{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:XKZPRYR3AZDKTPJCV3RZEAY2EM","short_pith_number":"pith:XKZPRYR3","canonical_record":{"source":{"id":"1605.00122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-04-30T15:04:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6c2063383989dbb6883528d34f428c27fe8b3188a00bf2b7aa04094626842bf3","abstract_canon_sha256":"9b6a8c710d8d7772585cba215991ad4e9cf066efd816ded8208e76f14c4361a3"},"schema_version":"1.0"},"canonical_sha256":"bab2f8e23b0646a9bd22aee392031a233c8d9411910adf6a92749ff914936289","source":{"kind":"arxiv","id":"1605.00122","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.00122","created_at":"2026-05-18T00:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"1605.00122v1","created_at":"2026-05-18T00:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.00122","created_at":"2026-05-18T00:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"XKZPRYR3AZDK","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XKZPRYR3AZDKTPJC","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XKZPRYR3","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:XKZPRYR3AZDKTPJCV3RZEAY2EM","target":"record","payload":{"canonical_record":{"source":{"id":"1605.00122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-04-30T15:04:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6c2063383989dbb6883528d34f428c27fe8b3188a00bf2b7aa04094626842bf3","abstract_canon_sha256":"9b6a8c710d8d7772585cba215991ad4e9cf066efd816ded8208e76f14c4361a3"},"schema_version":"1.0"},"canonical_sha256":"bab2f8e23b0646a9bd22aee392031a233c8d9411910adf6a92749ff914936289","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:09.446714Z","signature_b64":"mcAKHzlGKD+B7zV7GlsBqE3zb93rVEdFBlr1nRz8tu9bo5uckLu73HsuWvFDNYfaZc1tY5zv4sSMGHwSd+XBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bab2f8e23b0646a9bd22aee392031a233c8d9411910adf6a92749ff914936289","last_reissued_at":"2026-05-18T00:43:09.445991Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:09.445991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.00122","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":"2026-05-18T00:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ToGkqKXGngWd3Fmnp0MBef3En3fEp6jjTDHot4d7S+QZ2QqMH/NvS1o9R8otXHYiMk5brvdFhy/qS1yaoGCZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:05:43.564295Z"},"content_sha256":"1285ebc611f6a6497fa26c43a5c31206166b03a68154047376227cf688d7ee8d","schema_version":"1.0","event_id":"sha256:1285ebc611f6a6497fa26c43a5c31206166b03a68154047376227cf688d7ee8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:XKZPRYR3AZDKTPJCV3RZEAY2EM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Improved System for Sentence-level Novelty Detection in Textual Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Eugene Ch'ng, Lanyun Zhang, Uwe Aickelin, Xinyu Fu","submitted_at":"2016-04-30T15:04:19Z","abstract_excerpt":"Novelty detection in news events has long been a difficult problem. A number of models performed well on specific data streams but certain issues are far from being solved, particularly in large data streams from the WWW where unpredictability of new terms requires adaptation in the vector space model. We present a novel event detection system based on the Incremental Term Frequency-Inverse Document Frequency (TF-IDF) weighting incorporated with Locality Sensitive Hashing (LSH). Our system could efficiently and effectively adapt to the changes within the data streams of any new terms with cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.00122","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":"2026-05-18T00:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qoAWJy7Bi6gaodVmYgFAs6ebtFacujYCQi+FM+/oygQq5AYy6KB74R8PLKdUHnymUIMrBl6JfP3DniWl5BtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:05:43.564669Z"},"content_sha256":"d068485fe78e00e693dbc4988bb7ecf173b3aee1e167348b737782d4cd01e7ee","schema_version":"1.0","event_id":"sha256:d068485fe78e00e693dbc4988bb7ecf173b3aee1e167348b737782d4cd01e7ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKZPRYR3AZDKTPJCV3RZEAY2EM/bundle.json","state_url":"https://pith.science/pith/XKZPRYR3AZDKTPJCV3RZEAY2EM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKZPRYR3AZDKTPJCV3RZEAY2EM/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":"2026-05-30T12:05:43Z","links":{"resolver":"https://pith.science/pith/XKZPRYR3AZDKTPJCV3RZEAY2EM","bundle":"https://pith.science/pith/XKZPRYR3AZDKTPJCV3RZEAY2EM/bundle.json","state":"https://pith.science/pith/XKZPRYR3AZDKTPJCV3RZEAY2EM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKZPRYR3AZDKTPJCV3RZEAY2EM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XKZPRYR3AZDKTPJCV3RZEAY2EM","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":"9b6a8c710d8d7772585cba215991ad4e9cf066efd816ded8208e76f14c4361a3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-04-30T15:04:19Z","title_canon_sha256":"6c2063383989dbb6883528d34f428c27fe8b3188a00bf2b7aa04094626842bf3"},"schema_version":"1.0","source":{"id":"1605.00122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.00122","created_at":"2026-05-18T00:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"1605.00122v1","created_at":"2026-05-18T00:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.00122","created_at":"2026-05-18T00:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"XKZPRYR3AZDK","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XKZPRYR3AZDKTPJC","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XKZPRYR3","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:d068485fe78e00e693dbc4988bb7ecf173b3aee1e167348b737782d4cd01e7ee","target":"graph","created_at":"2026-05-18T00:43:09Z","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":"Novelty detection in news events has long been a difficult problem. A number of models performed well on specific data streams but certain issues are far from being solved, particularly in large data streams from the WWW where unpredictability of new terms requires adaptation in the vector space model. We present a novel event detection system based on the Incremental Term Frequency-Inverse Document Frequency (TF-IDF) weighting incorporated with Locality Sensitive Hashing (LSH). Our system could efficiently and effectively adapt to the changes within the data streams of any new terms with cont","authors_text":"Eugene Ch'ng, Lanyun Zhang, Uwe Aickelin, Xinyu Fu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-04-30T15:04:19Z","title":"An Improved System for Sentence-level Novelty Detection in Textual Streams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.00122","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":"sha256:1285ebc611f6a6497fa26c43a5c31206166b03a68154047376227cf688d7ee8d","target":"record","created_at":"2026-05-18T00:43:09Z","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":"9b6a8c710d8d7772585cba215991ad4e9cf066efd816ded8208e76f14c4361a3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-04-30T15:04:19Z","title_canon_sha256":"6c2063383989dbb6883528d34f428c27fe8b3188a00bf2b7aa04094626842bf3"},"schema_version":"1.0","source":{"id":"1605.00122","kind":"arxiv","version":1}},"canonical_sha256":"bab2f8e23b0646a9bd22aee392031a233c8d9411910adf6a92749ff914936289","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bab2f8e23b0646a9bd22aee392031a233c8d9411910adf6a92749ff914936289","first_computed_at":"2026-05-18T00:43:09.445991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:09.445991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mcAKHzlGKD+B7zV7GlsBqE3zb93rVEdFBlr1nRz8tu9bo5uckLu73HsuWvFDNYfaZc1tY5zv4sSMGHwSd+XBBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:09.446714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.00122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1285ebc611f6a6497fa26c43a5c31206166b03a68154047376227cf688d7ee8d","sha256:d068485fe78e00e693dbc4988bb7ecf173b3aee1e167348b737782d4cd01e7ee"],"state_sha256":"08454cc71a93990a6049f9a334658039e23aa7c229635896015da3b56eb2cd36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h4VVyftjm8hj8mcsNR08WA6zb3htp56xsPfTT/znFDBEiQ5A53KEMC0sTxq5wL1KJjGk/irhdJ1eVvT18xOQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:05:43.567049Z","bundle_sha256":"b3bc8fc4177b23cf3df80eeb80ff3a094206b3f15ca16745f5c7319d6a1651a8"}}