{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X3YZFM6HBMENXXH7D4FS2V6VCU","short_pith_number":"pith:X3YZFM6H","canonical_record":{"source":{"id":"1911.02991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T02:23:33Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"b0caf82fabd5a5ba8b0240717d122d05a70ac13ac503a43b06fb687db7079009","abstract_canon_sha256":"3cb2e866d724e6894caf7f9f98257021937761a307343e136795cdad07bd4dc9"},"schema_version":"1.0"},"canonical_sha256":"bef192b3c70b08dbdcff1f0b2d57d51509f807420cb4f1cf8053c88c2a759d79","source":{"kind":"arxiv","id":"1911.02991","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02991","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02991v1","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02991","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"X3YZFM6HBMEN","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"X3YZFM6HBMENXXH7","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"X3YZFM6H","created_at":"2026-07-05T00:17:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X3YZFM6HBMENXXH7D4FS2V6VCU","target":"record","payload":{"canonical_record":{"source":{"id":"1911.02991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T02:23:33Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"b0caf82fabd5a5ba8b0240717d122d05a70ac13ac503a43b06fb687db7079009","abstract_canon_sha256":"3cb2e866d724e6894caf7f9f98257021937761a307343e136795cdad07bd4dc9"},"schema_version":"1.0"},"canonical_sha256":"bef192b3c70b08dbdcff1f0b2d57d51509f807420cb4f1cf8053c88c2a759d79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:59.121516Z","signature_b64":"xGV9LKe3w5WmGcqJI2/u9WAoBFXzYW7gjTmTTl9092mhAW9YnWP1WL7eLpi5rOvdM8DKOUH2DeCFdCgugkvoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef192b3c70b08dbdcff1f0b2d57d51509f807420cb4f1cf8053c88c2a759d79","last_reissued_at":"2026-07-05T00:17:59.121116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:59.121116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.02991","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":"2026-07-05T00:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8KW47U9qobgEaob8/Osy97DaHqZk5nTahMfHRbpMQOeBbMFd0tWUvdQiUsXRbNjHBA3tg6xKXVP119JkzpMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T00:08:57.774056Z"},"content_sha256":"9f45abfe0fcef1d0c8a34d89c954157956f13d76a85d62a669acb94ad30829ff","schema_version":"1.0","event_id":"sha256:9f45abfe0fcef1d0c8a34d89c954157956f13d76a85d62a669acb94ad30829ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X3YZFM6HBMENXXH7D4FS2V6VCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Supervised Method using Gaussian Random Fields for Boilerplate Removal in Web Browsers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Joy Bose, Sumanta Mukherjee","submitted_at":"2019-11-08T02:23:33Z","abstract_excerpt":"Boilerplate removal refers to the problem of removing noisy content from a webpage such as ads and extracting relevant content that can be used by various services. This can be useful in several features in web browsers such as ad blocking, accessibility tools such as read out loud, translation, summarization etc. In order to create a training dataset to train a model for boilerplate detection and removal, labeling or tagging webpage data manually can be tedious and time consuming. Hence, a semi-supervised model, in which some of the webpage elements are labeled manually and labels for others "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02991","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.02991/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qnyT5mnXqSF55Ma4w4mA8BD3lXKY04ux+wWQW5jXIVzlWvu/5F1L/3Jl+0ZVO65stEyjkwj6mT8lN1/0ZujAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T00:08:57.774451Z"},"content_sha256":"4ab323362bd34975a7ff4b1e91aac913e09e74b5cd3e22cc1aaf10a31b205156","schema_version":"1.0","event_id":"sha256:4ab323362bd34975a7ff4b1e91aac913e09e74b5cd3e22cc1aaf10a31b205156"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3YZFM6HBMENXXH7D4FS2V6VCU/bundle.json","state_url":"https://pith.science/pith/X3YZFM6HBMENXXH7D4FS2V6VCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3YZFM6HBMENXXH7D4FS2V6VCU/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":"2026-07-26T00:08:57Z","links":{"resolver":"https://pith.science/pith/X3YZFM6HBMENXXH7D4FS2V6VCU","bundle":"https://pith.science/pith/X3YZFM6HBMENXXH7D4FS2V6VCU/bundle.json","state":"https://pith.science/pith/X3YZFM6HBMENXXH7D4FS2V6VCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3YZFM6HBMENXXH7D4FS2V6VCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X3YZFM6HBMENXXH7D4FS2V6VCU","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":"3cb2e866d724e6894caf7f9f98257021937761a307343e136795cdad07bd4dc9","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T02:23:33Z","title_canon_sha256":"b0caf82fabd5a5ba8b0240717d122d05a70ac13ac503a43b06fb687db7079009"},"schema_version":"1.0","source":{"id":"1911.02991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02991","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02991v1","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02991","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"X3YZFM6HBMEN","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"X3YZFM6HBMENXXH7","created_at":"2026-07-05T00:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"X3YZFM6H","created_at":"2026-07-05T00:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:4ab323362bd34975a7ff4b1e91aac913e09e74b5cd3e22cc1aaf10a31b205156","target":"graph","created_at":"2026-07-05T00:17:59Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.02991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Boilerplate removal refers to the problem of removing noisy content from a webpage such as ads and extracting relevant content that can be used by various services. This can be useful in several features in web browsers such as ad blocking, accessibility tools such as read out loud, translation, summarization etc. In order to create a training dataset to train a model for boilerplate detection and removal, labeling or tagging webpage data manually can be tedious and time consuming. Hence, a semi-supervised model, in which some of the webpage elements are labeled manually and labels for others ","authors_text":"Joy Bose, Sumanta Mukherjee","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T02:23:33Z","title":"Semi-Supervised Method using Gaussian Random Fields for Boilerplate Removal in Web Browsers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02991","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":"sha256:9f45abfe0fcef1d0c8a34d89c954157956f13d76a85d62a669acb94ad30829ff","target":"record","created_at":"2026-07-05T00:17:59Z","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":"3cb2e866d724e6894caf7f9f98257021937761a307343e136795cdad07bd4dc9","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T02:23:33Z","title_canon_sha256":"b0caf82fabd5a5ba8b0240717d122d05a70ac13ac503a43b06fb687db7079009"},"schema_version":"1.0","source":{"id":"1911.02991","kind":"arxiv","version":1}},"canonical_sha256":"bef192b3c70b08dbdcff1f0b2d57d51509f807420cb4f1cf8053c88c2a759d79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bef192b3c70b08dbdcff1f0b2d57d51509f807420cb4f1cf8053c88c2a759d79","first_computed_at":"2026-07-05T00:17:59.121116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:17:59.121116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xGV9LKe3w5WmGcqJI2/u9WAoBFXzYW7gjTmTTl9092mhAW9YnWP1WL7eLpi5rOvdM8DKOUH2DeCFdCgugkvoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:17:59.121516Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.02991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f45abfe0fcef1d0c8a34d89c954157956f13d76a85d62a669acb94ad30829ff","sha256:4ab323362bd34975a7ff4b1e91aac913e09e74b5cd3e22cc1aaf10a31b205156"],"state_sha256":"711fe93c420aecfe90b8db8727f440589c75f1e766002b559c5133b24a05dfe7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xkGKdtajER9z5RceZXtamQhrH6N4u+U0G8hs2a5ln7+/O8nPAM5A7QfHwP+ED3YWS/Ht+6aF8UJfKAfRue0ACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T00:08:57.777616Z","bundle_sha256":"5adbbfa2445109bddfdf65edb288c190f4e6c5d4e74057964a1b35505b91f569"}}