{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:63VUPPMOMZNZHTDIXQ6A33SZRA","short_pith_number":"pith:63VUPPMO","canonical_record":{"source":{"id":"2411.12056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T20:54:17Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"bd2c1e513a5310b295f1b0c6d560a618c2629196919c2f9429ff05acc774767a","abstract_canon_sha256":"479e86e9ddb8e3ae9f0409e038a7d4d2f1a8357d076364b568d3802b3bf1029d"},"schema_version":"1.0"},"canonical_sha256":"f6eb47bd8e665b93cc68bc3c0dee59881a71157448d48ff74be0d8c13164f498","source":{"kind":"arxiv","id":"2411.12056","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12056","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12056v1","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12056","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"63VUPPMOMZNZ","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"63VUPPMOMZNZHTDI","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"63VUPPMO","created_at":"2026-07-05T09:37:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:63VUPPMOMZNZHTDIXQ6A33SZRA","target":"record","payload":{"canonical_record":{"source":{"id":"2411.12056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T20:54:17Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"bd2c1e513a5310b295f1b0c6d560a618c2629196919c2f9429ff05acc774767a","abstract_canon_sha256":"479e86e9ddb8e3ae9f0409e038a7d4d2f1a8357d076364b568d3802b3bf1029d"},"schema_version":"1.0"},"canonical_sha256":"f6eb47bd8e665b93cc68bc3c0dee59881a71157448d48ff74be0d8c13164f498","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:15.441488Z","signature_b64":"GozEnWy05WIJFQN9h8rwqnkh5q1jaI7/F0RDg9FGhwNA+BJ4wBVWf7L0BMCeEXOBvzo4uCkWNFlliquN8w1ACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6eb47bd8e665b93cc68bc3c0dee59881a71157448d48ff74be0d8c13164f498","last_reissued_at":"2026-07-05T09:37:15.441059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:15.441059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.12056","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":"2026-07-05T09:37:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5lPjfKtnjMXgd/8A7uVAM3KB7+Ahng9/0jf9Jqt9uOOzYoodwcqZP86LIUTMRmSe5bP6vA/zxOEaVGqrWh+/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:09:07.411268Z"},"content_sha256":"9e825ffad82a74319c7d2322277579a55909e557651bf72a2ebc6141df038089","schema_version":"1.0","event_id":"sha256:9e825ffad82a74319c7d2322277579a55909e557651bf72a2ebc6141df038089"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:63VUPPMOMZNZHTDIXQ6A33SZRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking pre-trained text embedding models in aligning built asset information","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Motamedi, Mehrzad Shahinmoghadam","submitted_at":"2024-11-18T20:54:17Z","abstract_excerpt":"Accurate mapping of the built asset information to established data classification systems and taxonomies is crucial for effective asset management, whether for compliance at project handover or ad-hoc data integration scenarios. Due to the complex nature of built asset data, which predominantly comprises technical text elements, this process remains largely manual and reliant on domain expert input. Recent breakthroughs in contextual text representation learning (text embedding), particularly through pre-trained large language models, offer promising approaches that can facilitate the automat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12056","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/2411.12056/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":"2026-07-05T09:37:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vbLHi7+VFbOltz8PNu0oqfemMmdTXqIUAQN4ndYH6rMun40rRslHm5YarCT9CSPnRO2OTibXpfJpXpNUTlT1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:09:07.411859Z"},"content_sha256":"cd6e93e65a4beb83ead40a5cf430d0e7548afd891dfd82468fda38208490bb40","schema_version":"1.0","event_id":"sha256:cd6e93e65a4beb83ead40a5cf430d0e7548afd891dfd82468fda38208490bb40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/63VUPPMOMZNZHTDIXQ6A33SZRA/bundle.json","state_url":"https://pith.science/pith/63VUPPMOMZNZHTDIXQ6A33SZRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/63VUPPMOMZNZHTDIXQ6A33SZRA/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":"2026-08-13T13:09:07Z","links":{"resolver":"https://pith.science/pith/63VUPPMOMZNZHTDIXQ6A33SZRA","bundle":"https://pith.science/pith/63VUPPMOMZNZHTDIXQ6A33SZRA/bundle.json","state":"https://pith.science/pith/63VUPPMOMZNZHTDIXQ6A33SZRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/63VUPPMOMZNZHTDIXQ6A33SZRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:63VUPPMOMZNZHTDIXQ6A33SZRA","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":"479e86e9ddb8e3ae9f0409e038a7d4d2f1a8357d076364b568d3802b3bf1029d","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T20:54:17Z","title_canon_sha256":"bd2c1e513a5310b295f1b0c6d560a618c2629196919c2f9429ff05acc774767a"},"schema_version":"1.0","source":{"id":"2411.12056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12056","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12056v1","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12056","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"63VUPPMOMZNZ","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"63VUPPMOMZNZHTDI","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"63VUPPMO","created_at":"2026-07-05T09:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:cd6e93e65a4beb83ead40a5cf430d0e7548afd891dfd82468fda38208490bb40","target":"graph","created_at":"2026-07-05T09:37:15Z","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/2411.12056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate mapping of the built asset information to established data classification systems and taxonomies is crucial for effective asset management, whether for compliance at project handover or ad-hoc data integration scenarios. Due to the complex nature of built asset data, which predominantly comprises technical text elements, this process remains largely manual and reliant on domain expert input. Recent breakthroughs in contextual text representation learning (text embedding), particularly through pre-trained large language models, offer promising approaches that can facilitate the automat","authors_text":"Ali Motamedi, Mehrzad Shahinmoghadam","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T20:54:17Z","title":"Benchmarking pre-trained text embedding models in aligning built asset information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12056","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":"sha256:9e825ffad82a74319c7d2322277579a55909e557651bf72a2ebc6141df038089","target":"record","created_at":"2026-07-05T09:37:15Z","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":"479e86e9ddb8e3ae9f0409e038a7d4d2f1a8357d076364b568d3802b3bf1029d","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T20:54:17Z","title_canon_sha256":"bd2c1e513a5310b295f1b0c6d560a618c2629196919c2f9429ff05acc774767a"},"schema_version":"1.0","source":{"id":"2411.12056","kind":"arxiv","version":1}},"canonical_sha256":"f6eb47bd8e665b93cc68bc3c0dee59881a71157448d48ff74be0d8c13164f498","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6eb47bd8e665b93cc68bc3c0dee59881a71157448d48ff74be0d8c13164f498","first_computed_at":"2026-07-05T09:37:15.441059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:15.441059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GozEnWy05WIJFQN9h8rwqnkh5q1jaI7/F0RDg9FGhwNA+BJ4wBVWf7L0BMCeEXOBvzo4uCkWNFlliquN8w1ACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:15.441488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e825ffad82a74319c7d2322277579a55909e557651bf72a2ebc6141df038089","sha256:cd6e93e65a4beb83ead40a5cf430d0e7548afd891dfd82468fda38208490bb40"],"state_sha256":"738e72d5bafedec2e5ce9d551d638643f44bb33339e3a179961c3850ec68efa6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NECW5qb2ybflB/6/weXeOPuBd6LhMEGySJWUeK6bf1uM+jPm2d9gi/wRyqiPN5Kk5CWBXaEBl9wORay0rPGyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:09:07.429437Z","bundle_sha256":"4cd33962d1fab98417e1022ed62bf7456d70bf7ce7c460136c07988be12371de"}}