{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KAJRM56KWTBMQDI4YCEU3IPUUN","short_pith_number":"pith:KAJRM56K","canonical_record":{"source":{"id":"2302.12139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-02-23T16:26:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f1e49ee6f149394d18aa1a218f6468222c12e6c06dfb40d7de8e11b0dcc312d1","abstract_canon_sha256":"d27c0073323c2cc58d0d473a49979bfcf0c479fd85dab0226cc03eefaa9eb9cd"},"schema_version":"1.0"},"canonical_sha256":"50131677cab4c2c80d1cc0894da1f4a36bbd560d3e63f7e99d86b62adc0457d6","source":{"kind":"arxiv","id":"2302.12139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.12139","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"2302.12139v1","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12139","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"KAJRM56KWTBM","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"pith_short_16","alias_value":"KAJRM56KWTBMQDI4","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"pith_short_8","alias_value":"KAJRM56K","created_at":"2026-07-05T05:45:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KAJRM56KWTBMQDI4YCEU3IPUUN","target":"record","payload":{"canonical_record":{"source":{"id":"2302.12139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-02-23T16:26:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f1e49ee6f149394d18aa1a218f6468222c12e6c06dfb40d7de8e11b0dcc312d1","abstract_canon_sha256":"d27c0073323c2cc58d0d473a49979bfcf0c479fd85dab0226cc03eefaa9eb9cd"},"schema_version":"1.0"},"canonical_sha256":"50131677cab4c2c80d1cc0894da1f4a36bbd560d3e63f7e99d86b62adc0457d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:00.604935Z","signature_b64":"752hzXWk3uIujT9k9GCk6SVo5djhwJfMk2XbiOZ12AbIgfalWug0alfPKiPPT9qL9THuNwqOHWi8Clqfu0ZRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50131677cab4c2c80d1cc0894da1f4a36bbd560d3e63f7e99d86b62adc0457d6","last_reissued_at":"2026-07-05T05:45:00.604501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:00.604501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.12139","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":"2026-07-05T05:45:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h35BXn7+RnoVl0WuIa5jswlNexfsw43EB5hXswOEMMCVLyNCPF292JSp3XmLaACI6CTsNHdzK5UZF60n1lYdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:51:35.636970Z"},"content_sha256":"cc9a15346e05692bacb652341579ae5f142e889aa73d988cea88fe91ee906a71","schema_version":"1.0","event_id":"sha256:cc9a15346e05692bacb652341579ae5f142e889aa73d988cea88fe91ee906a71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KAJRM56KWTBMQDI4YCEU3IPUUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Extraction of Fine-Grained Standardized Product Information from Unstructured Multilingual Web Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Flick, Felix Biessmann, Ivana Trajanovska, Sebastian J\\\"ager","submitted_at":"2023-02-23T16:26:11Z","abstract_excerpt":"Extracting structured information from unstructured data is one of the key challenges in modern information retrieval applications, including e-commerce. Here, we demonstrate how recent advances in machine learning, combined with a recently published multilingual data set with standardized fine-grained product category information, enable robust product attribute extraction in challenging transfer learning settings. Our models can reliably predict product attributes across online shops, languages, or both. Furthermore, we show that our models can be used to match product taxonomies between onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12139","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/2302.12139/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":"2026-07-05T05:45:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4rpwNdyNIV9sNDg501MDyK+AsiLNe166laYOeQIDmsAjTfE9yci/MlPZ7zEuOdQQQWrzJM4+Yy5vOeWwJ6kDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:51:35.637367Z"},"content_sha256":"affea3fc04cd26790f208b6ad6bc1593cf77875575977d67482cbb728c3dcdea","schema_version":"1.0","event_id":"sha256:affea3fc04cd26790f208b6ad6bc1593cf77875575977d67482cbb728c3dcdea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAJRM56KWTBMQDI4YCEU3IPUUN/bundle.json","state_url":"https://pith.science