{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LO7EFIOWYCFG2V4776PJZ4EH2Y","short_pith_number":"pith:LO7EFIOW","schema_version":"1.0","canonical_sha256":"5bbe42a1d6c08a6d579fff9e9cf087d62d6932449991749e4a8a7077276c3d89","source":{"kind":"arxiv","id":"2509.25682","version":2},"attestation_state":"computed","paper":{"title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Li, Jing Liu, Shiyu Wu, Shuyan Li, Yequan Wang","submitted_at":"2025-09-30T02:36:40Z","abstract_excerpt":"AI-generated image (AIGI) attribution presents a pressing challenge that goes beyond mere AIGI detection, aiming to identify the source model or technique responsible for a synthetic image. However, most previous source attribution methods operate in a closed-set manner, which necessitates retraining to recognize any novel category, preventing adaptation to the rapid evolution of image generation. In this work, we propose a new paradigm for synthetic image attribution, termed few-shot attribution. This paradigm targets the reliable identification of unseen generators using only limited samples"},"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":"2509.25682","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-30T02:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"e99cbddb904b5b1eb875aa3f12c738cee6f533ab8d73ce9a2c30de5b0e9fe5b4","abstract_canon_sha256":"cac85d995fb154fcba9568b38bfefdd576b1031cd9a17bf02c253758e47be504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:41.801683Z","signature_b64":"A2JjDNttSHA1R/QgAnxjNO1yRgelMDItwOsVF7nEIkKJRgydWsu3CEENVvtX8YME7/wi1H7MWoFRK3rTbQq6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bbe42a1d6c08a6d579fff9e9cf087d62d6932449991749e4a8a7077276c3d89","last_reissued_at":"2026-07-01T01:17:41.801062Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:41.801062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Li, Jing Liu, Shiyu Wu, Shuyan Li, Yequan Wang","submitted_at":"2025-09-30T02:36:40Z","abstract_excerpt":"AI-generated image (AIGI) attribution presents a pressing challenge that goes beyond mere AIGI detection, aiming to identify the source model or technique responsible for a synthetic image. However, most previous source attribution methods operate in a closed-set manner, which necessitates retraining to recognize any novel category, preventing adaptation to the rapid evolution of image generation. In this work, we propose a new paradigm for synthetic image attribution, termed few-shot attribution. This paradigm targets the reliable identification of unseen generators using only limited samples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.25682","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/2509.25682/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":"2509.25682","created_at":"2026-07-01T01:17:41.801129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.25682v2","created_at":"2026-07-01T01:17:41.801129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.25682","created_at":"2026-07-01T01:17:41.801129+00:00"},{"alias_kind":"pith_short_12","alias_value":"LO7EFIOWYCFG","created_at":"2026-07-01T01:17:41.801129+00:00"},{"alias_kind":"pith_short_16","alias_value":"LO7EFIOWYCFG2V47","created_at":"2026-07-01T01:17:41.801129+00:00"},{"alias_kind":"pith_short_8","alias_value":"LO7EFIOW","created_at":"2026-07-01T01:17:41.801129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.12967","citing_title":"ImageAttributionBench: How Far Are We from Generalizable Attribution?","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y","json":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y.json","graph_json":"https://pith.science/api/pith-number/LO7EFIOWYCFG2V4776PJZ4EH2Y/graph.json","events_json":"https://pith.science/api/pith-number/LO7EFIOWYCFG2V4776PJZ4EH2Y/events.json","paper":"https://pith.science/paper/LO7EFIOW"},"agent_actions":{"view_html":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y","download_json":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y.json","view_paper":"https://pith.science/paper/LO7EFIOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.25682&json=true","fetch_graph":"https://pith.science/api/pith-number/LO7EFIOWYCFG2V4776PJZ4EH2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/LO7EFIOWYCFG2V4776PJZ4EH2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y/action/storage_attestation","attest_author":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y/action/author_attestation","sign_citation":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y/action/citation_signature","submit_replication":"https://pith.science/pith/LO7EFIOWYCFG2V4776PJZ4EH2Y/action/replication_record"}},"created_at":"2026-07-01T01:17:41.801129+00:00","updated_at":"2026-07-01T01:17:41.801129+00:00"}