{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BXQKTSB7UUSCQ3KBHGQTRTIELL","short_pith_number":"pith:BXQKTSB7","canonical_record":{"source":{"id":"2205.14677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2022-05-29T14:30:31Z","cross_cats_sorted":[],"title_canon_sha256":"7ee9259c0823cf7a01567d7bf61714f11b90af2c1efd5e1ba0a41882e55326c0","abstract_canon_sha256":"fe6a392e7e2f0e6851643cc1557ed6348c593196966ad51d502dcd87295d269b"},"schema_version":"1.0"},"canonical_sha256":"0de0a9c83fa524286d4139a138cd045ad705291cb4ed70f05c46bbebefe6aa7f","source":{"kind":"arxiv","id":"2205.14677","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14677","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14677v2","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14677","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"BXQKTSB7UUSC","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"BXQKTSB7UUSCQ3KB","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"BXQKTSB7","created_at":"2026-07-05T04:54:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BXQKTSB7UUSCQ3KBHGQTRTIELL","target":"record","payload":{"canonical_record":{"source":{"id":"2205.14677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2022-05-29T14:30:31Z","cross_cats_sorted":[],"title_canon_sha256":"7ee9259c0823cf7a01567d7bf61714f11b90af2c1efd5e1ba0a41882e55326c0","abstract_canon_sha256":"fe6a392e7e2f0e6851643cc1557ed6348c593196966ad51d502dcd87295d269b"},"schema_version":"1.0"},"canonical_sha256":"0de0a9c83fa524286d4139a138cd045ad705291cb4ed70f05c46bbebefe6aa7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:59.987941Z","signature_b64":"AlXs7QmV4FIraZJws0ajBqL1VNcHGA5BJlVx3SQDqMNdgdYuHDXdJtDcIcDqGX84skJGjAA9uUFPsVpU5SVTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0de0a9c83fa524286d4139a138cd045ad705291cb4ed70f05c46bbebefe6aa7f","last_reissued_at":"2026-07-05T04:54:59.987446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:59.987446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.14677","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JJgGoTWCFnuIVbRx73hxZuAlAwfzxaFoqW5d12TMmPFFYFZUMEOg7yWxZmSAe+VAXJTwE3pTi6yMZo5ODTrCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:38:46.477925Z"},"content_sha256":"cae323348323061769e4d58ca98f7b3b98a39712aa7b7ab3a8b59c607dbd5843","schema_version":"1.0","event_id":"sha256:cae323348323061769e4d58ca98f7b3b98a39712aa7b7ab3a8b59c607dbd5843"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BXQKTSB7UUSCQ3KBHGQTRTIELL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured references from PDF articles: assessing the tools for bibliographic reference extraction and parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"Alessia Cioffi, Silvio Peroni","submitted_at":"2022-05-29T14:30:31Z","abstract_excerpt":"Many solutions have been provided to extract bibliographic references from PDF papers. Machine learning, rule-based and regular expressions approaches were among the most used methods adopted in tools for addressing this task. This work aims to identify and evaluate all and only the tools which, given a full-text paper in PDF format, can recognise, extract and parse bibliographic references. We identified seven tools: Anystyle, Cermine, ExCite, Grobid, Pdfssa4met, Scholarcy and Science Parse. We compared and evaluated them against a corpus of 56 PDF articles published in 27 subject areas. Inde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14677","kind":"arxiv","version":2},"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/2205.14677/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":"2026-07-05T04:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"41rVKNt2GUVZt+/IR0vGrOyrV44PffmN0KsaQw9OUfO3vV4AxBoYoqUNLggf8CX97qPPMIMqob04nN2rIx7aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:38:46.478486Z"},"content_sha256":"6563e771c8f0eb7893109c55581a331f60d8ab2e8ea18f389bb87e2fa46fe852","schema_version":"1.0","event_id":"sha256:6563e771c8f0eb7893109c55581a331f60d8ab2e8ea18f389bb87e2fa46fe852"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXQKTSB7UUSCQ3KBHGQTRTIELL/bundle.json","state_url":"https://pith.science/pith/BXQKTSB7UUSCQ3KBHGQTRTIELL