{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WQZYLIDCVSEUTDY6VKH3OEH7H3","short_pith_number":"pith:WQZYLIDC","canonical_record":{"source":{"id":"2102.02240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-03T19:20:31Z","cross_cats_sorted":[],"title_canon_sha256":"78cf524484962efe6bb7c07fd6612a6334a1dec4a4840bf26adc0083addf3007","abstract_canon_sha256":"d0562d19472501975692298cdf88c84d0f96dc00ca66aadc08be447216578cf5"},"schema_version":"1.0"},"canonical_sha256":"b43385a062ac89498f1eaa8fb710ff3ec3e3da3c49f5dd69a32bae053854a66f","source":{"kind":"arxiv","id":"2102.02240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02240","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02240v1","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02240","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"WQZYLIDCVSEU","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"WQZYLIDCVSEUTDY6","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"WQZYLIDC","created_at":"2026-07-05T03:03:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WQZYLIDCVSEUTDY6VKH3OEH7H3","target":"record","payload":{"canonical_record":{"source":{"id":"2102.02240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-03T19:20:31Z","cross_cats_sorted":[],"title_canon_sha256":"78cf524484962efe6bb7c07fd6612a6334a1dec4a4840bf26adc0083addf3007","abstract_canon_sha256":"d0562d19472501975692298cdf88c84d0f96dc00ca66aadc08be447216578cf5"},"schema_version":"1.0"},"canonical_sha256":"b43385a062ac89498f1eaa8fb710ff3ec3e3da3c49f5dd69a32bae053854a66f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:18.681846Z","signature_b64":"t5gI78jthTnEZOohXFL1n5ygg9tCgc7u/idl5kAHpjtfB3kDPM6zeQrjLj78TPd4shmYf+zioKT5zeL1tVIyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43385a062ac89498f1eaa8fb710ff3ec3e3da3c49f5dd69a32bae053854a66f","last_reissued_at":"2026-07-05T03:03:18.681379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:18.681379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.02240","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":"2026-07-05T03:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zGtNHGbj2Xwu7tzCQQY4iL6hWv1asrA7CCGaXmIOPzAtS7BTDeN5g59LaftK/ok+FEkrB+fPhBl0pKsmYzGIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:20:59.368902Z"},"content_sha256":"6f7da6e1c3613177f0ad188e625bcbe111afe0bd91f926dc845e5c6e2af826dd","schema_version":"1.0","event_id":"sha256:6f7da6e1c3613177f0ad188e625bcbe111afe0bd91f926dc845e5c6e2af826dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WQZYLIDCVSEUTDY6VKH3OEH7H3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harvest -- An Open Source Toolkit for Extracting Posts and Post Metadata from Web Forums","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Adrian M. P. Brasoveanu, Albert Weichselbraun, Fabian Odoni, Roger Waldvogel","submitted_at":"2021-02-03T19:20:31Z","abstract_excerpt":"Automatic extraction of forum posts and metadata is a crucial but challenging task since forums do not expose their content in a standardized structure. Content extraction methods, therefore, often need customizations such as adaptations to page templates and improvements of their extraction code before they can be deployed to new forums. Most of the current solutions are also built for the more general case of content extraction from web pages and lack key features important for understanding forum content such as the identification of author metadata and information on the thread structure.\n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02240","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/2102.02240/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":"2026-07-05T03:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjAyEZutB9GQ7M9U8W68Z2dJsLuvp3z1BuHLnUwUhwKHM7CPnEmoWMQFDcsrBoaFuJ4K0sKpbB4+EKc5tD8iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:20:59.369529Z"},"content_sha256":"1819ac5e3bdda68ac573c99b5b34ba6d250efd77928f589bf5986a95a20ce22f","schema_version":"1.0","event_id":"sha256:1819ac5e3bdda68ac573c99b5b34ba6d250efd77928f589bf5986a95a20ce22f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQZYLIDCVSEUTDY6VKH3OEH7H3/bundle.json","state_url":"https