{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UOJQ4WG3WSEB5VPTM76PJTREDE","short_pith_number":"pith:UOJQ4WG3","canonical_record":{"source":{"id":"2506.03822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T10:52:55Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d49a6e581388a084ddc13fec3cf6bd03b24e15da0504ef7263de30d264e656dc","abstract_canon_sha256":"6230574864bcc4ce37359faf5624924f1dc12440793140b8923607c5a350f003"},"schema_version":"1.0"},"canonical_sha256":"a3930e58dbb4881ed5f367fcf4ce241923e9e8be0c7185afa428fbe15d5b708a","source":{"kind":"arxiv","id":"2506.03822","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03822","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03822v1","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03822","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"UOJQ4WG3WSEB","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"UOJQ4WG3WSEB5VPT","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"UOJQ4WG3","created_at":"2026-07-05T11:15:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UOJQ4WG3WSEB5VPTM76PJTREDE","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T10:52:55Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d49a6e581388a084ddc13fec3cf6bd03b24e15da0504ef7263de30d264e656dc","abstract_canon_sha256":"6230574864bcc4ce37359faf5624924f1dc12440793140b8923607c5a350f003"},"schema_version":"1.0"},"canonical_sha256":"a3930e58dbb4881ed5f367fcf4ce241923e9e8be0c7185afa428fbe15d5b708a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:52.390107Z","signature_b64":"DY+sQKw6O7JFBY1Sp4zILbI2AvvnSQ3udARxpgnbhUoGpJqMOFN5BMOeGUNoLsWyAsT4u/BQpOOVpBgBrIJ2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3930e58dbb4881ed5f367fcf4ce241923e9e8be0c7185afa428fbe15d5b708a","last_reissued_at":"2026-07-05T11:15:52.389732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:52.389732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03822","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":"2026-07-05T11:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gkzq8Xgji0lYCwh8PLDOl6LvT6irzf2K1BtD/FCH3rkPtaEmxFrXdDdjg7qABhkR6IYuekUH9pRq0eFv/3TxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:45:07.166455Z"},"content_sha256":"5ea3b33151b6344ec1d803da2c01afb0413f31ac2f87c7eb2ee8877183736026","schema_version":"1.0","event_id":"sha256:5ea3b33151b6344ec1d803da2c01afb0413f31ac2f87c7eb2ee8877183736026"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UOJQ4WG3WSEB5VPTM76PJTREDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ansgar Scherp, Fabian Karl","submitted_at":"2025-06-04T10:52:55Z","abstract_excerpt":"Publication databases rely on accurate metadata extraction from diverse web sources, yet variations in web layouts and data formats present challenges for metadata providers. This paper introduces CRAWLDoc, a new method for contextual ranking of linked web documents. Starting with a publication's URL, such as a digital object identifier, CRAWLDoc retrieves the landing page and all linked web resources, including PDFs, ORCID profiles, and supplementary materials. It embeds these resources, along with anchor texts and the URLs, into a unified representation. For evaluating CRAWLDoc, we have crea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03822","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/2506.03822/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":"2026-07-05T11:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9VINMA0kISzuK9fGg6nY9FED2zR6SdVZN5uZUoz9xfSpxm40vU7ciE70N0u02zBHtKhckCzZMFr0CHVW+gbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:45:07.166953Z"},"content_sha256":"b8e363e9591ab4d0b0ced4910d0676db51967c26cd7a1e55fd46bfac3068e5b0","schema_version":"1.0","event_id":"sha256:b8e363e9591ab4d0b0ced4910d0676db51967c26cd7a1e55fd46bfac3068e5b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/bundle.json","state_url":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/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":"2026-08-09T16:45:07Z","links":{"resolver":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE","bundle":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/bundle.json","state":"https://pith.science/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOJQ4WG3WSEB5VPTM76PJTREDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UOJQ4WG3WSEB5VPTM76PJTREDE","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":"6230574864bcc4ce37359faf5624924f1dc12440793140b8923607c5a350f003","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T10:52:55Z","title_canon_sha256":"d49a6e581388a084ddc13fec3cf6bd03b24e15da0504ef7263de30d264e656dc"},"schema_version":"1.0","source":{"id":"2506.03822","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03822","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03822v1","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03822","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"UOJQ4WG3WSEB","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"UOJQ4WG3WSEB5VPT","created_at":"2026-07-05T11:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"UOJQ4WG3","created_at":"2026-07-05T11:15:52Z"}],"graph_snapshots":[{"event_id":"sha256:b8e363e9591ab4d0b0ced4910d0676db51967c26cd7a1e55fd46bfac3068e5b0","target":"graph","created_at":"2026-07-05T11:15:52Z","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/2506.03822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Publication databases rely on accurate metadata extraction from diverse web sources, yet variations in web layouts and data formats present challenges for metadata providers. This paper introduces CRAWLDoc, a new method for contextual ranking of linked web documents. Starting with a publication's URL, such as a digital object identifier, CRAWLDoc retrieves the landing page and all linked web resources, including PDFs, ORCID profiles, and supplementary materials. It embeds these resources, along with anchor texts and the URLs, into a unified representation. For evaluating CRAWLDoc, we have crea","authors_text":"Ansgar Scherp, Fabian Karl","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T10:52:55Z","title":"CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03822","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":"sha256:5ea3b33151b6344ec1d803da2c01afb0413f31ac2f87c7eb2ee8877183736026","target":"record","created_at":"2026-07-05T11:15:52Z","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":"6230574864bcc4ce37359faf5624924f1dc12440793140b8923607c5a350f003","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T10:52:55Z","title_canon_sha256":"d49a6e581388a084ddc13fec3cf6bd03b24e15da0504ef7263de30d264e656dc"},"schema_version":"1.0","source":{"id":"2506.03822","kind":"arxiv","version":1}},"canonical_sha256":"a3930e58dbb4881ed5f367fcf4ce241923e9e8be0c7185afa428fbe15d5b708a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3930e58dbb4881ed5f367fcf4ce241923e9e8be0c7185afa428fbe15d5b708a","first_computed_at":"2026-07-05T11:15:52.389732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:52.389732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DY+sQKw6O7JFBY1Sp4zILbI2AvvnSQ3udARxpgnbhUoGpJqMOFN5BMOeGUNoLsWyAsT4u/BQpOOVpBgBrIJ2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:52.390107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03822","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ea3b33151b6344ec1d803da2c01afb0413f31ac2f87c7eb2ee8877183736026","sha256:b8e363e9591ab4d0b0ced4910d0676db51967c26cd7a1e55fd46bfac3068e5b0"],"state_sha256":"a208cbfb78d398160ab6a50b3355174e58bba3e648753f781954bb34d0060a06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9R71bFB2Tn48Zrt38ccbom0ZMSlwO0qMaKVK/n8TXRMFvHSbjEL1CeD0qycHT+ZR5JV7S0jd1RT8vXXmml6cBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:45:07.170682Z","bundle_sha256":"0116fcb36e4136f08265370f4c8c2a914aac4c174b1266edc68e99078f210f85"}}