{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZUFLHRLU2CN7WGWGH67KGQU7SV","short_pith_number":"pith:ZUFLHRLU","canonical_record":{"source":{"id":"1702.04946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2017-02-16T12:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"84a8021e159fa18f6e3e7aedd08f8c044b1799540bfdaeb63dfa465a7fdfc8f2","abstract_canon_sha256":"b6ecdbf7c59bb94ae5e277ed71666ca44145a22fbdb3d337df0a96bdf8844128"},"schema_version":"1.0"},"canonical_sha256":"cd0ab3c574d09bfb1ac63fbea3429f95720d872376796f43a90b44fdd1a183ce","source":{"kind":"arxiv","id":"1702.04946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.04946","created_at":"2026-05-18T00:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"1702.04946v1","created_at":"2026-05-18T00:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.04946","created_at":"2026-05-18T00:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZUFLHRLU2CN7","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZUFLHRLU2CN7WGWG","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZUFLHRLU","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZUFLHRLU2CN7WGWGH67KGQU7SV","target":"record","payload":{"canonical_record":{"source":{"id":"1702.04946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2017-02-16T12:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"84a8021e159fa18f6e3e7aedd08f8c044b1799540bfdaeb63dfa465a7fdfc8f2","abstract_canon_sha256":"b6ecdbf7c59bb94ae5e277ed71666ca44145a22fbdb3d337df0a96bdf8844128"},"schema_version":"1.0"},"canonical_sha256":"cd0ab3c574d09bfb1ac63fbea3429f95720d872376796f43a90b44fdd1a183ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:36.669133Z","signature_b64":"tVQaoSsSsqMB6W2icfw4VT+BTz4iDAoaq1Pn/2al3N9k43p5b/i/WXpLSSdPBsUMRDrJCij8lWSh8fUdcWtrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd0ab3c574d09bfb1ac63fbea3429f95720d872376796f43a90b44fdd1a183ce","last_reissued_at":"2026-05-18T00:50:36.668657Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:36.668657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.04946","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":"2026-05-18T00:50:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"llWwyxgTMOsduU6gQ6fQNKrP2FzwYB2i3MZ48AUhg4sQxWnTe9JkJ8I2uSwBL9/RBaCZI02145o3dl8nV5dHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T07:44:44.573891Z"},"content_sha256":"789e8566c30bf1f809d6e75d3e30570293508a87b5454621350c86998f90b1cd","schema_version":"1.0","event_id":"sha256:789e8566c30bf1f809d6e75d3e30570293508a87b5454621350c86998f90b1cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZUFLHRLU2CN7WGWGH67KGQU7SV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering articles based on semantic similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"Rob Koopman, Shenghui Wang","submitted_at":"2017-02-16T12:48:54Z","abstract_excerpt":"Document clustering is generally the first step for topic identification. Since many clustering methods operate on the similarities between documents, it is important to build representations of these documents which keep their semantics as much as possible and are also suitable for efficient similarity calculation. The metadata of articles in the Astro dataset contribute to a semantic matrix, which uses a vector space to capture the semantics of entities derived from these articles and consequently supports the contextual exploration of these entities in LittleAriadne. However, this semantic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.04946","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":"2026-05-18T00:50:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wClBaX0w+8tS6kwsHPa3Qw1Bmx2WYHrPBAK+Z+WexvFzGGk/KvvsyNq2PZBSfcwonHt5nhQCxz9Gvjg8Z2sCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T07:44:44.574238Z"},"content_sha256":"3ffdac133836f1a09ced423647dfddd8efba460f1d58755a261aff6cb0c4ca65","schema_version":"1.0","event_id":"sha256:3ffdac133836f1a09ced423647dfddd8efba460f1d58755a261aff6cb0c4ca65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZUFLHRLU2CN7WGWGH67KGQU7SV/bundle.json","state_url":"https://pith.science/pith/ZUFLHRLU2CN7WGWGH67KGQU7SV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZUFLHRLU2CN7WGWGH67KGQU7SV/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":"2026-06-26T07:44:44Z","links":{"resolver":"https://pith.science/pith/ZUFLHRLU2CN7WGWGH67KGQU7SV","bundle":"https://pith.science/pith/ZUFLHRLU2CN7WGWGH67KGQU7SV/bundle.json","state":"https://pith.science/pith/ZUFLHRLU2CN7WGWGH67KGQU7SV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZUFLHRLU2CN7WGWGH67KGQU7SV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZUFLHRLU2CN7WGWGH67KGQU7SV","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":"b6ecdbf7c59bb94ae5e277ed71666ca44145a22fbdb3d337df0a96bdf8844128","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2017-02-16T12:48:54Z","title_canon_sha256":"84a8021e159fa18f6e3e7aedd08f8c044b1799540bfdaeb63dfa465a7fdfc8f2"},"schema_version":"1.0","source":{"id":"1702.04946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.04946","created_at":"2026-05-18T00:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"1702.04946v1","created_at":"2026-05-18T00:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.04946","created_at":"2026-05-18T00:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZUFLHRLU2CN7","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZUFLHRLU2CN7WGWG","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZUFLHRLU","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:3ffdac133836f1a09ced423647dfddd8efba460f1d58755a261aff6cb0c4ca65","target":"graph","created_at":"2026-05-18T00:50:36Z","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":"Document clustering is generally the first step for topic identification. Since many clustering methods operate on the similarities between documents, it is important to build representations of these documents which keep their semantics as much as possible and are also suitable for efficient similarity calculation. The metadata of articles in the Astro dataset contribute to a semantic matrix, which uses a vector space to capture the semantics of entities derived from these articles and consequently supports the contextual exploration of these entities in LittleAriadne. However, this semantic ","authors_text":"Rob Koopman, Shenghui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2017-02-16T12:48:54Z","title":"Clustering articles based on semantic similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.04946","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":"sha256:789e8566c30bf1f809d6e75d3e30570293508a87b5454621350c86998f90b1cd","target":"record","created_at":"2026-05-18T00:50:36Z","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":"b6ecdbf7c59bb94ae5e277ed71666ca44145a22fbdb3d337df0a96bdf8844128","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2017-02-16T12:48:54Z","title_canon_sha256":"84a8021e159fa18f6e3e7aedd08f8c044b1799540bfdaeb63dfa465a7fdfc8f2"},"schema_version":"1.0","source":{"id":"1702.04946","kind":"arxiv","version":1}},"canonical_sha256":"cd0ab3c574d09bfb1ac63fbea3429f95720d872376796f43a90b44fdd1a183ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd0ab3c574d09bfb1ac63fbea3429f95720d872376796f43a90b44fdd1a183ce","first_computed_at":"2026-05-18T00:50:36.668657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:36.668657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tVQaoSsSsqMB6W2icfw4VT+BTz4iDAoaq1Pn/2al3N9k43p5b/i/WXpLSSdPBsUMRDrJCij8lWSh8fUdcWtrCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:36.669133Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.04946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:789e8566c30bf1f809d6e75d3e30570293508a87b5454621350c86998f90b1cd","sha256:3ffdac133836f1a09ced423647dfddd8efba460f1d58755a261aff6cb0c4ca65"],"state_sha256":"37f5039fd8aaa1b9d1c73f71c8e7aebf58668fe8b3b9758d80f201c40aa54301"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l17iSk6XgIzkwBAuk3kpwSfeaPvXd77wif/R80wrSlWXe+wf46AJLjD14Y/l2OXzK1JJ8TR6VMvJB44lwY9RBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T07:44:44.576348Z","bundle_sha256":"c1c18fc84bcf8501c35845f5c0bf416998188698556ac2dddeeeb1b413f822be"}}