{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:XFK5YX3HFCO4XO6T7P7KKNRGHD","short_pith_number":"pith:XFK5YX3H","canonical_record":{"source":{"id":"1605.09362","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-05-30T19:40:18Z","cross_cats_sorted":[],"title_canon_sha256":"7c62933fc77f420e48aa7ef4ab9e9897b6db03e11c05fcdbc050fdc63e9e3231","abstract_canon_sha256":"e8e071cf97f7ad94481c296d8992b57f8e02df379a2f07928c5f5a9766eeafdf"},"schema_version":"1.0"},"canonical_sha256":"b955dc5f67289dcbbbd3fbfea5362638e3de1276523aa4647188f1002a6454f1","source":{"kind":"arxiv","id":"1605.09362","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.09362","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"1605.09362v3","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09362","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"XFK5YX3HFCO4","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XFK5YX3HFCO4XO6T","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XFK5YX3H","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:XFK5YX3HFCO4XO6T7P7KKNRGHD","target":"record","payload":{"canonical_record":{"source":{"id":"1605.09362","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-05-30T19:40:18Z","cross_cats_sorted":[],"title_canon_sha256":"7c62933fc77f420e48aa7ef4ab9e9897b6db03e11c05fcdbc050fdc63e9e3231","abstract_canon_sha256":"e8e071cf97f7ad94481c296d8992b57f8e02df379a2f07928c5f5a9766eeafdf"},"schema_version":"1.0"},"canonical_sha256":"b955dc5f67289dcbbbd3fbfea5362638e3de1276523aa4647188f1002a6454f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:13.773332Z","signature_b64":"+dyr8+KTZ4CpHUubZNE/F5Aq0Y4mGaFGOi3K36+rerzXfr93PlKy6f/hCFwgvr6i2m/Jc2tmEl+DKJFapfNaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b955dc5f67289dcbbbd3fbfea5362638e3de1276523aa4647188f1002a6454f1","last_reissued_at":"2026-05-18T00:44:13.772856Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:13.772856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.09362","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oNyvrvO4d0GA+IH2GHh0ajimOvlnHUl0WOowh6Jub1c7QetaW7gyE5AXvowY/em8wATG+zsatKR+ojg8oIO2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:08:54.759622Z"},"content_sha256":"480483e9282f45e7e96d51345e3957e1c34df14344bcf941e3540a1875c2b215","schema_version":"1.0","event_id":"sha256:480483e9282f45e7e96d51345e3957e1c34df14344bcf941e3540a1875c2b215"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:XFK5YX3HFCO4XO6T7P7KKNRGHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Document Retrieval on Repetitive String Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aleksi Hartikainen, Gonzalo Navarro, Jouni Sir\\'en, Juha K\\\"arkk\\\"ainen, Kalle Karhu, Simon J. Puglisi, Travis Gagie","submitted_at":"2016-05-30T19:40:18Z","abstract_excerpt":"Most of the fastest-growing string collections today are repetitive, that is, most of the constituent documents are similar to many others. As these collections keep growing, a key approach to handling them is to exploit their repetitiveness, which can reduce their space usage by orders of magnitude. We study the problem of indexing repetitive string collections in order to perform efficient document retrieval operations on them. Document retrieval problems are routinely solved by search engines on large natural language collections, but the techniques are less developed on generic string coll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09362","kind":"arxiv","version":3},"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":"2026-05-18T00:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mK62OJ20sU0hzPUJ2/H+Mt7Zt1lDZLMUn56McEnmqBSJk/V/gQfbM7VyRNCxbJxj9kjVZTNVSJe9MEVpUpMcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:08:54.759967Z"},"content_sha256":"df27dbfc9ac8e5ca8c79eddb5f16d7fe1f880b25143857f6a0be7b7844356b85","schema_version":"1.0","event_id":"sha256:df27dbfc9ac8e5ca8c79eddb5f16d7fe1f880b25143857f6a0be7b7844356b85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFK5YX3HFCO4XO6T7P7KKNRGHD/bundle.json","state_url":"https://pith.science/pith/XFK5YX3HFCO4XO6T7P7KKNRGHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFK5YX3HFCO4XO6T7P7KKNRGHD/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":"2026-06-04T10:08:54Z","links":{"resolver":"https://pith.science/pith/XFK5YX3HFCO4XO6T7P7KKNRGHD","bundle":"https://pith.science/pith/XFK5YX3HFCO4XO6T7P7KKNRGHD/bundle.json","state":"https://pith.science/pith/XFK5YX3HFCO4XO6T7P7KKNRGHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFK5YX3HFCO4XO6T7P7KKNRGHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XFK5YX3HFCO4XO6T7P7KKNRGHD","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":"e8e071cf97f7ad94481c296d8992b57f8e02df379a2f07928c5f5a9766eeafdf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-05-30T19:40:18Z","title_canon_sha256":"7c62933fc77f420e48aa7ef4ab9e9897b6db03e11c05fcdbc050fdc63e9e3231"},"schema_version":"1.0","source":{"id":"1605.09362","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.09362","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"1605.09362v3","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09362","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"XFK5YX3HFCO4","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XFK5YX3HFCO4XO6T","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XFK5YX3H","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:df27dbfc9ac8e5ca8c79eddb5f16d7fe1f880b25143857f6a0be7b7844356b85","target":"graph","created_at":"2026-05-18T00:44:13Z","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":"Most of the fastest-growing string collections today are repetitive, that is, most of the constituent documents are similar to many others. As these collections keep growing, a key approach to handling them is to exploit their repetitiveness, which can reduce their space usage by orders of magnitude. We study the problem of indexing repetitive string collections in order to perform efficient document retrieval operations on them. Document retrieval problems are routinely solved by search engines on large natural language collections, but the techniques are less developed on generic string coll","authors_text":"Aleksi Hartikainen, Gonzalo Navarro, Jouni Sir\\'en, Juha K\\\"arkk\\\"ainen, Kalle Karhu, Simon J. Puglisi, Travis Gagie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-05-30T19:40:18Z","title":"Document Retrieval on Repetitive String Collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09362","kind":"arxiv","version":3},"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":"sha256:480483e9282f45e7e96d51345e3957e1c34df14344bcf941e3540a1875c2b215","target":"record","created_at":"2026-05-18T00:44:13Z","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":"e8e071cf97f7ad94481c296d8992b57f8e02df379a2f07928c5f5a9766eeafdf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-05-30T19:40:18Z","title_canon_sha256":"7c62933fc77f420e48aa7ef4ab9e9897b6db03e11c05fcdbc050fdc63e9e3231"},"schema_version":"1.0","source":{"id":"1605.09362","kind":"arxiv","version":3}},"canonical_sha256":"b955dc5f67289dcbbbd3fbfea5362638e3de1276523aa4647188f1002a6454f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b955dc5f67289dcbbbd3fbfea5362638e3de1276523aa4647188f1002a6454f1","first_computed_at":"2026-05-18T00:44:13.772856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:13.772856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+dyr8+KTZ4CpHUubZNE/F5Aq0Y4mGaFGOi3K36+rerzXfr93PlKy6f/hCFwgvr6i2m/Jc2tmEl+DKJFapfNaBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:13.773332Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.09362","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:480483e9282f45e7e96d51345e3957e1c34df14344bcf941e3540a1875c2b215","sha256:df27dbfc9ac8e5ca8c79eddb5f16d7fe1f880b25143857f6a0be7b7844356b85"],"state_sha256":"1fd5d2053776fdb0ecbe0211ad23ba4414e41e217788a45ce19aacd9b1ee85b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oSXDuKDQV1tqF3k0b7bbj3CRfqnND7cvaW5L85r0//iNpikECNzCwgoRcO347J7e6gkB4ToHxvBTRaeeZ1PDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T10:08:54.761901Z","bundle_sha256":"ad5a4636df51237ce634d20cf738d97a51fc43103875eae56a2f52b9720eda00"}}