{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MBD5O65AIKAO3HH4CTV6IU7EF4","short_pith_number":"pith:MBD5O65A","schema_version":"1.0","canonical_sha256":"6047d77ba04280ed9cfc14ebe453e42f17da76e0d044c18422a51b25d0b3c4ff","source":{"kind":"arxiv","id":"2412.14849","version":1},"attestation_state":"computed","paper":{"title":"DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongling Xu, Qianlong Wang, Ruifeng Xu, Yice Zhang","submitted_at":"2024-12-19T13:39:47Z","abstract_excerpt":"Recently developed large language models (LLMs) have presented promising new avenues to address data scarcity in low-resource scenarios. In few-shot aspect-based sentiment analysis (ABSA), previous efforts have explored data augmentation techniques, which prompt LLMs to generate new samples by modifying existing ones. However, these methods fail to produce adequately diverse data, impairing their effectiveness. Besides, some studies apply in-context learning for ABSA by using specific instructions and a few selected examples as prompts. Though promising, LLMs often yield labels that deviate fr"},"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":"2412.14849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T13:39:47Z","cross_cats_sorted":[],"title_canon_sha256":"67313ed7f72ae0bfaf33e61f045900e6b3255139706035966b66085f7c353319","abstract_canon_sha256":"7aea234dc1ab4ec4750d3972d6156c52b3b400192a7643583d2fb0c01d6926a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:53.569231Z","signature_b64":"fn2vrg/cTRA6uMYwIdYtMArE1lcxAJLSN/M09XiRSyV7j/i8ZMf1r2jn6dFfGuQ5jld6oNb1TLMfHXSRRHIrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6047d77ba04280ed9cfc14ebe453e42f17da76e0d044c18422a51b25d0b3c4ff","last_reissued_at":"2026-07-05T09:51:53.568772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:53.568772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongling Xu, Qianlong Wang, Ruifeng Xu, Yice Zhang","submitted_at":"2024-12-19T13:39:47Z","abstract_excerpt":"Recently developed large language models (LLMs) have presented promising new avenues to address data scarcity in low-resource scenarios. In few-shot aspect-based sentiment analysis (ABSA), previous efforts have explored data augmentation techniques, which prompt LLMs to generate new samples by modifying existing ones. However, these methods fail to produce adequately diverse data, impairing their effectiveness. Besides, some studies apply in-context learning for ABSA by using specific instructions and a few selected examples as prompts. Though promising, LLMs often yield labels that deviate fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14849","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/2412.14849/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":"2412.14849","created_at":"2026-07-05T09:51:53.568832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14849v1","created_at":"2026-07-05T09:51:53.568832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14849","created_at":"2026-07-05T09:51:53.568832+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBD5O65AIKAO","created_at":"2026-07-05T09:51:53.568832+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBD5O65AIKAO3HH4","created_at":"2026-07-05T09:51:53.568832+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBD5O65A","created_at":"2026-07-05T09:51:53.568832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07148","citing_title":"Semantic-preserved Augmentation with Confidence-weighted Fine-tuning for Aspect Category Sentiment Analysis","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4","json":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4.json","graph_json":"https://pith.science/api/pith-number/MBD5O65AIKAO3HH4CTV6IU7EF4/graph.json","events_json":"https://pith.science/api/pith-number/MBD5O65AIKAO3HH4CTV6IU7EF4/events.json","paper":"https://pith.science/paper/MBD5O65A"},"agent_actions":{"view_html":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4","download_json":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4.json","view_paper":"https://pith.science/paper/MBD5O65A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14849&json=true","fetch_graph":"https://pith.science/api/pith-number/MBD5O65AIKAO3HH4CTV6IU7EF4/graph.json","fetch_events":"https://pith.science/api/pith-number/MBD5O65AIKAO3HH4CTV6IU7EF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4/action/storage_attestation","attest_author":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4/action/author_attestation","sign_citation":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4/action/citation_signature","submit_replication":"https://pith.science/pith/MBD5O65AIKAO3HH4CTV6IU7EF4/action/replication_record"}},"created_at":"2026-07-05T09:51:53.568832+00:00","updated_at":"2026-07-05T09:51:53.568832+00:00"}