{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PADVMLXRGO7VIWWBLC4JSDORJB","short_pith_number":"pith:PADVMLXR","canonical_record":{"source":{"id":"1807.05962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-16T16:39:11Z","cross_cats_sorted":[],"title_canon_sha256":"67096346cad61f001dbeabecf9cc45f666a7a88b55d2f07ad5fc9d9b96ec23d6","abstract_canon_sha256":"d542846cb3260c9dcbbb206baecf92eaf59d0d193424520812a5b1abe611d9b7"},"schema_version":"1.0"},"canonical_sha256":"7807562ef133bf545ac158b8990dd14862adb7d58851144be07924d52ebc844f","source":{"kind":"arxiv","id":"1807.05962","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05962","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05962v1","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05962","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"PADVMLXRGO7V","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PADVMLXRGO7VIWWB","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PADVMLXR","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PADVMLXRGO7VIWWBLC4JSDORJB","target":"record","payload":{"canonical_record":{"source":{"id":"1807.05962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-16T16:39:11Z","cross_cats_sorted":[],"title_canon_sha256":"67096346cad61f001dbeabecf9cc45f666a7a88b55d2f07ad5fc9d9b96ec23d6","abstract_canon_sha256":"d542846cb3260c9dcbbb206baecf92eaf59d0d193424520812a5b1abe611d9b7"},"schema_version":"1.0"},"canonical_sha256":"7807562ef133bf545ac158b8990dd14862adb7d58851144be07924d52ebc844f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:42.082024Z","signature_b64":"Utt+Z2xo+KrTyWSvtxBAiUgiO4lwneRjE1QAGzOGTDmMyrUxIqahoCveW+F2FKUDfFROJB0bwHJiJG0lrj7eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7807562ef133bf545ac158b8990dd14862adb7d58851144be07924d52ebc844f","last_reissued_at":"2026-05-18T00:10:42.081338Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:42.081338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.05962","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":"2026-05-18T00:10:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqYT5lPUVJsQw5MagadGgP91eWPRSgW8DayZFnYStC1mb5XPpMGSIHJfX/CuoEJm8reUfsYaqzNbAVX1urDdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:24:24.009922Z"},"content_sha256":"91946474b3999c10041473feca6ec5a91c387462bc40e1450af1992f87e136c6","schema_version":"1.0","event_id":"sha256:91946474b3999c10041473feca6ec5a91c387462bc40e1450af1992f87e136c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PADVMLXRGO7VIWWBLC4JSDORJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Theme-weighted Ranking of Keywords from Text Documents using Phrase Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debanjan Mahata, John Kuriakose, John R. Talburt, Rajiv Ratn Shah, Roger Zimmermann","submitted_at":"2018-07-16T16:39:11Z","abstract_excerpt":"Keyword extraction is a fundamental task in natural language processing that facilitates mapping of documents to a concise set of representative single and multi-word phrases. Keywords from text documents are primarily extracted using supervised and unsupervised approaches. In this paper, we present an unsupervised technique that uses a combination of theme-weighted personalized PageRank algorithm and neural phrase embeddings for extracting and ranking keywords. We also introduce an efficient way of processing text documents and training phrase embeddings using existing techniques. We share an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05962","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":"2026-05-18T00:10:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eZJNDTMLx5V/aWs7Y9AwsnV3habP3risNWCiqQDegCoP7apa+bjFUBSS1hCniVEJT4FpkNQMDA+zvydiqsE0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:24:24.010701Z"},"content_sha256":"7a408fab23436e07a7be25d27bc55bbca33230199b0c8ad4dba3c49ccf5fe4b0","schema_version":"1.0","event_id":"sha256:7a408fab23436e07a7be25d27bc55bbca33230199b0c8ad4dba3c49ccf5fe4b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PADVMLXRGO7VIWWBLC4JSDORJB/bundle.json","state_url":"https://pith.science/pith/PADVMLXRGO7VIWWBLC4JSDORJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PADVMLXRGO7VIWWBLC4JSDORJB/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":"2026-05-25T14:24:24Z","links":{"resolver":"https://pith.science/pith/PADVMLXRGO7VIWWBLC4JSDORJB","bundle":"https://pith.science/pith/PADVMLXRGO7VIWWBLC4JSDORJB/bundle.json","state":"https://pith.science/pith/PADVMLXRGO7VIWWBLC4JSDORJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PADVMLXRGO7VIWWBLC4JSDORJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PADVMLXRGO7VIWWBLC4JSDORJB","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":"d542846cb3260c9dcbbb206baecf92eaf59d0d193424520812a5b1abe611d9b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-16T16:39:11Z","title_canon_sha256":"67096346cad61f001dbeabecf9cc45f666a7a88b55d2f07ad5fc9d9b96ec23d6"},"schema_version":"1.0","source":{"id":"1807.05962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05962","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05962v1","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05962","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"PADVMLXRGO7V","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PADVMLXRGO7VIWWB","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PADVMLXR","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:7a408fab23436e07a7be25d27bc55bbca33230199b0c8ad4dba3c49ccf5fe4b0","target":"graph","created_at":"2026-05-18T00:10:42Z","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":"Keyword extraction is a fundamental task in natural language processing that facilitates mapping of documents to a concise set of representative single and multi-word phrases. Keywords from text documents are primarily extracted using supervised and unsupervised approaches. In this paper, we present an unsupervised technique that uses a combination of theme-weighted personalized PageRank algorithm and neural phrase embeddings for extracting and ranking keywords. We also introduce an efficient way of processing text documents and training phrase embeddings using existing techniques. We share an","authors_text":"Debanjan Mahata, John Kuriakose, John R. Talburt, Rajiv Ratn Shah, Roger Zimmermann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-16T16:39:11Z","title":"Theme-weighted Ranking of Keywords from Text Documents using Phrase Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05962","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":"sha256:91946474b3999c10041473feca6ec5a91c387462bc40e1450af1992f87e136c6","target":"record","created_at":"2026-05-18T00:10:42Z","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":"d542846cb3260c9dcbbb206baecf92eaf59d0d193424520812a5b1abe611d9b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-16T16:39:11Z","title_canon_sha256":"67096346cad61f001dbeabecf9cc45f666a7a88b55d2f07ad5fc9d9b96ec23d6"},"schema_version":"1.0","source":{"id":"1807.05962","kind":"arxiv","version":1}},"canonical_sha256":"7807562ef133bf545ac158b8990dd14862adb7d58851144be07924d52ebc844f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7807562ef133bf545ac158b8990dd14862adb7d58851144be07924d52ebc844f","first_computed_at":"2026-05-18T00:10:42.081338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:42.081338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Utt+Z2xo+KrTyWSvtxBAiUgiO4lwneRjE1QAGzOGTDmMyrUxIqahoCveW+F2FKUDfFROJB0bwHJiJG0lrj7eDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:42.082024Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91946474b3999c10041473feca6ec5a91c387462bc40e1450af1992f87e136c6","sha256:7a408fab23436e07a7be25d27bc55bbca33230199b0c8ad4dba3c49ccf5fe4b0"],"state_sha256":"aeaa5d5d97156796f00d43c685d0c896910af09f5ec6ab36bc68b884ddb183b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27ygp6k0M0IRrLfqkuaqgq6/ZIwTuW6iDIIuo3+0PwYMxmWBnD3qQJ9fVetM5MxReK5c6IMoThvQylrpBtmEDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T14:24:24.014389Z","bundle_sha256":"4a9cc016a5503b035b7deec3863e604d72b1ef3d4010368877742b9ac4aed71d"}}