{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:5XC4I7LOSZWMBOFPTG7ISGPDCT","short_pith_number":"pith:5XC4I7LO","canonical_record":{"source":{"id":"1507.02002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-08T01:06:55Z","cross_cats_sorted":[],"title_canon_sha256":"ce3db49bc6cbacc2d31fbe76c28fdf2d7c72e223ca1fac4808509be63092b969","abstract_canon_sha256":"acae78176f3a1291b79de2ae3b7a2ee2b5d5b0985dd63c2f539a4daa89ef816e"},"schema_version":"1.0"},"canonical_sha256":"edc5c47d6e966cc0b8af99be8919e314e1461d2b8ad72f82110e5a72381f0e01","source":{"kind":"arxiv","id":"1507.02002","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.02002","created_at":"2026-05-18T01:37:10Z"},{"alias_kind":"arxiv_version","alias_value":"1507.02002v1","created_at":"2026-05-18T01:37:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.02002","created_at":"2026-05-18T01:37:10Z"},{"alias_kind":"pith_short_12","alias_value":"5XC4I7LOSZWM","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"5XC4I7LOSZWMBOFP","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"5XC4I7LO","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:5XC4I7LOSZWMBOFPTG7ISGPDCT","target":"record","payload":{"canonical_record":{"source":{"id":"1507.02002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-08T01:06:55Z","cross_cats_sorted":[],"title_canon_sha256":"ce3db49bc6cbacc2d31fbe76c28fdf2d7c72e223ca1fac4808509be63092b969","abstract_canon_sha256":"acae78176f3a1291b79de2ae3b7a2ee2b5d5b0985dd63c2f539a4daa89ef816e"},"schema_version":"1.0"},"canonical_sha256":"edc5c47d6e966cc0b8af99be8919e314e1461d2b8ad72f82110e5a72381f0e01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:10.514197Z","signature_b64":"hcfJ4U5fsRNsnCesHk17q8avxAUw/fedX1MzsaFgwI7JVm3nk9Bqf/E1XzG7EfZsoyY3Bx9ICKgcUZqnnmwaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc5c47d6e966cc0b8af99be8919e314e1461d2b8ad72f82110e5a72381f0e01","last_reissued_at":"2026-05-18T01:37:10.513579Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:10.513579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.02002","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":"2026-05-18T01:37:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FEn5fYuS9x2KP16WBYDiSHcpIhZbHVlqLGHiWEmpTyxNMktK6Eg8Q6pqQShWxbxUF+Iv87J2ISDyTJPGVNiFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:20:35.773429Z"},"content_sha256":"58ef5bf76fd826688797c64a866c8c08324bac526b692d80b546b73610e30d6b","schema_version":"1.0","event_id":"sha256:58ef5bf76fd826688797c64a866c8c08324bac526b692d80b546b73610e30d6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:5XC4I7LOSZWMBOFPTG7ISGPDCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topical Discovery of Web Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Giancarlo Crocetti","submitted_at":"2015-07-08T01:06:55Z","abstract_excerpt":"This work describes the theory and the implementation of a new software tool, the \"Web Topical Discovery System\" (WTDS), which provides an approach to the automatic discovery and selection of new web pages relevant to specific analytical needs. We will see how it is possible to specify the research context with search keywords related to the area of interest and consider the important problem of removing extraneous data from a web page containing an article in order to reduce, to a minimum, false positives represented by a match on a keyword that is showing up on the latest news box of the sam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.02002","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":"2026-05-18T01:37:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9AanQNB+B7qaI4BGtVhjwVjtCd0j7tmrA1lTr97Bq9HQF3Nds7fRuwexIPNRax6CjOJt9izZulevszVpef3TBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:20:35.773780Z"},"content_sha256":"b30d3cf7b7e7250e4ce2296a69765cd789228785cae419c51496a32ba899a22d","schema_version":"1.0","event_id":"sha256:b30d3cf7b7e7250e4ce2296a69765cd789228785cae419c51496a32ba899a22d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XC4I7LOSZWMBOFPTG7ISGPDCT/bundle.json","state_url":"https://pith.science/pith/5