{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6PFCXVRTGDBQAWZZLEVCKDMSEV","short_pith_number":"pith:6PFCXVRT","canonical_record":{"source":{"id":"1804.01603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-04T20:40:47Z","cross_cats_sorted":[],"title_canon_sha256":"b76f5c45ab905b800568da2348fe8a147481b587a1f86ed8957ba8de844e4ce3","abstract_canon_sha256":"e950809d77100a7f87d79078bd1ff34bffd8f7848a2359026b9c04356447e4cb"},"schema_version":"1.0"},"canonical_sha256":"f3ca2bd63330c3005b39592a250d9225697c737fcd07b03ced5b48efc06cc9e7","source":{"kind":"arxiv","id":"1804.01603","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01603","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01603v1","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01603","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"6PFCXVRTGDBQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6PFCXVRTGDBQAWZZ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6PFCXVRT","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6PFCXVRTGDBQAWZZLEVCKDMSEV","target":"record","payload":{"canonical_record":{"source":{"id":"1804.01603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-04T20:40:47Z","cross_cats_sorted":[],"title_canon_sha256":"b76f5c45ab905b800568da2348fe8a147481b587a1f86ed8957ba8de844e4ce3","abstract_canon_sha256":"e950809d77100a7f87d79078bd1ff34bffd8f7848a2359026b9c04356447e4cb"},"schema_version":"1.0"},"canonical_sha256":"f3ca2bd63330c3005b39592a250d9225697c737fcd07b03ced5b48efc06cc9e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:10.744146Z","signature_b64":"C3FufSmT926D/hl4Sz8aXXgX4j4jNJ5rr1dZLf3aH7MX++uOlStArThZHEGv6omF5RJDAgvei+6XDtI+rz3yDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3ca2bd63330c3005b39592a250d9225697c737fcd07b03ced5b48efc06cc9e7","last_reissued_at":"2026-05-18T00:19:10.743529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:10.743529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.01603","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":"2026-05-18T00:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"osIUos/kWhX88Kt6QT+bvKfD/AMjbtdMWy1+GGCV59vNC/1CdOsgHzu2YpDGNlNV+gKfB+PFbvY52jJICp51DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:57:33.752402Z"},"content_sha256":"0890fbd947ec30f5525c8ba47190a0f5164d21f8636cec6f1fbd7b4f599d7bc2","schema_version":"1.0","event_id":"sha256:0890fbd947ec30f5525c8ba47190a0f5164d21f8636cec6f1fbd7b4f599d7bc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6PFCXVRTGDBQAWZZLEVCKDMSEV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Focused Crawl of Web Archives to Build Event Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"Herbert Van de Sompel, Lyudmila Balakireva, Martin Klein","submitted_at":"2018-04-04T20:40:47Z","abstract_excerpt":"Event collections are frequently built by crawling the live web on the basis of seed URIs nominated by human experts. Focused web crawling is a technique where the crawler is guided by reference content pertaining to the event. Given the dynamic nature of the web and the pace with which topics evolve, the timing of the crawl is a concern for both approaches. We investigate the feasibility of performing focused crawls on the archived web. By utilizing the Memento infrastructure, we obtain resources from 22 web archives that contribute to building event collections. We create collections on four"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01603","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":"2026-05-18T00:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3JvUfnhI26H8+W/48Jj4A4ktr6KK6eN864OGOpiXA7In1J+AfjRKUfNVSA482ArEbGxnjJVcjkAyQ/bO0MelCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:57:33.753309Z"},"content_sha256":"1220bebf52822a46031714fa6989863b9a006e324d3d9f13df8da686c39e926b","schema_version":"1.0","event_id":"sha256:1220bebf52822a46031714fa6989863b9a006e324d3d9f13df8da686c39e926b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PFCXVRTGDBQAWZZLEVCKDMSEV/bundle.json","state_url":"https://pith.science/pith/6PFCXVRTGDBQAWZZLEVCKDMSEV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PFCXVRTGDBQAWZZLEVCKDMSEV/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":"2026-05-31T18:57:33Z","links":{"resolver":"https://pith.science/pith/6PFCXVRTGDBQAWZZLEVCKDMSEV","bundle":"https://pith.science/pith/6PFCXVRTGDBQAWZZLEVCKDMSEV/bundle.json","state":"https://pith.science/pith/6PFCXVRTGDBQAWZZLEVCKDMSEV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PFCXVRTGDBQAWZZLEVCKDMSEV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6PFCXVRTGDBQAWZZLEVCKDMSEV","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":"e950809d77100a7f87d79078bd1ff34bffd8f7848a2359026b9c04356447e4cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-04T20:40:47Z","title_canon_sha256":"b76f5c45ab905b800568da2348fe8a147481b587a1f86ed8957ba8de844e4ce3"},"schema_version":"1.0","source":{"id":"1804.01603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01603","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01603v1","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01603","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"6PFCXVRTGDBQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6PFCXVRTGDBQAWZZ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6PFCXVRT","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:1220bebf52822a46031714fa6989863b9a006e324d3d9f13df8da686c39e926b","target":"graph","created_at":"2026-05-18T00:19:10Z","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":"Event collections are frequently built by crawling the live web on the basis of seed URIs nominated by human experts. Focused web crawling is a technique where the crawler is guided by reference content pertaining to the event. Given the dynamic nature of the web and the pace with which topics evolve, the timing of the crawl is a concern for both approaches. We investigate the feasibility of performing focused crawls on the archived web. By utilizing the Memento infrastructure, we obtain resources from 22 web archives that contribute to building event collections. We create collections on four","authors_text":"Herbert Van de Sompel, Lyudmila Balakireva, Martin Klein","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-04T20:40:47Z","title":"Focused Crawl of Web Archives to Build Event Collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01603","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":"sha256:0890fbd947ec30f5525c8ba47190a0f5164d21f8636cec6f1fbd7b4f599d7bc2","target":"record","created_at":"2026-05-18T00:19:10Z","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":"e950809d77100a7f87d79078bd1ff34bffd8f7848a2359026b9c04356447e4cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-04T20:40:47Z","title_canon_sha256":"b76f5c45ab905b800568da2348fe8a147481b587a1f86ed8957ba8de844e4ce3"},"schema_version":"1.0","source":{"id":"1804.01603","kind":"arxiv","version":1}},"canonical_sha256":"f3ca2bd63330c3005b39592a250d9225697c737fcd07b03ced5b48efc06cc9e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3ca2bd63330c3005b39592a250d9225697c737fcd07b03ced5b48efc06cc9e7","first_computed_at":"2026-05-18T00:19:10.743529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:10.743529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C3FufSmT926D/hl4Sz8aXXgX4j4jNJ5rr1dZLf3aH7MX++uOlStArThZHEGv6omF5RJDAgvei+6XDtI+rz3yDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:10.744146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0890fbd947ec30f5525c8ba47190a0f5164d21f8636cec6f1fbd7b4f599d7bc2","sha256:1220bebf52822a46031714fa6989863b9a006e324d3d9f13df8da686c39e926b"],"state_sha256":"4e42b91484ab6317b16fcc56578e9c0751dd7e27a9d36f120f1c4c4803bb46ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZZPjBT5Yrv6dMohKR8NLIv9ndVt9a+5mdXymrxVk/ZwYy1HrshHX07L3KO0nKOp7SrsUjraTwchNsQ8/PjcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:57:33.756160Z","bundle_sha256":"0d056e7327b43d95028a8c6b888f17d8e9a98094b81c126fc1c0fa2a936dbffb"}}