{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UZW55XKICVPZJZIB7GLUFK5TUE","short_pith_number":"pith:UZW55XKI","canonical_record":{"source":{"id":"1811.10422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-11-22T12:55:40Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"80cfbb81add34bbc4c13a4375c040b8a7b570965003d4d38f9fa031b072b1733","abstract_canon_sha256":"b34201ce1971c7f68049ea814af0cdd4e74ecf177514d06c363d608da2b6f914"},"schema_version":"1.0"},"canonical_sha256":"a66ddedd48155f94e501f99742abb3a13d82f8a4d7c15d32916c9be950e3c923","source":{"kind":"arxiv","id":"1811.10422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10422","created_at":"2026-05-17T23:59:56Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10422v1","created_at":"2026-05-17T23:59:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10422","created_at":"2026-05-17T23:59:56Z"},{"alias_kind":"pith_short_12","alias_value":"UZW55XKICVPZ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UZW55XKICVPZJZIB","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UZW55XKI","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UZW55XKICVPZJZIB7GLUFK5TUE","target":"record","payload":{"canonical_record":{"source":{"id":"1811.10422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-11-22T12:55:40Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"80cfbb81add34bbc4c13a4375c040b8a7b570965003d4d38f9fa031b072b1733","abstract_canon_sha256":"b34201ce1971c7f68049ea814af0cdd4e74ecf177514d06c363d608da2b6f914"},"schema_version":"1.0"},"canonical_sha256":"a66ddedd48155f94e501f99742abb3a13d82f8a4d7c15d32916c9be950e3c923","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:56.509788Z","signature_b64":"Hd69KJq53e3y/odxtBY20s0/M1qRyF+zDht7WB2VSRCkyZJiC3GGgQl4mwVG56+BbQrKiZi1aFIn9H8Ma9kCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a66ddedd48155f94e501f99742abb3a13d82f8a4d7c15d32916c9be950e3c923","last_reissued_at":"2026-05-17T23:59:56.509257Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:56.509257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.10422","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":"2026-05-17T23:59:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Roz0DVs+Axi6vRq7ut5vAwWxeZd+p0pEDVmf2xhA/jX9F+jJ62zHpDUZuAWYq4R7Xtlf273bvz2ZLUmg1ckAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T13:10:31.134920Z"},"content_sha256":"08064d184ee902cfa8ea3852f97ea6012c39f84bc18ee8b269de003c7c5a50b5","schema_version":"1.0","event_id":"sha256:08064d184ee902cfa8ea3852f97ea6012c39f84bc18ee8b269de003c7c5a50b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UZW55XKICVPZJZIB7GLUFK5TUE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Creating a contemporary corpus of similes in Serbian by using natural language processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Goran Nenadic, Nikola Milosevic","submitted_at":"2018-11-22T12:55:40Z","abstract_excerpt":"Simile is a figure of speech that compares two things through the use of connection words, but where comparison is not intended to be taken literally. They are often used in everyday communication, but they are also a part of linguistic cultural heritage. In this paper we present a methodology for semi-automated collection of similes from the World Wide Web using text mining and machine learning techniques. We expanded an existing corpus by collecting 442 similes from the internet and adding them to the existing corpus collected by Vuk Stefanovic Karadzic that contained 333 similes. We, also, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10422","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":"2026-05-17T23:59:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xe3f9pioLIzsa/JU4jv7CPn9huXPua5pch3BhrsU9J5b+0YqRIuPjaLMgR9PA3yaCjt2MpcBmsghDM0OhCP0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T13:10:31.135290Z"},"content_sha256":"26e5872e4e11280b16313eac194dc5e136e2627bc4016eb3d45f98bfbfe917b7","schema_version":"1.0","event_id":"sha256:26e5872e4e11280b16313eac194dc5e136e2627bc4016eb3d45f98bfbfe917b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UZW55XKICVPZJZIB7GLUFK5TUE/bundle.json","state