with the long tail of rare labels in highly skewed distributions. This paper addresses the challenge of tail label prediction by proposing a novel approach, which combines the effectiveness of a trained bag-of-words (BoW) classifier in generating informative label descriptions under severe data scarce conditions, and the power of neural embedding based retrieval models in mapping input do","authors_text":"Donghan Yu, Likun Lei, Ruohong Zhang, Tom Vu, Yau-Shian Wang, Yiming Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T23:42:32Z","title":"Long-tailed Extreme Multi-label Text Classification with Generated Pseudo Label Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00958","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:b1337a23f108c9505bbd11c717a6ac3dadd4a8578b9d79dc7c82ad32a93b42e4","target":"record","created_at":"2026-07-05T04:11:13Z","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":"d1daf6271ef8dbc5dd21e0943d071d8c01a9b7dfc1b3333dd7e2d15b4b645d61","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T23:42:32Z","title_canon_sha256":"f2669bfdadb97874a5381b1d61c47b81b018ca50eb022bb8e8b3193eb7f47cec"},"schema_version":"1.0","source":{"id":"2204.00958","kind":"arxiv","version":1}},"canonical_sha256":"dc59dee2b7efaab546d173200a4b46ac63cb3fa3c296ef5925c7003f7c26446a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc59dee2b7efaab546d173200a4b46ac63cb3fa3c296ef5925c7003f7c26446a","first_computed_at":"2026-07-05T04:11:13.697376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:13.697376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X26Csy9CUP2Ew+/0ddkXpFkI8gIGuDar3hzQZamdcue5ng4A2hkktmXyXouJSFSFBonaOxfODCtncQiYXDt8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:13.697789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1337a23f108c9505bbd11c717a6ac3dadd4a8578b9d79dc7c82ad32a93b42e4","sha256:1f1fa38c1dff62c2bc9a83cc8c4f6c49948fde3e65a64b1dde15d792f41a0e00"],"state_sha256":"f4083b513d0b045406a6b33e6a41cdb78103ae2d305fa46ae6ffe45ba4c6980d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OeaNJhY6YOjbDj3qDbk1Lv/HItaLvPq6cgs+42BxC+zuKmq5nwYIK06OPDYICPDYqPvocvwu0X+IkhXe6TonDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:57:16.699230Z","bundle_sha256":"59e395514e9e37c0213dd27df4e9ae9fa98d416e0dcd080f58d4e7e067ce3848"}}