{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6YI7HB6DDZI7HKD54XSME25LVH","short_pith_number":"pith:6YI7HB6D","canonical_record":{"source":{"id":"1703.10349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-30T08:25:35Z","cross_cats_sorted":[],"title_canon_sha256":"9e3858d2105813ed60777b6d3f283bddb744f3d379f730128ab7983147a8d602","abstract_canon_sha256":"bb08a2de3858faf6e61fa0a21c8286aca74e43f17a9959cbd32c416474d968a3"},"schema_version":"1.0"},"canonical_sha256":"f611f387c31e51f3a87de5e4c26baba9d3be796f97a2ac31bc86afcf3d71eb1d","source":{"kind":"arxiv","id":"1703.10349","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10349","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10349v1","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10349","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"6YI7HB6DDZI7","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6YI7HB6DDZI7HKD5","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6YI7HB6D","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6YI7HB6DDZI7HKD54XSME25LVH","target":"record","payload":{"canonical_record":{"source":{"id":"1703.10349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-30T08:25:35Z","cross_cats_sorted":[],"title_canon_sha256":"9e3858d2105813ed60777b6d3f283bddb744f3d379f730128ab7983147a8d602","abstract_canon_sha256":"bb08a2de3858faf6e61fa0a21c8286aca74e43f17a9959cbd32c416474d968a3"},"schema_version":"1.0"},"canonical_sha256":"f611f387c31e51f3a87de5e4c26baba9d3be796f97a2ac31bc86afcf3d71eb1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:37.265802Z","signature_b64":"acEat53lDh/OIADbu8jKk2hDiXmh0JLb6mGn38zcqkZDcZGgPKMXfTmQg4Gkud3JnXB73WS/DxCsSWkedBUqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f611f387c31e51f3a87de5e4c26baba9d3be796f97a2ac31bc86afcf3d71eb1d","last_reissued_at":"2026-05-18T00:47:37.265254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:37.265254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.10349","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":"2026-05-18T00:47:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wg7REpo1Se+00PBx+CT6wLkAHsUDAWue2136Lq+qP1Ua2xnOtrsd8aIvtc0kA4OQBIsl06iFcXJaEVHgevnMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:20:02.212099Z"},"content_sha256":"a0dde17f1dc1ae6094605bd62d33a2c78749b0a2db7ec822e56c9178bbc2917d","schema_version":"1.0","event_id":"sha256:a0dde17f1dc1ae6094605bd62d33a2c78749b0a2db7ec822e56c9178bbc2917d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6YI7HB6DDZI7HKD54XSME25LVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Entity Retrieval on Structured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Besnik Fetahu, Stefan Dietze, Ujwal Gadiraju","submitted_at":"2017-03-30T08:25:35Z","abstract_excerpt":"The increasing amount of data on the Web, in particular of Linked Data, has led to a diverse landscape of datasets, which make entity retrieval a challenging task. Explicit cross-dataset links, for instance to indicate co-references or related entities can significantly improve entity retrieval. However, only a small fraction of entities are interlinked through explicit statements. In this paper, we propose a two-fold entity retrieval approach. In a first, offline preprocessing step, we cluster entities based on the \\emph{x--means} and \\emph{spectral} clustering algorithms. In the second step,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10349","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":""},"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":"2026-05-18T00:47:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ZeF+Qb3Dp0UPZcZkaE2PY/BLB3PBJy8mSdmA/BB+cJz0YhWWzi46Ou5n1hcqga8lHGxSyQUE1q7qamnzlb4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:20:02.212464Z"},"content_sha256":"32705aa5603796b4f641bfb9326ced4452f17ec8fb49243f9d722825225fefd0","schema_version":"1.0","event_id":"sha256:32705aa5603796b4f641bfb9326ced4452f17ec8fb49243f9d722825225fefd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YI7HB6DDZI7HKD54XSME25LVH/bundle.json","state_url":"https://pith.science/pith/6YI7HB6DDZI7HKD54XSME25LVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YI7HB6DDZI7HKD54XSME25LVH/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":"2026-06-01T09:20:02Z","links":{"resolver":"https://pith.science/pith/6YI7HB6DDZI7HKD54XSME25LVH","bundle":"https://pith.science/pith/6YI7HB6DDZI7HKD54XSME25LVH/bundle.json","state":"https://pith.science/pith/6YI7HB6DDZI7HKD54XSME25LVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YI7HB6DDZI7HKD54XSME25LVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6YI7HB6DDZI7HKD54XSME25LVH","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":"bb08a2de3858faf6e61fa0a21c8286aca74e43f17a9959cbd32c416474d968a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-30T08:25:35Z","title_canon_sha256":"9e3858d2105813ed60777b6d3f283bddb744f3d379f730128ab7983147a8d602"},"schema_version":"1.0","source":{"id":"1703.10349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10349","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10349v1","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10349","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"6YI7HB6DDZI7","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6YI7HB6DDZI7HKD5","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6YI7HB6D","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:32705aa5603796b4f641bfb9326ced4452f17ec8fb49243f9d722825225fefd0","target":"graph","created_at":"2026-05-18T00:47:37Z","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"},"paper":{"abstract_excerpt":"The increasing amount of data on the Web, in particular of Linked Data, has led to a diverse landscape of datasets, which make entity retrieval a challenging task. Explicit cross-dataset links, for instance to indicate co-references or related entities can significantly improve entity retrieval. However, only a small fraction of entities are interlinked through explicit statements. In this paper, we propose a two-fold entity retrieval approach. In a first, offline preprocessing step, we cluster entities based on the \\emph{x--means} and \\emph{spectral} clustering algorithms. In the second step,","authors_text":"Besnik Fetahu, Stefan Dietze, Ujwal Gadiraju","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-30T08:25:35Z","title":"Improving Entity Retrieval on Structured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10349","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:a0dde17f1dc1ae6094605bd62d33a2c78749b0a2db7ec822e56c9178bbc2917d","target":"record","created_at":"2026-05-18T00:47:37Z","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":"bb08a2de3858faf6e61fa0a21c8286aca74e43f17a9959cbd32c416474d968a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-30T08:25:35Z","title_canon_sha256":"9e3858d2105813ed60777b6d3f283bddb744f3d379f730128ab7983147a8d602"},"schema_version":"1.0","source":{"id":"1703.10349","kind":"arxiv","version":1}},"canonical_sha256":"f611f387c31e51f3a87de5e4c26baba9d3be796f97a2ac31bc86afcf3d71eb1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f611f387c31e51f3a87de5e4c26baba9d3be796f97a2ac31bc86afcf3d71eb1d","first_computed_at":"2026-05-18T00:47:37.265254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:37.265254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"acEat53lDh/OIADbu8jKk2hDiXmh0JLb6mGn38zcqkZDcZGgPKMXfTmQg4Gkud3JnXB73WS/DxCsSWkedBUqDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:37.265802Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.10349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0dde17f1dc1ae6094605bd62d33a2c78749b0a2db7ec822e56c9178bbc2917d","sha256:32705aa5603796b4f641bfb9326ced4452f17ec8fb49243f9d722825225fefd0"],"state_sha256":"3e1bd976a1cf6cb2e17ab75f76a625ef87b100e9c2894c293a7ba674313918a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asNRxPPE70aNK6NgYYnw/ndvwfsxADXfD5AmEcpPJdRZr6KXYC2vy6wUAwfkeAYGDcig1Me8BzN3gqezNHsWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T09:20:02.214414Z","bundle_sha256":"0c43b993ff634ebd2afc7318bddcc4f6c756c20feec9f70bc01d613752be44e0"}}