{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AM5ABKMIV4PFJ2HD3GAMFF62AT","short_pith_number":"pith:AM5ABKMI","canonical_record":{"source":{"id":"2407.17284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T13:50:21Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"a03559cc55e014f2673f082849c225569a3cbbd44a3d300cf2176e9791bbdf3c","abstract_canon_sha256":"0789338a27a1218cda6778689cebdd9669fb3e6cf385179a7711f50235fefa41"},"schema_version":"1.0"},"canonical_sha256":"033a00a988af1e54e8e3d980c297da04e0aa07e1f9aa568b94321a622c05dc61","source":{"kind":"arxiv","id":"2407.17284","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17284","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17284v1","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17284","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"pith_short_12","alias_value":"AM5ABKMIV4PF","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"pith_short_16","alias_value":"AM5ABKMIV4PFJ2HD","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"pith_short_8","alias_value":"AM5ABKMI","created_at":"2026-07-05T08:48:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AM5ABKMIV4PFJ2HD3GAMFF62AT","target":"record","payload":{"canonical_record":{"source":{"id":"2407.17284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T13:50:21Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"a03559cc55e014f2673f082849c225569a3cbbd44a3d300cf2176e9791bbdf3c","abstract_canon_sha256":"0789338a27a1218cda6778689cebdd9669fb3e6cf385179a7711f50235fefa41"},"schema_version":"1.0"},"canonical_sha256":"033a00a988af1e54e8e3d980c297da04e0aa07e1f9aa568b94321a622c05dc61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:05.882964Z","signature_b64":"yYbfe6Mwr8D2SP6liEqs8T4AEQgJJL4Pc90Oa5SGveG3GDx0SFf0ALnbKOLPd03LpqKb0FCnMXKRZAk3rD9dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"033a00a988af1e54e8e3d980c297da04e0aa07e1f9aa568b94321a622c05dc61","last_reissued_at":"2026-07-05T08:48:05.882497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:05.882497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.17284","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":"2026-07-05T08:48:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2ux5jlwwdxyOYjwE1sJW/9XODHflEvHUHL/kcpiMa8YKINTRV+cT+rzkRngnFRaqG93Mi/lczbnisggRuh5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:21:12.763666Z"},"content_sha256":"4bd4a5708a69980caadb5d0ee7af4711ec2c5d8e5775032a957f4ec811d5bf75","schema_version":"1.0","event_id":"sha256:4bd4a5708a69980caadb5d0ee7af4711ec2c5d8e5775032a957f4ec811d5bf75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AM5ABKMIV4PFJ2HD3GAMFF62AT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.LG","authors_text":"Celso Fran\\c{c}a, Claudio Andrade, Fabiano Bel\\'em, Leonardo Rocha, Marcos Andr\\'e Gon\\c{c}alves, Washington Cunha","submitted_at":"2024-07-24T13:50:21Z","abstract_excerpt":"This is the first work to investigate the effectiveness of BERT-based contextual embeddings in active learning (AL) tasks on cold-start scenarios, where traditional fine-tuning is infeasible due to the absence of labeled data. Our primary contribution is the proposal of a more robust fine-tuning pipeline - DoTCAL - that diminishes the reliance on labeled data in AL using two steps: (1) fully leveraging unlabeled data through domain adaptation of the embeddings via masked language modeling and (2) further adjusting model weights using labeled data selected by AL. Our evaluation contrasts BERT-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17284","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/2407.17284/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":"2026-07-05T08:48:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GkMYwl+J02ag8HVBG25eR/dDEZUFi27gD44opOl49palPaprhoGepMo71QDhnL+Ou6bIOmnO9h01kaXCAUGxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:21:12.764037Z"},"content_sha256":"f9834e28d0640d5207bf2fc65b27136b2dc4fb94aa0bffe769db54cbc4bc1759","schema_version":"1.0","event_id":"sha256:f9834e28d0640d5207bf2fc65b27136b2dc4fb94aa0bffe769db54cbc4bc1759"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AM5ABKMIV4PFJ2HD3GAMFF62AT/bundle.json","state_url":"https://pith.science/pith/AM5ABKMIV4PFJ2HD3GAMFF62AT