{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GTUKUUBESXFHNIGYKMSA66LQLO","short_pith_number":"pith:GTUKUUBE","schema_version":"1.0","canonical_sha256":"34e8aa502495ca76a0d853240f79705b8dea971bb2466e974b77909cd14d4c18","source":{"kind":"arxiv","id":"2004.13852","version":2},"attestation_state":"computed","paper":{"title":"TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Giannis Karamanolakis, Jun Ma, Xin Luna Dong","submitted_at":"2020-04-15T03:02:09Z","abstract_excerpt":"Extracting structured knowledge from product profiles is crucial for various applications in e-Commerce. State-of-the-art approaches for knowledge extraction were each designed for a single category of product, and thus do not apply to real-life e-Commerce scenarios, which often contain thousands of diverse categories. This paper proposes TXtract, a taxonomy-aware knowledge extraction model that applies to thousands of product categories organized in a hierarchical taxonomy. Through category conditional self-attention and multi-task learning, our approach is both scalable, as it trains a singl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.13852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-15T03:02:09Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"6f4c93320e328073ece87c330acc27bf0c3048dc8663e98d9c006379a2025898","abstract_canon_sha256":"a3d8302877ddf99f2f865098a7c08455d6c9c60b2582d2ed23b8c621bb2d24fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:36.823512Z","signature_b64":"nozUvFzRwF8TSvNgzUcI1Pm28pY8Xd86y3Hkd35av74EUSb0o1IAOvF46A/jaWmx72fnpVg8I60bvnaD/4oWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34e8aa502495ca76a0d853240f79705b8dea971bb2466e974b77909cd14d4c18","last_reissued_at":"2026-07-05T00:59:36.823066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:36.823066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Giannis Karamanolakis, Jun Ma, Xin Luna Dong","submitted_at":"2020-04-15T03:02:09Z","abstract_excerpt":"Extracting structured knowledge from product profiles is crucial for various applications in e-Commerce. State-of-the-art approaches for knowledge extraction were each designed for a single category of product, and thus do not apply to real-life e-Commerce scenarios, which often contain thousands of diverse categories. This paper proposes TXtract, a taxonomy-aware knowledge extraction model that applies to thousands of product categories organized in a hierarchical taxonomy. Through category conditional self-attention and multi-task learning, our approach is both scalable, as it trains a singl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13852","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/2004.13852/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.13852","created_at":"2026-07-05T00:59:36.823127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13852v2","created_at":"2026-07-05T00:59:36.823127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13852","created_at":"2026-07-05T00:59:36.823127+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTUKUUBESXFH","created_at":"2026-07-05T00:59:36.823127+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTUKUUBESXFHNIGY","created_at":"2026-07-05T00:59:36.823127+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTUKUUBE","created_at":"2026-07-05T00:59:36.823127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO","json":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO.json","graph_json":"https://pith.science/api/pith-number/GTUKUUBESXFHNIGYKMSA66LQLO/graph.json","events_json":"https://pith.science/api/pith-number/GTUKUUBESXFHNIGYKMSA66LQLO/events.json","paper":"https://pith.science/paper/GTUKUUBE"},"agent_actions":{"view_html":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO","download_json":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO.json","view_paper":"https://pith.science/paper/GTUKUUBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13852&json=true","fetch_graph":"https://pith.science/api/pith-number/GTUKUUBESXFHNIGYKMSA66LQLO/graph.json","fetch_events":"https://pith.science/api/pith-number/GTUKUUBESXFHNIGYKMSA66LQLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/action/storage_attestation","attest_author":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/action/author_attestation","sign_citation":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/action/citation_signature","submit_replication":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/action/replication_record"}},"created_at":"2026-07-05T00:59:36.823127+00:00","updated_at":"2026-07-05T00:59:36.823127+00:00"}