{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZEYUWJBILBKU6LCZVFU4VG4NMQ","short_pith_number":"pith:ZEYUWJBI","canonical_record":{"source":{"id":"1702.00619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-02T11:09:53Z","cross_cats_sorted":[],"title_canon_sha256":"f0bd6892ea94dbe9c241a2de8296686207e59450ff3e98962f1dd14d87b950d6","abstract_canon_sha256":"b75e6364d772d6545ab727c28e0e3862c5cfb5f38d7093f0a2e63c66600f7d89"},"schema_version":"1.0"},"canonical_sha256":"c9314b242858554f2c59a969ca9b8d6429e0a3e35fc1ffbe2b794e99e4de45ac","source":{"kind":"arxiv","id":"1702.00619","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00619","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00619v1","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00619","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZEYUWJBILBKU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZEYUWJBILBKU6LCZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZEYUWJBI","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZEYUWJBILBKU6LCZVFU4VG4NMQ","target":"record","payload":{"canonical_record":{"source":{"id":"1702.00619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-02T11:09:53Z","cross_cats_sorted":[],"title_canon_sha256":"f0bd6892ea94dbe9c241a2de8296686207e59450ff3e98962f1dd14d87b950d6","abstract_canon_sha256":"b75e6364d772d6545ab727c28e0e3862c5cfb5f38d7093f0a2e63c66600f7d89"},"schema_version":"1.0"},"canonical_sha256":"c9314b242858554f2c59a969ca9b8d6429e0a3e35fc1ffbe2b794e99e4de45ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:33.086579Z","signature_b64":"t8J6DxYm2YYh5rU+/tXU+evMwZ9j6t7Ol7RNO1umWT2gcqQFBZF7dgAaaP/6hHj3yjOu+b/ExkiBroF9vWn7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9314b242858554f2c59a969ca9b8d6429e0a3e35fc1ffbe2b794e99e4de45ac","last_reissued_at":"2026-05-18T00:51:33.086058Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:33.086058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.00619","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":"2026-05-18T00:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ao8lRU9JsMCjHlmCMrU5Xe1y/DkvDgRncDbGakH5FrvM4j3ep4pnTZ4CmEhHB6FoD3fP2bLkag2X4iR5ZwxgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:14:49.876411Z"},"content_sha256":"f166225acfce54c199f34cb79a43cfada3a72ffaa385d756d7efeb2c224b992f","schema_version":"1.0","event_id":"sha256:f166225acfce54c199f34cb79a43cfada3a72ffaa385d756d7efeb2c224b992f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZEYUWJBILBKU6LCZVFU4VG4NMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Elena Demidova, Gerhard Gossen, Helge Holzmann, Julian Szymanski, Tarcisio Souza, Thomas Risse","submitted_at":"2017-02-02T11:09:53Z","abstract_excerpt":"Long-term Web archives comprise Web documents gathered over longer time periods and can easily reach hundreds of terabytes in size. Semantic annotations such as named entities can facilitate intelligent access to the Web archive data. However, the annotation of the entire archive content on this scale is often infeasible. The most efficient way to access the documents within Web archives is provided through their URLs, which are typically stored in dedicated index files.The URLs of the archived Web documents can contain semantic information and can offer an efficient way to obtain initial sema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00619","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":"2026-05-18T00:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ThfP+OJ8Y4nC0PZoIzjE4JNKBdQMJ2xz4LsJFiEtvyjcP0bF1syS66cI2pEQWjz50P3w98UuQVvfaskKikUiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:14:49.876760Z"},"content_sha256":"be3b21bf6ed05a0b4bc8a9fa6094132e56c61b7f3b5eb043977e3c2794ca7adc","schema_version":"1.0","event_id":"sha256:be3b21bf6ed05a0b4bc8a9fa6094132e56c61b7f3b5eb043977e3c2794ca7adc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEYUWJBILBKU6LCZVFU4VG4NMQ/bundle.json","state_url":"https://pith.science/pith/ZEYUWJBILBKU6LCZVFU4VG4NMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEYUWJBILBKU6LCZVFU4VG4NMQ/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":"2026-05-28T14:14:49Z","links":{"resolver":"https://pith.science/pith/ZEYUWJBILBKU6LCZVFU4VG4NMQ","bundle":"https://pith.science/pith/ZEYUWJBILBKU6LCZVFU4VG4NMQ/bundle.json","state":"https://pith.science/pith/ZEYUWJBILBKU6LCZVFU4VG4NMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEYUWJBILBKU6LCZVFU4VG4NMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZEYUWJBILBKU6LCZVFU4VG4NMQ","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":"b75e6364d772d6545ab727c28e0e3862c5cfb5f38d7093f0a2e63c66600f7d89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-02T11:09:53Z","title_canon_sha256":"f0bd6892ea94dbe9c241a2de8296686207e59450ff3e98962f1dd14d87b950d6"},"schema_version":"1.0","source":{"id":"1702.00619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00619","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00619v1","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00619","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZEYUWJBILBKU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZEYUWJBILBKU6LCZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZEYUWJBI","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:be3b21bf6ed05a0b4bc8a9fa6094132e56c61b7f3b5eb043977e3c2794ca7adc","target":"graph","created_at":"2026-05-18T00:51:33Z","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":"Long-term Web archives comprise Web documents gathered over longer time periods and can easily reach hundreds of terabytes in size. Semantic annotations such as named entities can facilitate intelligent access to the Web archive data. However, the annotation of the entire archive content on this scale is often infeasible. The most efficient way to access the documents within Web archives is provided through their URLs, which are typically stored in dedicated index files.The URLs of the archived Web documents can contain semantic information and can offer an efficient way to obtain initial sema","authors_text":"Elena Demidova, Gerhard Gossen, Helge Holzmann, Julian Szymanski, Tarcisio Souza, Thomas Risse","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-02T11:09:53Z","title":"Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00619","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:f166225acfce54c199f34cb79a43cfada3a72ffaa385d756d7efeb2c224b992f","target":"record","created_at":"2026-05-18T00:51:33Z","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":"b75e6364d772d6545ab727c28e0e3862c5cfb5f38d7093f0a2e63c66600f7d89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-02T11:09:53Z","title_canon_sha256":"f0bd6892ea94dbe9c241a2de8296686207e59450ff3e98962f1dd14d87b950d6"},"schema_version":"1.0","source":{"id":"1702.00619","kind":"arxiv","version":1}},"canonical_sha256":"c9314b242858554f2c59a969ca9b8d6429e0a3e35fc1ffbe2b794e99e4de45ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9314b242858554f2c59a969ca9b8d6429e0a3e35fc1ffbe2b794e99e4de45ac","first_computed_at":"2026-05-18T00:51:33.086058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:33.086058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t8J6DxYm2YYh5rU+/tXU+evMwZ9j6t7Ol7RNO1umWT2gcqQFBZF7dgAaaP/6hHj3yjOu+b/ExkiBroF9vWn7CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:33.086579Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.00619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f166225acfce54c199f34cb79a43cfada3a72ffaa385d756d7efeb2c224b992f","sha256:be3b21bf6ed05a0b4bc8a9fa6094132e56c61b7f3b5eb043977e3c2794ca7adc"],"state_sha256":"39a9f16d6d0f6b628ad1fd57d585cb4d1287ce22dd0c196f1d1f33c21384f1f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VLlQr+VoPYKkLiZWTOfXivJfaYVQ+W681phHkXXNj8HoK9S7S5ktmIM3pzoNa9CGmZjgaPICrCbiXpl5J+DMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:14:49.878808Z","bundle_sha256":"48c821137fcfc15bdc54bc177aca4a63f70dff44d9d1998b5023958089b5ff79"}}