{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GTUKUUBESXFHNIGYKMSA66LQLO","short_pith_number":"pith:GTUKUUBE","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"},"canonical_sha256":"34e8aa502495ca76a0d853240f79705b8dea971bb2466e974b77909cd14d4c18","source":{"kind":"arxiv","id":"2004.13852","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13852","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13852v2","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13852","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"GTUKUUBESXFH","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"GTUKUUBESXFHNIGY","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"GTUKUUBE","created_at":"2026-07-05T00:59:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GTUKUUBESXFHNIGYKMSA66LQLO","target":"record","payload":{"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"},"canonical_sha256":"34e8aa502495ca76a0d853240f79705b8dea971bb2466e974b77909cd14d4c18","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"},"source_kind":"arxiv","source_id":"2004.13852","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":"2026-07-05T00:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIOhlfQC5a8yhFkjOhWDQm74vPCLBUssgPXvgfkmN8Am/qwYQDuqTg8ClwodQmJgAI3nSDPWWQkgJjQYT94sDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:59:39.704141Z"},"content_sha256":"9a5afa7fe9e487330982e94b84bf7a042a585e0472d73e9d5c4c043134ab3c28","schema_version":"1.0","event_id":"sha256:9a5afa7fe9e487330982e94b84bf7a042a585e0472d73e9d5c4c043134ab3c28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GTUKUUBESXFHNIGYKMSA66LQLO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wkjaUD/kBq3N9HWbQS5C9pk639PBJUN/TeIU4efL0/x5KrL+wjaIh1V/Rprb/5Jy9xtu4mzcLeL8FdYlvg7xAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:59:39.704534Z"},"content_sha256":"bc1884fc9ec732af35e802c8ecc10fa1cbb256adbfb25f1b1387402e5a511451","schema_version":"1.0","event_id":"sha256:bc1884fc9ec732af35e802c8ecc10fa1cbb256adbfb25f1b1387402e5a511451"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/bundle.json","state_url":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTUKUUBESXFHNIGYKMSA66LQLO/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":"2026-07-07T11:59:39Z","links":{"resolver":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO","bundle":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/bundle.json","state":"https://pith.science/pith/GTUKUUBESXFHNIGYKMSA66LQLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTUKUUBESXFHNIGYKMSA66LQLO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GTUKUUBESXFHNIGYKMSA66LQLO","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":"a3d8302877ddf99f2f865098a7c08455d6c9c60b2582d2ed23b8c621bb2d24fa","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-15T03:02:09Z","title_canon_sha256":"6f4c93320e328073ece87c330acc27bf0c3048dc8663e98d9c006379a2025898"},"schema_version":"1.0","source":{"id":"2004.13852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13852","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13852v2","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13852","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"GTUKUUBESXFH","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"GTUKUUBESXFHNIGY","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"GTUKUUBE","created_at":"2026-07-05T00:59:36Z"}],"graph_snapshots":[{"event_id":"sha256:bc1884fc9ec732af35e802c8ecc10fa1cbb256adbfb25f1b1387402e5a511451","target":"graph","created_at":"2026-07-05T00:59:36Z","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/2004.13852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Giannis Karamanolakis, Jun Ma, Xin Luna Dong","cross_cats":["cs.IR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-15T03:02:09Z","title":"TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13852","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":"sha256:9a5afa7fe9e487330982e94b84bf7a042a585e0472d73e9d5c4c043134ab3c28","target":"record","created_at":"2026-07-05T00:59:36Z","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":"a3d8302877ddf99f2f865098a7c08455d6c9c60b2582d2ed23b8c621bb2d24fa","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-15T03:02:09Z","title_canon_sha256":"6f4c93320e328073ece87c330acc27bf0c3048dc8663e98d9c006379a2025898"},"schema_version":"1.0","source":{"id":"2004.13852","kind":"arxiv","version":2}},"canonical_sha256":"34e8aa502495ca76a0d853240f79705b8dea971bb2466e974b77909cd14d4c18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34e8aa502495ca76a0d853240f79705b8dea971bb2466e974b77909cd14d4c18","first_computed_at":"2026-07-05T00:59:36.823066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:36.823066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nozUvFzRwF8TSvNgzUcI1Pm28pY8Xd86y3Hkd35av74EUSb0o1IAOvF46A/jaWmx72fnpVg8I60bvnaD/4oWDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:36.823512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.13852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a5afa7fe9e487330982e94b84bf7a042a585e0472d73e9d5c4c043134ab3c28","sha256:bc1884fc9ec732af35e802c8ecc10fa1cbb256adbfb25f1b1387402e5a511451"],"state_sha256":"c2bf267ead1c91759cf6d6155c35438ea51a037732fe0f370edddb88133c5908"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"47EKA+K9ESAhVPgC7gCX819FgM5ahauH/I/nX6GOg2U7Me3HdZzuaWwesI6orO2KP3VllaGzJ5TV7duZawNZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:59:39.706611Z","bundle_sha256":"9ecaad937fe06be6f84a066ce36d38f8cf7224faed0f1ebe0c774dcfa2b85b3b"}}