XC4I7LOSZWMBOFPTG7ISGPDCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XC4I7LOSZWMBOFPTG7ISGPDCT/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":"2026-05-28T09:20:35Z","links":{"resolver":"https://pith.science/pith/5XC4I7LOSZWMBOFPTG7ISGPDCT","bundle":"https://pith.science/pith/5XC4I7LOSZWMBOFPTG7ISGPDCT/bundle.json","state":"https://pith.science/pith/5XC4I7LOSZWMBOFPTG7ISGPDCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XC4I7LOSZWMBOFPTG7ISGPDCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:5XC4I7LOSZWMBOFPTG7ISGPDCT","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":"acae78176f3a1291b79de2ae3b7a2ee2b5d5b0985dd63c2f539a4daa89ef816e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-08T01:06:55Z","title_canon_sha256":"ce3db49bc6cbacc2d31fbe76c28fdf2d7c72e223ca1fac4808509be63092b969"},"schema_version":"1.0","source":{"id":"1507.02002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.02002","created_at":"2026-05-18T01:37:10Z"},{"alias_kind":"arxiv_version","alias_value":"1507.02002v1","created_at":"2026-05-18T01:37:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.02002","created_at":"2026-05-18T01:37:10Z"},{"alias_kind":"pith_short_12","alias_value":"5XC4I7LOSZWM","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"5XC4I7LOSZWMBOFP","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"5XC4I7LO","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:b30d3cf7b7e7250e4ce2296a69765cd789228785cae419c51496a32ba899a22d","target":"graph","created_at":"2026-05-18T01:37:10Z","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":"This work describes the theory and the implementation of a new software tool, the \"Web Topical Discovery System\" (WTDS), which provides an approach to the automatic discovery and selection of new web pages relevant to specific analytical needs. We will see how it is possible to specify the research context with search keywords related to the area of interest and consider the important problem of removing extraneous data from a web page containing an article in order to reduce, to a minimum, false positives represented by a match on a keyword that is showing up on the latest news box of the sam","authors_text":"Giancarlo Crocetti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-08T01:06:55Z","title":"Topical Discovery of Web Content"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.02002","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":"sha256:58ef5bf76fd826688797c64a866c8c08324bac526b692d80b546b73610e30d6b","target":"record","created_at":"2026-05-18T01:37:10Z","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":"acae78176f3a1291b79de2ae3b7a2ee2b5d5b0985dd63c2f539a4daa89ef816e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-08T01:06:55Z","title_canon_sha256":"ce3db49bc6cbacc2d31fbe76c28fdf2d7c72e223ca1fac4808509be63092b969"},"schema_version":"1.0","source":{"id":"1507.02002","kind":"arxiv","version":1}},"canonical_sha256":"edc5c47d6e966cc0b8af99be8919e314e1461d2b8ad72f82110e5a72381f0e01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edc5c47d6e966cc0b8af99be8919e314e1461d2b8ad72f82110e5a72381f0e01","first_computed_at":"2026-05-18T01:37:10.513579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:37:10.513579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hcfJ4U5fsRNsnCesHk17q8avxAUw/fedX1MzsaFgwI7JVm3nk9Bqf/E1XzG7EfZsoyY3Bx9ICKgcUZqnnmwaDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:37:10.514197Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.02002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58ef5bf76fd826688797c64a866c8c08324bac526b692d80b546b73610e30d6b","sha256:b30d3cf7b7e7250e4ce2296a69765cd789228785cae419c51496a32ba899a22d"],"state_sha256":"ae462a4a1bd746f771c75aa72081d2b226f1299c714d4db8e614bc858cb79226"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iNDMbLJHHkqUhAGQ4QLJoB9ALPP2rssVoo1Zp60JY6DXoPdyk4GFB/515I2xxrzBYSQQSPX/KYmIgdLSvAteBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:20:35.775855Z","bundle_sha256":"3d03fd13e048c462673351f6cf30c18b46082afa7200c4258eb734365b73fb8d"}}