/pith/KAJRM56KWTBMQDI4YCEU3IPUUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAJRM56KWTBMQDI4YCEU3IPUUN/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":"2026-07-09T06:51:35Z","links":{"resolver":"https://pith.science/pith/KAJRM56KWTBMQDI4YCEU3IPUUN","bundle":"https://pith.science/pith/KAJRM56KWTBMQDI4YCEU3IPUUN/bundle.json","state":"https://pith.science/pith/KAJRM56KWTBMQDI4YCEU3IPUUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAJRM56KWTBMQDI4YCEU3IPUUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KAJRM56KWTBMQDI4YCEU3IPUUN","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":"d27c0073323c2cc58d0d473a49979bfcf0c479fd85dab0226cc03eefaa9eb9cd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-02-23T16:26:11Z","title_canon_sha256":"f1e49ee6f149394d18aa1a218f6468222c12e6c06dfb40d7de8e11b0dcc312d1"},"schema_version":"1.0","source":{"id":"2302.12139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.12139","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"2302.12139v1","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12139","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"KAJRM56KWTBM","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"pith_short_16","alias_value":"KAJRM56KWTBMQDI4","created_at":"2026-07-05T05:45:00Z"},{"alias_kind":"pith_short_8","alias_value":"KAJRM56K","created_at":"2026-07-05T05:45:00Z"}],"graph_snapshots":[{"event_id":"sha256:affea3fc04cd26790f208b6ad6bc1593cf77875575977d67482cbb728c3dcdea","target":"graph","created_at":"2026-07-05T05:45:00Z","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/2302.12139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting structured information from unstructured data is one of the key challenges in modern information retrieval applications, including e-commerce. Here, we demonstrate how recent advances in machine learning, combined with a recently published multilingual data set with standardized fine-grained product category information, enable robust product attribute extraction in challenging transfer learning settings. Our models can reliably predict product attributes across online shops, languages, or both. Furthermore, we show that our models can be used to match product taxonomies between onl","authors_text":"Alexander Flick, Felix Biessmann, Ivana Trajanovska, Sebastian J\\\"ager","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-02-23T16:26:11Z","title":"Automated Extraction of Fine-Grained Standardized Product Information from Unstructured Multilingual Web Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12139","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:cc9a15346e05692bacb652341579ae5f142e889aa73d988cea88fe91ee906a71","target":"record","created_at":"2026-07-05T05:45:00Z","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":"d27c0073323c2cc58d0d473a49979bfcf0c479fd85dab0226cc03eefaa9eb9cd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-02-23T16:26:11Z","title_canon_sha256":"f1e49ee6f149394d18aa1a218f6468222c12e6c06dfb40d7de8e11b0dcc312d1"},"schema_version":"1.0","source":{"id":"2302.12139","kind":"arxiv","version":1}},"canonical_sha256":"50131677cab4c2c80d1cc0894da1f4a36bbd560d3e63f7e99d86b62adc0457d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50131677cab4c2c80d1cc0894da1f4a36bbd560d3e63f7e99d86b62adc0457d6","first_computed_at":"2026-07-05T05:45:00.604501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:00.604501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"752hzXWk3uIujT9k9GCk6SVo5djhwJfMk2XbiOZ12AbIgfalWug0alfPKiPPT9qL9THuNwqOHWi8Clqfu0ZRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:00.604935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.12139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc9a15346e05692bacb652341579ae5f142e889aa73d988cea88fe91ee906a71","sha256:affea3fc04cd26790f208b6ad6bc1593cf77875575977d67482cbb728c3dcdea"],"state_sha256":"6fc34facfe788b17833e26e38933ac87f2d5bb4bd11a690ec4877c21f215c0dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M5ZhlCAP6Lh82eubFqUhHYNzr0/5pq4bLClG2yiFkhCkhE8Wd0dNsZsdSMjZ4QLd7kN6kHl2JTQ4XJSNEaryAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:51:35.640156Z","bundle_sha256":"7fc7cf999ce80771e5cb28a57849c7b470b9bd6fd5972313eaaa7d0148bef431"}}