{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:WZIE4FIY7Z6D6L3W32RX5F5K3S","short_pith_number":"pith:WZIE4FIY","canonical_record":{"source":{"id":"1204.2231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DL","submitted_at":"2012-04-10T17:57:42Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c96b5b902cd46f885bd68877721573ab6cbec3e88a2852dd3b07cd6f7ce7c5f3","abstract_canon_sha256":"918e99e59bcc6f3406a55f3cbd2a972055792d8d81cb8a9525fe3186fdfc4ed5"},"schema_version":"1.0"},"canonical_sha256":"b6504e1518fe7c3f2f76dea37e97aadc800c14f61a80229d05f9f4d88178012c","source":{"kind":"arxiv","id":"1204.2231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1204.2231","created_at":"2026-05-18T03:58:12Z"},{"alias_kind":"arxiv_version","alias_value":"1204.2231v1","created_at":"2026-05-18T03:58:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.2231","created_at":"2026-05-18T03:58:12Z"},{"alias_kind":"pith_short_12","alias_value":"WZIE4FIY7Z6D","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WZIE4FIY7Z6D6L3W","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WZIE4FIY","created_at":"2026-05-18T12:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:WZIE4FIY7Z6D6L3W32RX5F5K3S","target":"record","payload":{"canonical_record":{"source":{"id":"1204.2231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DL","submitted_at":"2012-04-10T17:57:42Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c96b5b902cd46f885bd68877721573ab6cbec3e88a2852dd3b07cd6f7ce7c5f3","abstract_canon_sha256":"918e99e59bcc6f3406a55f3cbd2a972055792d8d81cb8a9525fe3186fdfc4ed5"},"schema_version":"1.0"},"canonical_sha256":"b6504e1518fe7c3f2f76dea37e97aadc800c14f61a80229d05f9f4d88178012c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:58:12.975731Z","signature_b64":"6DW/9gIEGlcgJ/OfLg/GDN3G/zdVurHMj/3B+9rM/9eopxrderDZSKDVVkxxpCAd8Q6qQwumAXxAdiRkTeb9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6504e1518fe7c3f2f76dea37e97aadc800c14f61a80229d05f9f4d88178012c","last_reissued_at":"2026-05-18T03:58:12.974958Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:58:12.974958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1204.2231","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":"2026-05-18T03:58:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MXmygosVwKNGtSSSFRXGVBcCGLmxdbQjmR80LivUZvYMUTj2X+t+G1pCu4JucAb9lq59xLYP+Nrt+JVBUj6PDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:48:23.786336Z"},"content_sha256":"68008005f7ff9f5d9ca841bd34d859310f779423e0add1c40a057094d7b2dc86","schema_version":"1.0","event_id":"sha256:68008005f7ff9f5d9ca841bd34d859310f779423e0add1c40a057094d7b2dc86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:WZIE4FIY7Z6D6L3W32RX5F5K3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Keyphrase Indexing with Text Denoising","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DL","authors_text":"Robert E. Mercer, Rushdi Shams","submitted_at":"2012-04-10T17:57:42Z","abstract_excerpt":"In this paper, we report on indexing performance by a state-of-the-art keyphrase indexer, Maui, when paired with a text extraction procedure called text denoising. Text denoising is a method that extracts the denoised text, comprising the content-rich sentences, from full texts. The performance of the keyphrase indexer is demonstrated on three standard corpora collected from three domains, namely food and agriculture, high energy physics, and biomedical science. Maui is trained using the full texts and denoised texts. The indexer, using its trained models, then extracts keyphrases from test se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.2231","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":"2026-05-18T03:58:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGI0UfVkvqBbA8mCSDluqpZZl3hhRkh4sGzqeL52yX3Tr5sGceZFCFgcgEzhtbx1kXcERC67jlwOelt6NTUFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:48:23.786944Z"},"content_sha256":"f938d84ba608e6fb2c95285a2235769646a2814e3bfb983bd03c468bcfcac943","schema_version":"1.0","event_id":"sha256:f938d84ba608e6fb2c95285a2235769646a2814e3bfb983bd03c468bcfcac943"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZIE4FIY7Z6D6L3W32RX5F5K3S/bundle.json","state_url":"https://pith.science/pith/WZIE4FIY7Z6D6L3W32RX5F5K3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZIE4FIY7Z6D6L3W32RX5F5K3S/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":"2026-06-01T01:48:23Z","links":{"resolver":"https://pith.science/pith/WZIE4FIY7Z6D6L3W32RX5F5K3S","bundle":"https://pith.science/pith/WZIE4FIY7Z6D6L3W32RX5F5K3S/bundle.json","state":"https://pith.science/pith/WZIE4FIY7Z6D6L3W32RX5F5K3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZIE4FIY7Z6D6L3W32RX5F5K3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:WZIE4FIY7Z6D6L3W32RX5F5K3S","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":"918e99e59bcc6f3406a55f3cbd2a972055792d8d81cb8a9525fe3186fdfc4ed5","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DL","submitted_at":"2012-04-10T17:57:42Z","title_canon_sha256":"c96b5b902cd46f885bd68877721573ab6cbec3e88a2852dd3b07cd6f7ce7c5f3"},"schema_version":"1.0","source":{"id":"1204.2231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1204.2231","created_at":"2026-05-18T03:58:12Z"},{"alias_kind":"arxiv_version","alias_value":"1204.2231v1","created_at":"2026-05-18T03:58:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.2231","created_at":"2026-05-18T03:58:12Z"},{"alias_kind":"pith_short_12","alias_value":"WZIE4FIY7Z6D","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WZIE4FIY7Z6D6L3W","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WZIE4FIY","created_at":"2026-05-18T12:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:f938d84ba608e6fb2c95285a2235769646a2814e3bfb983bd03c468bcfcac943","target":"graph","created_at":"2026-05-18T03:58:12Z","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":"In this paper, we report on indexing performance by a state-of-the-art keyphrase indexer, Maui, when paired with a text extraction procedure called text denoising. Text denoising is a method that extracts the denoised text, comprising the content-rich sentences, from full texts. The performance of the keyphrase indexer is demonstrated on three standard corpora collected from three domains, namely food and agriculture, high energy physics, and biomedical science. Maui is trained using the full texts and denoised texts. The indexer, using its trained models, then extracts keyphrases from test se","authors_text":"Robert E. Mercer, Rushdi Shams","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DL","submitted_at":"2012-04-10T17:57:42Z","title":"Investigating Keyphrase Indexing with Text Denoising"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.2231","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":"sha256:68008005f7ff9f5d9ca841bd34d859310f779423e0add1c40a057094d7b2dc86","target":"record","created_at":"2026-05-18T03:58:12Z","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":"918e99e59bcc6f3406a55f3cbd2a972055792d8d81cb8a9525fe3186fdfc4ed5","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DL","submitted_at":"2012-04-10T17:57:42Z","title_canon_sha256":"c96b5b902cd46f885bd68877721573ab6cbec3e88a2852dd3b07cd6f7ce7c5f3"},"schema_version":"1.0","source":{"id":"1204.2231","kind":"arxiv","version":1}},"canonical_sha256":"b6504e1518fe7c3f2f76dea37e97aadc800c14f61a80229d05f9f4d88178012c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6504e1518fe7c3f2f76dea37e97aadc800c14f61a80229d05f9f4d88178012c","first_computed_at":"2026-05-18T03:58:12.974958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:58:12.974958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6DW/9gIEGlcgJ/OfLg/GDN3G/zdVurHMj/3B+9rM/9eopxrderDZSKDVVkxxpCAd8Q6qQwumAXxAdiRkTeb9CA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:58:12.975731Z","signed_message":"canonical_sha256_bytes"},"source_id":"1204.2231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68008005f7ff9f5d9ca841bd34d859310f779423e0add1c40a057094d7b2dc86","sha256:f938d84ba608e6fb2c95285a2235769646a2814e3bfb983bd03c468bcfcac943"],"state_sha256":"b323ac366fa39952e71021b56f788f4ff93da5d7ef7301d6125fb86bb35130b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"su2t7bSy60p7TdQFOl71tHNb+LQgHVbsThahK+Ahyrcu49s1cgPhXflbyj8tsCYU6dxVbUaGSti9UQvNFPn6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T01:48:23.791099Z","bundle_sha256":"3999df83f0435f697822b589704bcac5453159c59ae876904e7b385c936259ab"}}