{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:B3LGU3YAQ2SXONET2LOQ3I4IKW","short_pith_number":"pith:B3LGU3YA","canonical_record":{"source":{"id":"2305.14588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:53:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8728e296046fa9e90265e1808045546917ec911c485d207fce4c45028ef248bb","abstract_canon_sha256":"59636e881faff66c88f4e1c4a0c6b0429b0d9987b6f6b755609acb6bb1ff2f92"},"schema_version":"1.0"},"canonical_sha256":"0ed66a6f0086a5773493d2dd0da38855ab1c072080eb982fafe8864d65504d31","source":{"kind":"arxiv","id":"2305.14588","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14588","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14588v1","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14588","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"pith_short_12","alias_value":"B3LGU3YAQ2SX","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"pith_short_16","alias_value":"B3LGU3YAQ2SXONET","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"pith_short_8","alias_value":"B3LGU3YA","created_at":"2026-07-05T06:13:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:B3LGU3YAQ2SXONET2LOQ3I4IKW","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:53:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8728e296046fa9e90265e1808045546917ec911c485d207fce4c45028ef248bb","abstract_canon_sha256":"59636e881faff66c88f4e1c4a0c6b0429b0d9987b6f6b755609acb6bb1ff2f92"},"schema_version":"1.0"},"canonical_sha256":"0ed66a6f0086a5773493d2dd0da38855ab1c072080eb982fafe8864d65504d31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:25.392973Z","signature_b64":"HDvKIekratOm0pMrRdJ8ynTACn5Y9Udonvb0WHwKnlI+cgo17HPbR05a5+RZ39Fk7nYgDjnZi6iLg0XUng40Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ed66a6f0086a5773493d2dd0da38855ab1c072080eb982fafe8864d65504d31","last_reissued_at":"2026-07-05T06:13:25.392550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:25.392550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14588","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":"2026-07-05T06:13:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5En3jO0maB2epL/0ekAaWK7tRW51dz3asC71MjiT4uwdN3SqtA0VH4uKahBa3TEe/6uqHTPXN9D2u/x9BNvhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:53:01.692820Z"},"content_sha256":"6e4a334e9bc362d9b05859efb46c011f3120cc88b0e894adaa5d345879ebddbf","schema_version":"1.0","event_id":"sha256:6e4a334e9bc362d9b05859efb46c011f3120cc88b0e894adaa5d345879ebddbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:B3LGU3YAQ2SXONET2LOQ3I4IKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating end-to-end entity linking on domain-specific knowledge bases: Learning about ancient technologies from museum collections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Danial Lashkari, Daniel Simig, Johannes Boehm, Khalil Kacem, Rafael Aparecido Martins Frade, Sebastian Cadavid-Sanchez, Thomas Chaney","submitted_at":"2023-05-23T23:53:58Z","abstract_excerpt":"To study social, economic, and historical questions, researchers in the social sciences and humanities have started to use increasingly large unstructured textual datasets. While recent advances in NLP provide many tools to efficiently process such data, most existing approaches rely on generic solutions whose performance and suitability for domain-specific tasks is not well understood. This work presents an attempt to bridge this domain gap by exploring the use of modern Entity Linking approaches for the enrichment of museum collection data. We collect a dataset comprising of more than 1700 t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14588","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/2305.14588/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":"2026-07-05T06:13:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vAVzpJX2JI4MkxdLOq/aNGYZcPOgnDUgBHBc+tKf2lRW4Lp54dGNefusjnIKVnQialzbwFeh2lXScLAzNJFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:53:01.693623Z"},"content_sha256":"5addcbcb29be435d2eb2f029b6a1bcec01f14d8cf8ef83f329c81d83a47e3266","schema_version":"1.0","event_id":"sha256:5addcbcb29be435d2eb2f029b6a1bcec01f14d8cf8ef83f329c81d83a47e3266"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3LGU3YAQ2SXONET2LOQ3I4IKW/bundle.json","state_url":"https://pith.science/pith/B3LGU3YAQ2SXONET2LOQ3I4IKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3LGU3YAQ2SXONET2LOQ3I4IKW/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":"2026-08-17T02:53:01Z","links":{"resolver":"https://pith.science/pith/B3LGU3YAQ2SXONET2LOQ3I4IKW","bundle":"https://pith.science/pith/B3LGU3YAQ2SXONET2LOQ3I4IKW/bundle.json","state":"https://pith.science/pith/B3LGU3YAQ2SXONET2LOQ3I4IKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3LGU3YAQ2SXONET2LOQ3I4IKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B3LGU3YAQ2SXONET2LOQ3I4IKW","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":"59636e881faff66c88f4e1c4a0c6b0429b0d9987b6f6b755609acb6bb1ff2f92","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:53:58Z","title_canon_sha256":"8728e296046fa9e90265e1808045546917ec911c485d207fce4c45028ef248bb"},"schema_version":"1.0","source":{"id":"2305.14588","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14588","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14588v1","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14588","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"pith_short_12","alias_value":"B3LGU3YAQ2SX","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"pith_short_16","alias_value":"B3LGU3YAQ2SXONET","created_at":"2026-07-05T06:13:25Z"},{"alias_kind":"pith_short_8","alias_value":"B3LGU3YA","created_at":"2026-07-05T06:13:25Z"}],"graph_snapshots":[{"event_id":"sha256:5addcbcb29be435d2eb2f029b6a1bcec01f14d8cf8ef83f329c81d83a47e3266","target":"graph","created_at":"2026-07-05T06:13:25Z","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/2305.14588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To study social, economic, and historical questions, researchers in the social sciences and humanities have started to use increasingly large unstructured textual datasets. While recent advances in NLP provide many tools to efficiently process such data, most existing approaches rely on generic solutions whose performance and suitability for domain-specific tasks is not well understood. This work presents an attempt to bridge this domain gap by exploring the use of modern Entity Linking approaches for the enrichment of museum collection data. We collect a dataset comprising of more than 1700 t","authors_text":"Danial Lashkari, Daniel Simig, Johannes Boehm, Khalil Kacem, Rafael Aparecido Martins Frade, Sebastian Cadavid-Sanchez, Thomas Chaney","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:53:58Z","title":"Evaluating end-to-end entity linking on domain-specific knowledge bases: Learning about ancient technologies from museum collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14588","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":"sha256:6e4a334e9bc362d9b05859efb46c011f3120cc88b0e894adaa5d345879ebddbf","target":"record","created_at":"2026-07-05T06:13:25Z","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":"59636e881faff66c88f4e1c4a0c6b0429b0d9987b6f6b755609acb6bb1ff2f92","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:53:58Z","title_canon_sha256":"8728e296046fa9e90265e1808045546917ec911c485d207fce4c45028ef248bb"},"schema_version":"1.0","source":{"id":"2305.14588","kind":"arxiv","version":1}},"canonical_sha256":"0ed66a6f0086a5773493d2dd0da38855ab1c072080eb982fafe8864d65504d31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ed66a6f0086a5773493d2dd0da38855ab1c072080eb982fafe8864d65504d31","first_computed_at":"2026-07-05T06:13:25.392550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:25.392550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HDvKIekratOm0pMrRdJ8ynTACn5Y9Udonvb0WHwKnlI+cgo17HPbR05a5+RZ39Fk7nYgDjnZi6iLg0XUng40Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:25.392973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14588","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e4a334e9bc362d9b05859efb46c011f3120cc88b0e894adaa5d345879ebddbf","sha256:5addcbcb29be435d2eb2f029b6a1bcec01f14d8cf8ef83f329c81d83a47e3266"],"state_sha256":"889496a5007811799365a77b89625320cdecb00c703684cb14ccc450638c08b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MC9DIBUxbV11FAY6WZ8PE3cgDrRVAfx7E58nZkv3JuMNxfmN6QG86gunMmZMAPG8rT4Bhlm70W8kanBllc87CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T02:53:01.700589Z","bundle_sha256":"35ffe7bdb59fa7334b9e34ba08f4ef54694e2bf87e8e45d4c6d2e07beaaa04a0"}}