://pith.science/pith/WQZYLIDCVSEUTDY6VKH3OEH7H3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQZYLIDCVSEUTDY6VKH3OEH7H3/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":"2026-08-07T07:20:59Z","links":{"resolver":"https://pith.science/pith/WQZYLIDCVSEUTDY6VKH3OEH7H3","bundle":"https://pith.science/pith/WQZYLIDCVSEUTDY6VKH3OEH7H3/bundle.json","state":"https://pith.science/pith/WQZYLIDCVSEUTDY6VKH3OEH7H3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQZYLIDCVSEUTDY6VKH3OEH7H3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WQZYLIDCVSEUTDY6VKH3OEH7H3","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":"d0562d19472501975692298cdf88c84d0f96dc00ca66aadc08be447216578cf5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-03T19:20:31Z","title_canon_sha256":"78cf524484962efe6bb7c07fd6612a6334a1dec4a4840bf26adc0083addf3007"},"schema_version":"1.0","source":{"id":"2102.02240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02240","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02240v1","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02240","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"WQZYLIDCVSEU","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"WQZYLIDCVSEUTDY6","created_at":"2026-07-05T03:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"WQZYLIDC","created_at":"2026-07-05T03:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:1819ac5e3bdda68ac573c99b5b34ba6d250efd77928f589bf5986a95a20ce22f","target":"graph","created_at":"2026-07-05T03:03:18Z","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/2102.02240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic extraction of forum posts and metadata is a crucial but challenging task since forums do not expose their content in a standardized structure. Content extraction methods, therefore, often need customizations such as adaptations to page templates and improvements of their extraction code before they can be deployed to new forums. Most of the current solutions are also built for the more general case of content extraction from web pages and lack key features important for understanding forum content such as the identification of author metadata and information on the thread structure.\n","authors_text":"Adrian M. P. Brasoveanu, Albert Weichselbraun, Fabian Odoni, Roger Waldvogel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-03T19:20:31Z","title":"Harvest -- An Open Source Toolkit for Extracting Posts and Post Metadata from Web Forums"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02240","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":"sha256:6f7da6e1c3613177f0ad188e625bcbe111afe0bd91f926dc845e5c6e2af826dd","target":"record","created_at":"2026-07-05T03:03:18Z","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":"d0562d19472501975692298cdf88c84d0f96dc00ca66aadc08be447216578cf5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-03T19:20:31Z","title_canon_sha256":"78cf524484962efe6bb7c07fd6612a6334a1dec4a4840bf26adc0083addf3007"},"schema_version":"1.0","source":{"id":"2102.02240","kind":"arxiv","version":1}},"canonical_sha256":"b43385a062ac89498f1eaa8fb710ff3ec3e3da3c49f5dd69a32bae053854a66f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b43385a062ac89498f1eaa8fb710ff3ec3e3da3c49f5dd69a32bae053854a66f","first_computed_at":"2026-07-05T03:03:18.681379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:18.681379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t5gI78jthTnEZOohXFL1n5ygg9tCgc7u/idl5kAHpjtfB3kDPM6zeQrjLj78TPd4shmYf+zioKT5zeL1tVIyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:18.681846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f7da6e1c3613177f0ad188e625bcbe111afe0bd91f926dc845e5c6e2af826dd","sha256:1819ac5e3bdda68ac573c99b5b34ba6d250efd77928f589bf5986a95a20ce22f"],"state_sha256":"6dd725a408aa2686edb623262e719c02cc4e815c8118d069d9398dc8103b3835"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mjBWPAhFYoMZsoRKNgXvVRF++xIFVSEOgHY7qDfk8ylcxnKLc8CTZg4InYowEssqkB/iosT31es2Lp9tMgAvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:20:59.374197Z","bundle_sha256":"ff94f04541770780bf5690d3e1c127624a68f4f06333b393d918c6e6c2217905"}}