_url":"https://pith.science/pith/UZW55XKICVPZJZIB7GLUFK5TUE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UZW55XKICVPZJZIB7GLUFK5TUE/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":"2026-06-03T13:10:31Z","links":{"resolver":"https://pith.science/pith/UZW55XKICVPZJZIB7GLUFK5TUE","bundle":"https://pith.science/pith/UZW55XKICVPZJZIB7GLUFK5TUE/bundle.json","state":"https://pith.science/pith/UZW55XKICVPZJZIB7GLUFK5TUE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UZW55XKICVPZJZIB7GLUFK5TUE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UZW55XKICVPZJZIB7GLUFK5TUE","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":"b34201ce1971c7f68049ea814af0cdd4e74ecf177514d06c363d608da2b6f914","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-11-22T12:55:40Z","title_canon_sha256":"80cfbb81add34bbc4c13a4375c040b8a7b570965003d4d38f9fa031b072b1733"},"schema_version":"1.0","source":{"id":"1811.10422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10422","created_at":"2026-05-17T23:59:56Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10422v1","created_at":"2026-05-17T23:59:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10422","created_at":"2026-05-17T23:59:56Z"},{"alias_kind":"pith_short_12","alias_value":"UZW55XKICVPZ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UZW55XKICVPZJZIB","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UZW55XKI","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:26e5872e4e11280b16313eac194dc5e136e2627bc4016eb3d45f98bfbfe917b7","target":"graph","created_at":"2026-05-17T23:59:56Z","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":"Simile is a figure of speech that compares two things through the use of connection words, but where comparison is not intended to be taken literally. They are often used in everyday communication, but they are also a part of linguistic cultural heritage. In this paper we present a methodology for semi-automated collection of similes from the World Wide Web using text mining and machine learning techniques. We expanded an existing corpus by collecting 442 similes from the internet and adding them to the existing corpus collected by Vuk Stefanovic Karadzic that contained 333 similes. We, also, ","authors_text":"Goran Nenadic, Nikola Milosevic","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-11-22T12:55:40Z","title":"Creating a contemporary corpus of similes in Serbian by using natural language processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10422","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":"sha256:08064d184ee902cfa8ea3852f97ea6012c39f84bc18ee8b269de003c7c5a50b5","target":"record","created_at":"2026-05-17T23:59:56Z","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":"b34201ce1971c7f68049ea814af0cdd4e74ecf177514d06c363d608da2b6f914","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-11-22T12:55:40Z","title_canon_sha256":"80cfbb81add34bbc4c13a4375c040b8a7b570965003d4d38f9fa031b072b1733"},"schema_version":"1.0","source":{"id":"1811.10422","kind":"arxiv","version":1}},"canonical_sha256":"a66ddedd48155f94e501f99742abb3a13d82f8a4d7c15d32916c9be950e3c923","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a66ddedd48155f94e501f99742abb3a13d82f8a4d7c15d32916c9be950e3c923","first_computed_at":"2026-05-17T23:59:56.509257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:56.509257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hd69KJq53e3y/odxtBY20s0/M1qRyF+zDht7WB2VSRCkyZJiC3GGgQl4mwVG56+BbQrKiZi1aFIn9H8Ma9kCCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:56.509788Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08064d184ee902cfa8ea3852f97ea6012c39f84bc18ee8b269de003c7c5a50b5","sha256:26e5872e4e11280b16313eac194dc5e136e2627bc4016eb3d45f98bfbfe917b7"],"state_sha256":"b08e04741022b060266b4aea87ab39e41c63b852b62f6ec72703f72183a6df93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fw3090uaQMUhOTIJdIAqC+XfeGDT6o8QnosPk0c6TV8DnQgihc48052P1cQYhSCzrL4+DcpqY1VO0C5VE4HSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T13:10:31.137277Z","bundle_sha256":"8a9b5f9a3712c7d70e6619edd5bee8487fa5ef1bc782e75b91b216bddbc323a6"}}