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AM5ABKMIV4PFJ2HD3GAMFF62AT/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":"2026-07-06T15:21:12Z","links":{"resolver":"https://pith.science/pith/AM5ABKMIV4PFJ2HD3GAMFF62AT","bundle":"https://pith.science/pith/AM5ABKMIV4PFJ2HD3GAMFF62AT/bundle.json","state":"https://pith.science/pith/AM5ABKMIV4PFJ2HD3GAMFF62AT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AM5ABKMIV4PFJ2HD3GAMFF62AT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AM5ABKMIV4PFJ2HD3GAMFF62AT","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":"0789338a27a1218cda6778689cebdd9669fb3e6cf385179a7711f50235fefa41","cross_cats_sorted":["cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T13:50:21Z","title_canon_sha256":"a03559cc55e014f2673f082849c225569a3cbbd44a3d300cf2176e9791bbdf3c"},"schema_version":"1.0","source":{"id":"2407.17284","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17284","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17284v1","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17284","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"pith_short_12","alias_value":"AM5ABKMIV4PF","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"pith_short_16","alias_value":"AM5ABKMIV4PFJ2HD","created_at":"2026-07-05T08:48:05Z"},{"alias_kind":"pith_short_8","alias_value":"AM5ABKMI","created_at":"2026-07-05T08:48:05Z"}],"graph_snapshots":[{"event_id":"sha256:f9834e28d0640d5207bf2fc65b27136b2dc4fb94aa0bffe769db54cbc4bc1759","target":"graph","created_at":"2026-07-05T08:48:05Z","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/2407.17284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This is the first work to investigate the effectiveness of BERT-based contextual embeddings in active learning (AL) tasks on cold-start scenarios, where traditional fine-tuning is infeasible due to the absence of labeled data. Our primary contribution is the proposal of a more robust fine-tuning pipeline - DoTCAL - that diminishes the reliance on labeled data in AL using two steps: (1) fully leveraging unlabeled data through domain adaptation of the embeddings via masked language modeling and (2) further adjusting model weights using labeled data selected by AL. Our evaluation contrasts BERT-b","authors_text":"Celso Fran\\c{c}a, Claudio Andrade, Fabiano Bel\\'em, Leonardo Rocha, Marcos Andr\\'e Gon\\c{c}alves, Washington Cunha","cross_cats":["cs.DB","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T13:50:21Z","title":"A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17284","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":"sha256:4bd4a5708a69980caadb5d0ee7af4711ec2c5d8e5775032a957f4ec811d5bf75","target":"record","created_at":"2026-07-05T08:48:05Z","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":"0789338a27a1218cda6778689cebdd9669fb3e6cf385179a7711f50235fefa41","cross_cats_sorted":["cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T13:50:21Z","title_canon_sha256":"a03559cc55e014f2673f082849c225569a3cbbd44a3d300cf2176e9791bbdf3c"},"schema_version":"1.0","source":{"id":"2407.17284","kind":"arxiv","version":1}},"canonical_sha256":"033a00a988af1e54e8e3d980c297da04e0aa07e1f9aa568b94321a622c05dc61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"033a00a988af1e54e8e3d980c297da04e0aa07e1f9aa568b94321a622c05dc61","first_computed_at":"2026-07-05T08:48:05.882497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:05.882497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yYbfe6Mwr8D2SP6liEqs8T4AEQgJJL4Pc90Oa5SGveG3GDx0SFf0ALnbKOLPd03LpqKb0FCnMXKRZAk3rD9dAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:05.882964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17284","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bd4a5708a69980caadb5d0ee7af4711ec2c5d8e5775032a957f4ec811d5bf75","sha256:f9834e28d0640d5207bf2fc65b27136b2dc4fb94aa0bffe769db54cbc4bc1759"],"state_sha256":"fa8518cf02651b226d55ab39dcba46673dab9098035e966fcd8ecda4ee119e5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NuuexunhwLq0vPj77SzlBLeV1TDNa4qbF2QOEVuca08pzzJ6HDUzWMqfrmrgelxySUFivzkOQD4C3Ux3yOEdDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:21:12.766107Z","bundle_sha256":"7d8ce06c466791565ac1aa117be0154e4e0b0704ee150626fd5076e2c9328935"}}