{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PMFLAF6YXC745LIRKFYKHI63RG","short_pith_number":"pith:PMFLAF6Y","schema_version":"1.0","canonical_sha256":"7b0ab017d8b8bfcead115170a3a3db89a3ae0c99a712c546cfc41e23956e499b","source":{"kind":"arxiv","id":"2507.16424","version":1},"attestation_state":"computed","paper":{"title":"PromptAL: Sample-Aware Dynamic Soft Prompts for Few-Shot Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Xiang, Jinqiao Shi, Ting Zhang, Xiaojie Zhao, Yong Liu, Yong Ma","submitted_at":"2025-07-22T10:17:42Z","abstract_excerpt":"Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision boundary and perform uncertainty or diversity estimation, subsequently identifying potential high-quality samples. In few-shot scenarios, the empirical distribution often diverges significantly from the target distribution, causing the decision boundary to shift away from its optimal position. However, existing methods overlook the role of unlabeled samples in enha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.16424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-22T10:17:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"28c729dbbeacf43f603c165a668c46c817c2b4511bed4ea44cfeccf807c5019c","abstract_canon_sha256":"363a2a0d38084899d215e9d57b387a8368b0a2ff1917d25631d7d1b39d6a448f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:09.189927Z","signature_b64":"4hBxgZ2kZdEuiFxywSAOmbDfYimwUGORIfuTEuHtRG0zZacgrXf7B59WJyCWh3+ITtp0d6Tcn9FgiKFykp+lAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b0ab017d8b8bfcead115170a3a3db89a3ae0c99a712c546cfc41e23956e499b","last_reissued_at":"2026-07-05T11:41:09.189503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:09.189503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptAL: Sample-Aware Dynamic Soft Prompts for Few-Shot Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Xiang, Jinqiao Shi, Ting Zhang, Xiaojie Zhao, Yong Liu, Yong Ma","submitted_at":"2025-07-22T10:17:42Z","abstract_excerpt":"Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision boundary and perform uncertainty or diversity estimation, subsequently identifying potential high-quality samples. In few-shot scenarios, the empirical distribution often diverges significantly from the target distribution, causing the decision boundary to shift away from its optimal position. However, existing methods overlook the role of unlabeled samples in enha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16424","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/2507.16424/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.16424","created_at":"2026-07-05T11:41:09.189564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16424v1","created_at":"2026-07-05T11:41:09.189564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16424","created_at":"2026-07-05T11:41:09.189564+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMFLAF6YXC74","created_at":"2026-07-05T11:41:09.189564+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMFLAF6YXC745LIR","created_at":"2026-07-05T11:41:09.189564+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMFLAF6Y","created_at":"2026-07-05T11:41:09.189564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG","json":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG.json","graph_json":"https://pith.science/api/pith-number/PMFLAF6YXC745LIRKFYKHI63RG/graph.json","events_json":"https://pith.science/api/pith-number/PMFLAF6YXC745LIRKFYKHI63RG/events.json","paper":"https://pith.science/paper/PMFLAF6Y"},"agent_actions":{"view_html":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG","download_json":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG.json","view_paper":"https://pith.science/paper/PMFLAF6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16424&json=true","fetch_graph":"https://pith.science/api/pith-number/PMFLAF6YXC745LIRKFYKHI63RG/graph.json","fetch_events":"https://pith.science/api/pith-number/PMFLAF6YXC745LIRKFYKHI63RG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG/action/storage_attestation","attest_author":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG/action/author_attestation","sign_citation":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG/action/citation_signature","submit_replication":"https://pith.science/pith/PMFLAF6YXC745LIRKFYKHI63RG/action/replication_record"}},"created_at":"2026-07-05T11:41:09.189564+00:00","updated_at":"2026-07-05T11:41:09.189564+00:00"}