{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TZNTAOBJWLY7GMC6ICAQVYKDJ2","short_pith_number":"pith:TZNTAOBJ","canonical_record":{"source":{"id":"2411.19295","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T18:04:31Z","cross_cats_sorted":[],"title_canon_sha256":"9192c5fcc16b79d3cc9e6706197a5d7a97af06e4bf9ee71c40d3ccda49d42d9b","abstract_canon_sha256":"27a26eb4e1f5d657cd86cc13b99d1d7d75144b4e415f32c4ca0ece8ae2986c02"},"schema_version":"1.0"},"canonical_sha256":"9e5b303829b2f1f3305e40810ae1434e8bfe840262f5c0941c01b2520ca34090","source":{"kind":"arxiv","id":"2411.19295","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19295","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19295v2","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19295","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"TZNTAOBJWLY7","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"TZNTAOBJWLY7GMC6","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"TZNTAOBJ","created_at":"2026-07-05T10:27:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TZNTAOBJWLY7GMC6ICAQVYKDJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19295","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T18:04:31Z","cross_cats_sorted":[],"title_canon_sha256":"9192c5fcc16b79d3cc9e6706197a5d7a97af06e4bf9ee71c40d3ccda49d42d9b","abstract_canon_sha256":"27a26eb4e1f5d657cd86cc13b99d1d7d75144b4e415f32c4ca0ece8ae2986c02"},"schema_version":"1.0"},"canonical_sha256":"9e5b303829b2f1f3305e40810ae1434e8bfe840262f5c0941c01b2520ca34090","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:20.575564Z","signature_b64":"uXt45G5qxKDW9DWWd+PZSu9VtOrr2QbDIaX2d/TAvaxbGWYjI14TFNbMxsdDNHY2G3FdkOX6W0cFh7ApiDlADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e5b303829b2f1f3305e40810ae1434e8bfe840262f5c0941c01b2520ca34090","last_reissued_at":"2026-07-05T10:27:20.574991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:20.574991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19295","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":"2026-07-05T10:27:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MUFf2n7LsDTNzHkxfzyqqBGv1p1XgXdXxg6/qIYbF3dH1glsG2FR0gRlBPiM0XWCubox7ZeNWl2zFUyViYryAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:23:54.000238Z"},"content_sha256":"5d2d3c9a1b27a31eea6e44a99a132f9a456308c3ac0924e8d37ecf7e7320a7c7","schema_version":"1.0","event_id":"sha256:5d2d3c9a1b27a31eea6e44a99a132f9a456308c3ac0924e8d37ecf7e7320a7c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TZNTAOBJWLY7GMC6ICAQVYKDJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Information in a Low-resource Setting: Case Study on Bioinformatics Workflows","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aur\\'elie N\\'ev\\'eol, Cl\\'emence Sebe, Olivier Ferret, Sarah Cohen-Boulakia","submitted_at":"2024-11-28T18:04:31Z","abstract_excerpt":"Bioinformatics workflows are essential for complex biological data analyses and are often described in scientific articles with source code in public repositories. Extracting detailed workflow information from articles can improve accessibility and reusability but is hindered by limited annotated corpora. To address this, we framed the problem as a low-resource extraction task and tested four strategies: 1) creating a tailored annotated corpus, 2) few-shot named-entity recognition (NER) with an autoregressive language model, 3) NER using masked language models with existing and new corpora, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19295","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/2411.19295/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":"2026-07-05T10:27:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LJoE3QtUJFNjmEBHfGGYCaJ+rQwJJzea3U1Zxpkt7TPEjCAU5QXRof1reJzifeXLJMKiQ6f7n4rOzr/jtzNRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:23:54.001090Z"},"content_sha256":"df9cfbee537be34a2ea2cf30b1e4457df92ab3b55cd436d427290d358325795c","schema_version":"1.0","event_id":"sha256:df9cfbee537be34a2ea2cf30b1e4457df92ab3b55cd436d427290d358325795c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TZNTAOBJWLY7GMC6ICAQVYKDJ2/bundle.json","state_url":"https://pith.science/pith/TZNTAOBJWLY7GMC6ICAQVYKDJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TZNTAOBJWLY7GMC6ICAQVYKDJ2/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":"2026-08-18T22:23:54Z","links":{"resolver":"https://pith.science/pith/TZNTAOBJWLY7GMC6ICAQVYKDJ2","bundle":"https://pith.science/pith/TZNTAOBJWLY7GMC6ICAQVYKDJ2/bundle.json","state":"https://pith.science/pith/TZNTAOBJWLY7GMC6ICAQVYKDJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TZNTAOBJWLY7GMC6ICAQVYKDJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TZNTAOBJWLY7GMC6ICAQVYKDJ2","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":"27a26eb4e1f5d657cd86cc13b99d1d7d75144b4e415f32c4ca0ece8ae2986c02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T18:04:31Z","title_canon_sha256":"9192c5fcc16b79d3cc9e6706197a5d7a97af06e4bf9ee71c40d3ccda49d42d9b"},"schema_version":"1.0","source":{"id":"2411.19295","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19295","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19295v2","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19295","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"TZNTAOBJWLY7","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"TZNTAOBJWLY7GMC6","created_at":"2026-07-05T10:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"TZNTAOBJ","created_at":"2026-07-05T10:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:df9cfbee537be34a2ea2cf30b1e4457df92ab3b55cd436d427290d358325795c","target":"graph","created_at":"2026-07-05T10:27:20Z","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/2411.19295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bioinformatics workflows are essential for complex biological data analyses and are often described in scientific articles with source code in public repositories. Extracting detailed workflow information from articles can improve accessibility and reusability but is hindered by limited annotated corpora. To address this, we framed the problem as a low-resource extraction task and tested four strategies: 1) creating a tailored annotated corpus, 2) few-shot named-entity recognition (NER) with an autoregressive language model, 3) NER using masked language models with existing and new corpora, an","authors_text":"Aur\\'elie N\\'ev\\'eol, Cl\\'emence Sebe, Olivier Ferret, Sarah Cohen-Boulakia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T18:04:31Z","title":"Extracting Information in a Low-resource Setting: Case Study on Bioinformatics Workflows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19295","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":"sha256:5d2d3c9a1b27a31eea6e44a99a132f9a456308c3ac0924e8d37ecf7e7320a7c7","target":"record","created_at":"2026-07-05T10:27:20Z","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":"27a26eb4e1f5d657cd86cc13b99d1d7d75144b4e415f32c4ca0ece8ae2986c02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T18:04:31Z","title_canon_sha256":"9192c5fcc16b79d3cc9e6706197a5d7a97af06e4bf9ee71c40d3ccda49d42d9b"},"schema_version":"1.0","source":{"id":"2411.19295","kind":"arxiv","version":2}},"canonical_sha256":"9e5b303829b2f1f3305e40810ae1434e8bfe840262f5c0941c01b2520ca34090","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e5b303829b2f1f3305e40810ae1434e8bfe840262f5c0941c01b2520ca34090","first_computed_at":"2026-07-05T10:27:20.574991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:20.574991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXt45G5qxKDW9DWWd+PZSu9VtOrr2QbDIaX2d/TAvaxbGWYjI14TFNbMxsdDNHY2G3FdkOX6W0cFh7ApiDlADg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:20.575564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19295","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d2d3c9a1b27a31eea6e44a99a132f9a456308c3ac0924e8d37ecf7e7320a7c7","sha256:df9cfbee537be34a2ea2cf30b1e4457df92ab3b55cd436d427290d358325795c"],"state_sha256":"1bf9c8aee01affa491cece857a50c448d9515f9d6053eb94dc1d3a5aa85ffd8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kx37dODz3El7Jpc+N0RF1iriRaZtWaCT5l3wsoieVghzQXB9aiKsWy1GbOlebyEs9FawPkLzA0OnYctr+ImMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:23:54.007211Z","bundle_sha256":"48ae9547587014d4748cdb1065b94c7e8971725ea178fe925a5a2d5de1a5fb64"}}