{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DGEOO6MRISWXOTQKGIOPVVWFH3","short_pith_number":"pith:DGEOO6MR","canonical_record":{"source":{"id":"1610.07809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T09:59:13Z","cross_cats_sorted":[],"title_canon_sha256":"fda13924fd1d6f123b599fc7fa967830f64ada7dc40548b823bf306794c86764","abstract_canon_sha256":"e730815b505bb5321fab5663f8399a5bd91a442011bc1400be88cdd7a6081e17"},"schema_version":"1.0"},"canonical_sha256":"1988e7799144ad774e0a321cfad6c53ee878d8307753c5b84da79b0caf936bd5","source":{"kind":"arxiv","id":"1610.07809","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.07809","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"1610.07809v1","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.07809","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"DGEOO6MRISWX","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DGEOO6MRISWXOTQK","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DGEOO6MR","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DGEOO6MRISWXOTQKGIOPVVWFH3","target":"record","payload":{"canonical_record":{"source":{"id":"1610.07809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T09:59:13Z","cross_cats_sorted":[],"title_canon_sha256":"fda13924fd1d6f123b599fc7fa967830f64ada7dc40548b823bf306794c86764","abstract_canon_sha256":"e730815b505bb5321fab5663f8399a5bd91a442011bc1400be88cdd7a6081e17"},"schema_version":"1.0"},"canonical_sha256":"1988e7799144ad774e0a321cfad6c53ee878d8307753c5b84da79b0caf936bd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:17.503923Z","signature_b64":"s7TBHfmIVZkcP1JIMuhOdmzIoduBfVRv3zDrto91+lj6xpHaZnTwc2t8ggHrc+1rOAmV0V46Da21UUeqFaYkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1988e7799144ad774e0a321cfad6c53ee878d8307753c5b84da79b0caf936bd5","last_reissued_at":"2026-05-18T01:01:17.503301Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:17.503301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.07809","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":"2026-05-18T01:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gV27gcfXRwBdIPGzaPPQnS+O8sY4sj7xOZax3rHm5DRPwXMscCoMpUOa0Dz4kHpm3kOcfD7weTr3AVCh1SrJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:07:23.467637Z"},"content_sha256":"387fc001f743cdc5081f6465a177e948a229348f6adb9b0dabbb1188f918a077","schema_version":"1.0","event_id":"sha256:387fc001f743cdc5081f6465a177e948a229348f6adb9b0dabbb1188f918a077"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DGEOO6MRISWXOTQKGIOPVVWFH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Document Pre-processing affects Keyphrase Extraction Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Damien Cram, Florian Boudin, Hugo Mougard","submitted_at":"2016-10-25T09:59:13Z","abstract_excerpt":"The SemEval-2010 benchmark dataset has brought renewed attention to the task of automatic keyphrase extraction. This dataset is made up of scientific articles that were automatically converted from PDF format to plain text and thus require careful preprocessing so that irrevelant spans of text do not negatively affect keyphrase extraction performance. In previous work, a wide range of document preprocessing techniques were described but their impact on the overall performance of keyphrase extraction models is still unexplored. Here, we re-assess the performance of several keyphrase extraction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.07809","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":"2026-05-18T01:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lvsqu1LOBhTFkxhB+v6tcwNnG+QP9kqxxp2E67MUTtV+n/JImjR+TtAUjaE1XTWYt3eWnviYpkCW/qZQsx1yBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:07:23.468333Z"},"content_sha256":"282ec96ef67c94ba407babf13d865ab11d1b9cf46915930e82455366810c0faf","schema_version":"1.0","event_id":"sha256:282ec96ef67c94ba407babf13d865ab11d1b9cf46915930e82455366810c0faf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGEOO6MRISWXOTQKGIOPVVWFH3/bundle.json","state_url":"https://pith.science/pith/DGEOO6MRISWXOTQKGIOPVVWFH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGEOO6MRISWXOTQKGIOPVVWFH3/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":"2026-05-31T05:07:23Z","links":{"resolver":"https://pith.science/pith/DGEOO6MRISWXOTQKGIOPVVWFH3","bundle":"https://pith.science/pith/DGEOO6MRISWXOTQKGIOPVVWFH3/bundle.json","state":"https://pith.science/pith/DGEOO6MRISWXOTQKGIOPVVWFH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGEOO6MRISWXOTQKGIOPVVWFH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DGEOO6MRISWXOTQKGIOPVVWFH3","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":"e730815b505bb5321fab5663f8399a5bd91a442011bc1400be88cdd7a6081e17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T09:59:13Z","title_canon_sha256":"fda13924fd1d6f123b599fc7fa967830f64ada7dc40548b823bf306794c86764"},"schema_version":"1.0","source":{"id":"1610.07809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.07809","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"1610.07809v1","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.07809","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"DGEOO6MRISWX","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DGEOO6MRISWXOTQK","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DGEOO6MR","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:282ec96ef67c94ba407babf13d865ab11d1b9cf46915930e82455366810c0faf","target":"graph","created_at":"2026-05-18T01:01:17Z","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":"The SemEval-2010 benchmark dataset has brought renewed attention to the task of automatic keyphrase extraction. This dataset is made up of scientific articles that were automatically converted from PDF format to plain text and thus require careful preprocessing so that irrevelant spans of text do not negatively affect keyphrase extraction performance. In previous work, a wide range of document preprocessing techniques were described but their impact on the overall performance of keyphrase extraction models is still unexplored. Here, we re-assess the performance of several keyphrase extraction ","authors_text":"Damien Cram, Florian Boudin, Hugo Mougard","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T09:59:13Z","title":"How Document Pre-processing affects Keyphrase Extraction Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.07809","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":"sha256:387fc001f743cdc5081f6465a177e948a229348f6adb9b0dabbb1188f918a077","target":"record","created_at":"2026-05-18T01:01:17Z","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":"e730815b505bb5321fab5663f8399a5bd91a442011bc1400be88cdd7a6081e17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T09:59:13Z","title_canon_sha256":"fda13924fd1d6f123b599fc7fa967830f64ada7dc40548b823bf306794c86764"},"schema_version":"1.0","source":{"id":"1610.07809","kind":"arxiv","version":1}},"canonical_sha256":"1988e7799144ad774e0a321cfad6c53ee878d8307753c5b84da79b0caf936bd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1988e7799144ad774e0a321cfad6c53ee878d8307753c5b84da79b0caf936bd5","first_computed_at":"2026-05-18T01:01:17.503301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:01:17.503301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s7TBHfmIVZkcP1JIMuhOdmzIoduBfVRv3zDrto91+lj6xpHaZnTwc2t8ggHrc+1rOAmV0V46Da21UUeqFaYkBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:01:17.503923Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.07809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:387fc001f743cdc5081f6465a177e948a229348f6adb9b0dabbb1188f918a077","sha256:282ec96ef67c94ba407babf13d865ab11d1b9cf46915930e82455366810c0faf"],"state_sha256":"6ccc2e700cae8fed55037572cf1a07c99a35c06cb3c415a64cc6db6d6d55644c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvekObBEgYBBEA95lu1g1MlgnvfjopGT8L0gjS/GXYObTUskCe8zFzYIgZj2dIYAi9INjrlXlCjGGhtTv7HYDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T05:07:23.472029Z","bundle_sha256":"704a1a6156dc04a71264f12c00b1a034224564d4cd997ebf9bb7fd8c873faed2"}}