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXQKTSB7UUSCQ3KBHGQTRTIELL/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":"2026-08-14T22:38:46Z","links":{"resolver":"https://pith.science/pith/BXQKTSB7UUSCQ3KBHGQTRTIELL","bundle":"https://pith.science/pith/BXQKTSB7UUSCQ3KBHGQTRTIELL/bundle.json","state":"https://pith.science/pith/BXQKTSB7UUSCQ3KBHGQTRTIELL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXQKTSB7UUSCQ3KBHGQTRTIELL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BXQKTSB7UUSCQ3KBHGQTRTIELL","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":"fe6a392e7e2f0e6851643cc1557ed6348c593196966ad51d502dcd87295d269b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2022-05-29T14:30:31Z","title_canon_sha256":"7ee9259c0823cf7a01567d7bf61714f11b90af2c1efd5e1ba0a41882e55326c0"},"schema_version":"1.0","source":{"id":"2205.14677","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14677","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14677v2","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14677","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"BXQKTSB7UUSC","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"BXQKTSB7UUSCQ3KB","created_at":"2026-07-05T04:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"BXQKTSB7","created_at":"2026-07-05T04:54:59Z"}],"graph_snapshots":[{"event_id":"sha256:6563e771c8f0eb7893109c55581a331f60d8ab2e8ea18f389bb87e2fa46fe852","target":"graph","created_at":"2026-07-05T04:54:59Z","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/2205.14677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many solutions have been provided to extract bibliographic references from PDF papers. Machine learning, rule-based and regular expressions approaches were among the most used methods adopted in tools for addressing this task. This work aims to identify and evaluate all and only the tools which, given a full-text paper in PDF format, can recognise, extract and parse bibliographic references. We identified seven tools: Anystyle, Cermine, ExCite, Grobid, Pdfssa4met, Scholarcy and Science Parse. We compared and evaluated them against a corpus of 56 PDF articles published in 27 subject areas. Inde","authors_text":"Alessia Cioffi, Silvio Peroni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2022-05-29T14:30:31Z","title":"Structured references from PDF articles: assessing the tools for bibliographic reference extraction and parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14677","kind":"arxiv","version":2},"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:cae323348323061769e4d58ca98f7b3b98a39712aa7b7ab3a8b59c607dbd5843","target":"record","created_at":"2026-07-05T04:54:59Z","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":"fe6a392e7e2f0e6851643cc1557ed6348c593196966ad51d502dcd87295d269b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2022-05-29T14:30:31Z","title_canon_sha256":"7ee9259c0823cf7a01567d7bf61714f11b90af2c1efd5e1ba0a41882e55326c0"},"schema_version":"1.0","source":{"id":"2205.14677","kind":"arxiv","version":2}},"canonical_sha256":"0de0a9c83fa524286d4139a138cd045ad705291cb4ed70f05c46bbebefe6aa7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0de0a9c83fa524286d4139a138cd045ad705291cb4ed70f05c46bbebefe6aa7f","first_computed_at":"2026-07-05T04:54:59.987446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:59.987446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AlXs7QmV4FIraZJws0ajBqL1VNcHGA5BJlVx3SQDqMNdgdYuHDXdJtDcIcDqGX84skJGjAA9uUFPsVpU5SVTCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:59.987941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14677","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cae323348323061769e4d58ca98f7b3b98a39712aa7b7ab3a8b59c607dbd5843","sha256:6563e771c8f0eb7893109c55581a331f60d8ab2e8ea18f389bb87e2fa46fe852"],"state_sha256":"2d45fb9385bc06c721016e569b4f7a2ec4ea156c4dcdc164a1d539296496700e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jWpKOyPBYHQxwzKKcjLGapQfMcgu2GNOBTCrADqIgZsqSk2NZivTq7qaDnyEbtwp96AFC1VCCJhxkemyCtfABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:38:46.484218Z","bundle_sha256":"a7c22e66250a3537f615d3b9e45df6fda9e3cf249b63e57375f50caf781f8a0e"}}