{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WYGAQAQ3K52S2VHVXZR66PEHB3","short_pith_number":"pith:WYGAQAQ3","canonical_record":{"source":{"id":"2503.00867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T12:06:16Z","cross_cats_sorted":[],"title_canon_sha256":"09d5138c844c1dacd66e671c3d72f03e4d4d534fc82fccd0b5dc03a560f06f7d","abstract_canon_sha256":"048648dbed56532a926be8aa186b5255881388a31e47488c5a4cb031d34dbb39"},"schema_version":"1.0"},"canonical_sha256":"b60c08021b57752d54f5be63ef3c870eff057729b9fb38bbae003435862e6589","source":{"kind":"arxiv","id":"2503.00867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00867","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00867v1","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00867","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"WYGAQAQ3K52S","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"WYGAQAQ3K52S2VHV","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"WYGAQAQ3","created_at":"2026-07-05T10:22:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WYGAQAQ3K52S2VHVXZR66PEHB3","target":"record","payload":{"canonical_record":{"source":{"id":"2503.00867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T12:06:16Z","cross_cats_sorted":[],"title_canon_sha256":"09d5138c844c1dacd66e671c3d72f03e4d4d534fc82fccd0b5dc03a560f06f7d","abstract_canon_sha256":"048648dbed56532a926be8aa186b5255881388a31e47488c5a4cb031d34dbb39"},"schema_version":"1.0"},"canonical_sha256":"b60c08021b57752d54f5be63ef3c870eff057729b9fb38bbae003435862e6589","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:31.279752Z","signature_b64":"TiptQfnoik4QnnddGEhIGH5CF7I4O5uhbhI28VNY8smfpUQBKArYfZI8NKolkEld5+mXCuwT/qYR/aZHRPJ2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b60c08021b57752d54f5be63ef3c870eff057729b9fb38bbae003435862e6589","last_reissued_at":"2026-07-05T10:22:31.279248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:31.279248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.00867","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":"2026-07-05T10:22:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmZCER/mbCriXOTBBE7NN/TZ9nlX5ktDIP3wJ5GO6prZ2+FifE3Jrwv1GK2TrK7gHSFbzgN1HIWi/wH2E2HHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:28:55.060129Z"},"content_sha256":"a517b10f66a0b8dc9360db7004243fa8e5140addf353cc3245c5aed9457fe2f3","schema_version":"1.0","event_id":"sha256:a517b10f66a0b8dc9360db7004243fa8e5140addf353cc3245c5aed9457fe2f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WYGAQAQ3K52S2VHVXZR66PEHB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DUAL: Diversity and Uncertainty Active Learning for Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexios Gidiotis, Grigorios Tsoumakas, Petros Stylianos Giouroukis","submitted_at":"2025-03-02T12:06:16Z","abstract_excerpt":"With the rise of large language models, neural text summarization has advanced significantly in recent years. However, even state-of-the-art models continue to rely heavily on high-quality human-annotated data for training and evaluation. Active learning is frequently used as an effective way to collect such datasets, especially when annotation resources are scarce. Active learning methods typically prioritize either uncertainty or diversity but have shown limited effectiveness in summarization, often being outperformed by random sampling. We present Diversity and Uncertainty Active Learning ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00867","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/2503.00867/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":"2026-07-05T10:22:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMZozKdjntd543u8DPkprTsf6GqaomF2RzYIywyjyyYPD44X4AZRE92nAmwxP3R0MuQZrnIxCNyhx3a8oNhmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:28:55.060655Z"},"content_sha256":"24764654493da2daf01c028d8b47ed7f000f34587bc436c4ef9ed9520f32872f","schema_version":"1.0","event_id":"sha256:24764654493da2daf01c028d8b47ed7f000f34587bc436c4ef9ed9520f32872f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WYGAQAQ3K52S2VHVXZR66PEHB3/bundle.json","state_url":"https://pith.science/pith/WYGAQAQ3K52S2VHVXZR66PEHB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WYGAQAQ3K52S2VHVXZR66PEHB3/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":"2026-08-09T20:28:55Z","links":{"resolver":"https://pith.science/pith/WYGAQAQ3K52S2VHVXZR66PEHB3","bundle":"https://pith.science/pith/WYGAQAQ3K52S2VHVXZR66PEHB3/bundle.json","state":"https://pith.science/pith/WYGAQAQ3K52S2VHVXZR66PEHB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WYGAQAQ3K52S2VHVXZR66PEHB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WYGAQAQ3K52S2VHVXZR66PEHB3","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":"048648dbed56532a926be8aa186b5255881388a31e47488c5a4cb031d34dbb39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T12:06:16Z","title_canon_sha256":"09d5138c844c1dacd66e671c3d72f03e4d4d534fc82fccd0b5dc03a560f06f7d"},"schema_version":"1.0","source":{"id":"2503.00867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00867","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00867v1","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00867","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"WYGAQAQ3K52S","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"WYGAQAQ3K52S2VHV","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"WYGAQAQ3","created_at":"2026-07-05T10:22:31Z"}],"graph_snapshots":[{"event_id":"sha256:24764654493da2daf01c028d8b47ed7f000f34587bc436c4ef9ed9520f32872f","target":"graph","created_at":"2026-07-05T10:22:31Z","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/2503.00867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of large language models, neural text summarization has advanced significantly in recent years. However, even state-of-the-art models continue to rely heavily on high-quality human-annotated data for training and evaluation. Active learning is frequently used as an effective way to collect such datasets, especially when annotation resources are scarce. Active learning methods typically prioritize either uncertainty or diversity but have shown limited effectiveness in summarization, often being outperformed by random sampling. We present Diversity and Uncertainty Active Learning (","authors_text":"Alexios Gidiotis, Grigorios Tsoumakas, Petros Stylianos Giouroukis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T12:06:16Z","title":"DUAL: Diversity and Uncertainty Active Learning for Text Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00867","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:a517b10f66a0b8dc9360db7004243fa8e5140addf353cc3245c5aed9457fe2f3","target":"record","created_at":"2026-07-05T10:22:31Z","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":"048648dbed56532a926be8aa186b5255881388a31e47488c5a4cb031d34dbb39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T12:06:16Z","title_canon_sha256":"09d5138c844c1dacd66e671c3d72f03e4d4d534fc82fccd0b5dc03a560f06f7d"},"schema_version":"1.0","source":{"id":"2503.00867","kind":"arxiv","version":1}},"canonical_sha256":"b60c08021b57752d54f5be63ef3c870eff057729b9fb38bbae003435862e6589","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b60c08021b57752d54f5be63ef3c870eff057729b9fb38bbae003435862e6589","first_computed_at":"2026-07-05T10:22:31.279248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:31.279248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TiptQfnoik4QnnddGEhIGH5CF7I4O5uhbhI28VNY8smfpUQBKArYfZI8NKolkEld5+mXCuwT/qYR/aZHRPJ2Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:31.279752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a517b10f66a0b8dc9360db7004243fa8e5140addf353cc3245c5aed9457fe2f3","sha256:24764654493da2daf01c028d8b47ed7f000f34587bc436c4ef9ed9520f32872f"],"state_sha256":"575276ba3042e462b7d6e0638d001745b850726ae6398fe3d42284cfba75ba67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jComPs5LRLf3fW3jlJW+2mvSMyK4pdXO6S/Qyc3dEkYxTCnJOgGXTx3cQAk6GSUsusc8WnfvJyCyYwEl2wX0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:28:55.064870Z","bundle_sha256":"2eacc2514b9cdc219c0ee3209b836821a1b39135522150fbc4d2b3ac49ff6130"}}