{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:B4NHTUCHUVVIOXGPPPBNDB3W4F","short_pith_number":"pith:B4NHTUCH","canonical_record":{"source":{"id":"1602.06223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2016-02-19T17:07:24Z","cross_cats_sorted":[],"title_canon_sha256":"af003ffc1a62e52418bc4e24fa0b11fecb1767710521e616ff779c5df3c090f4","abstract_canon_sha256":"da924923126e6fb3548615007286e567d4a3a2fef081b20a28d62c6b28666dc8"},"schema_version":"1.0"},"canonical_sha256":"0f1a79d047a56a875ccf7bc2d18776e17916617446471303056a5742cb65a929","source":{"kind":"arxiv","id":"1602.06223","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.06223","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"1602.06223v2","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06223","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"B4NHTUCHUVVI","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"B4NHTUCHUVVIOXGP","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"B4NHTUCH","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:B4NHTUCHUVVIOXGPPPBNDB3W4F","target":"record","payload":{"canonical_record":{"source":{"id":"1602.06223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2016-02-19T17:07:24Z","cross_cats_sorted":[],"title_canon_sha256":"af003ffc1a62e52418bc4e24fa0b11fecb1767710521e616ff779c5df3c090f4","abstract_canon_sha256":"da924923126e6fb3548615007286e567d4a3a2fef081b20a28d62c6b28666dc8"},"schema_version":"1.0"},"canonical_sha256":"0f1a79d047a56a875ccf7bc2d18776e17916617446471303056a5742cb65a929","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:07.829040Z","signature_b64":"BDl3ZAGOHGK/l5rjUijrOHQCn8hmmP5ZVQtj32km/gj6ep/isFfazyo2krsRACnHFcsoWs1/NALT1Q3FKAW+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1a79d047a56a875ccf7bc2d18776e17916617446471303056a5742cb65a929","last_reissued_at":"2026-05-18T01:20:07.828413Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:07.828413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.06223","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:20:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZPxnQNCpuOif+SL5fvlhphZPKv9iADkkfccgEUzN5CcXBVUhWHzW/n6xxn7TPaHgBTPCwIgcpyLcqCipogsSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:32:45.661617Z"},"content_sha256":"5813dc36798dc87b707e35dbfd5e07089fea70871818feadbb6c5d951043ac54","schema_version":"1.0","event_id":"sha256:5813dc36798dc87b707e35dbfd5e07089fea70871818feadbb6c5d951043ac54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:B4NHTUCHUVVIOXGPPPBNDB3W4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rules of Acquisition for Mementos and Their Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"Harihar Shankar, Shawn M. Jones","submitted_at":"2016-02-19T17:07:24Z","abstract_excerpt":"Text extraction from web pages has many applications, including web crawling optimization and document clustering. Though much has been written about the acquisition of content from live web pages, content acquisition of archived web pages, known as mementos, remains a relatively new enterprise. In the course of conducting a study with almost 700,000 web pages, we encountered issues acquiring mementos and extracting text from them. The acquisition of memento content via HTTP is expected to be a relatively painless exercise, but we have found cases to the contrary. We also find that the parsing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06223","kind":"arxiv","version":2},"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":"2026-05-18T01:20:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cx0XYmjgZZ7Dzz6JYBdjLXE6iDSkmp6jdseaqr7Q8PrWTuEY0khqIF/gQ+w2kWOVBBx+BgbjQNox+QiDjsR5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:32:45.661962Z"},"content_sha256":"d6edb37382fccc598ba5e0bb1066b2e9887a34399a90b742fa62283572aaea30","schema_version":"1.0","event_id":"sha256:d6edb37382fccc598ba5e0bb1066b2e9887a34399a90b742fa62283572aaea30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B4NHTUCHUVVIOXGPPPBNDB3W4F/bundle.json","state_url":"https://pith.science/pith/B4NHTUCHUVVIOXGPPPBNDB3W4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B4NHTUCHUVVIOXGPPPBNDB3W4F/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":"2026-06-01T23:32:45Z","links":{"resolver":"https://pith.science/pith/B4NHTUCHUVVIOXGPPPBNDB3W4F","bundle":"https://pith.science/pith/B4NHTUCHUVVIOXGPPPBNDB3W4F/bundle.json","state":"https://pith.science/pith/B4NHTUCHUVVIOXGPPPBNDB3W4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B4NHTUCHUVVIOXGPPPBNDB3W4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:B4NHTUCHUVVIOXGPPPBNDB3W4F","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":"da924923126e6fb3548615007286e567d4a3a2fef081b20a28d62c6b28666dc8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2016-02-19T17:07:24Z","title_canon_sha256":"af003ffc1a62e52418bc4e24fa0b11fecb1767710521e616ff779c5df3c090f4"},"schema_version":"1.0","source":{"id":"1602.06223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.06223","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"1602.06223v2","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06223","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"B4NHTUCHUVVI","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"B4NHTUCHUVVIOXGP","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"B4NHTUCH","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:d6edb37382fccc598ba5e0bb1066b2e9887a34399a90b742fa62283572aaea30","target":"graph","created_at":"2026-05-18T01:20:07Z","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":"Text extraction from web pages has many applications, including web crawling optimization and document clustering. Though much has been written about the acquisition of content from live web pages, content acquisition of archived web pages, known as mementos, remains a relatively new enterprise. In the course of conducting a study with almost 700,000 web pages, we encountered issues acquiring mementos and extracting text from them. The acquisition of memento content via HTTP is expected to be a relatively painless exercise, but we have found cases to the contrary. We also find that the parsing","authors_text":"Harihar Shankar, Shawn M. Jones","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2016-02-19T17:07:24Z","title":"Rules of Acquisition for Mementos and Their Content"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06223","kind":"arxiv","version":2},"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":"sha256:5813dc36798dc87b707e35dbfd5e07089fea70871818feadbb6c5d951043ac54","target":"record","created_at":"2026-05-18T01:20:07Z","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":"da924923126e6fb3548615007286e567d4a3a2fef081b20a28d62c6b28666dc8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2016-02-19T17:07:24Z","title_canon_sha256":"af003ffc1a62e52418bc4e24fa0b11fecb1767710521e616ff779c5df3c090f4"},"schema_version":"1.0","source":{"id":"1602.06223","kind":"arxiv","version":2}},"canonical_sha256":"0f1a79d047a56a875ccf7bc2d18776e17916617446471303056a5742cb65a929","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f1a79d047a56a875ccf7bc2d18776e17916617446471303056a5742cb65a929","first_computed_at":"2026-05-18T01:20:07.828413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:07.828413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDl3ZAGOHGK/l5rjUijrOHQCn8hmmP5ZVQtj32km/gj6ep/isFfazyo2krsRACnHFcsoWs1/NALT1Q3FKAW+BA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:07.829040Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.06223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5813dc36798dc87b707e35dbfd5e07089fea70871818feadbb6c5d951043ac54","sha256:d6edb37382fccc598ba5e0bb1066b2e9887a34399a90b742fa62283572aaea30"],"state_sha256":"950dcfcdb5a31e72a003b5334a9063d8e04e58231fe15896805e5d481f3b8835"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0REmK9WTOtlIdlLhSbpa8bneUctPzSZXCOGVoVGT7kqCyxoGfe+x8IerWAywKaBpEIlkqYXGn4WgJDzUlKMbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T23:32:45.663902Z","bundle_sha256":"5f1eae3c43871f08e617683caee2328efada454311d2b40d8b118bb03367f94e"}}