{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WGRV6AVUXS4EABTHYXIEGE5IWR","short_pith_number":"pith:WGRV6AVU","schema_version":"1.0","canonical_sha256":"b1a35f02b4bcb8400667c5d04313a8b46d6d6bf234f24caa02bb94ee4ff85416","source":{"kind":"arxiv","id":"2306.05949","version":4},"attestation_state":"computed","paper":{"title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Alberto Lusoli, Alina Leidinger, Anaelia Ovalle, Andrew Strait, Arjun Subramonian, Avijit Ghosh, Canyu Chen, Dylan Baker, Ellie Evans, Felix Friedrich, Hal Daum\\'e III, Irene Solaiman, Isabella Duan, Jennifer Mickel, Jesse Dodge, Jessica Newman, Lama Ahmad, Lukas Struppek, Margaret Mitchell, Marie-Therese Png, Michelle Lin, Ria Kalluri, Sara Hooker, Sasha Luccioni, Shubham Singh, Su Lin Blodgett, Usman Gohar, William Agnew, Xiuzhu Lin, Yacine Jernite, Zeerak Talat","submitted_at":"2023-06-09T15:05:13Z","abstract_excerpt":"Generative AI systems across modalities, ranging from text (including code), image, audio, and video, have broad social impacts, but there is no official standard for means of evaluating those impacts or for which impacts should be evaluated. In this paper, we present a guide that moves toward a standard approach in evaluating a base generative AI system for any modality in two overarching categories: what can be evaluated in a base system independent of context and what can be evaluated in a societal context. Importantly, this refers to base systems that have no predetermined application or d"},"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":"2306.05949","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2023-06-09T15:05:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ee5a42f47c3a030c01c05d0b5d649dda1f045670a5ef333d569e15a4f4bbe9f2","abstract_canon_sha256":"e33364ddcf0249acfac7429589670215fd5bcbb8a185d4767fd98ad717d974df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:03.487805Z","signature_b64":"Be33yqswSAVtaRPRTk6gRyUO8/aYjFfwPALqjaZtlrbDp9cp1gPLlZU4KN+iVLTjuza5SYNphD6Pl2upWrlgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1a35f02b4bcb8400667c5d04313a8b46d6d6bf234f24caa02bb94ee4ff85416","last_reissued_at":"2026-07-05T10:45:03.487294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:03.487294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Alberto Lusoli, Alina Leidinger, Anaelia Ovalle, Andrew Strait, Arjun Subramonian, Avijit Ghosh, Canyu Chen, Dylan Baker, Ellie Evans, Felix Friedrich, Hal Daum\\'e III, Irene Solaiman, Isabella Duan, Jennifer Mickel, Jesse Dodge, Jessica Newman, Lama Ahmad, Lukas Struppek, Margaret Mitchell, Marie-Therese Png, Michelle Lin, Ria Kalluri, Sara Hooker, Sasha Luccioni, Shubham Singh, Su Lin Blodgett, Usman Gohar, William Agnew, Xiuzhu Lin, Yacine Jernite, Zeerak Talat","submitted_at":"2023-06-09T15:05:13Z","abstract_excerpt":"Generative AI systems across modalities, ranging from text (including code), image, audio, and video, have broad social impacts, but there is no official standard for means of evaluating those impacts or for which impacts should be evaluated. In this paper, we present a guide that moves toward a standard approach in evaluating a base generative AI system for any modality in two overarching categories: what can be evaluated in a base system independent of context and what can be evaluated in a societal context. Importantly, this refers to base systems that have no predetermined application or d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05949","kind":"arxiv","version":4},"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/2306.05949/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":"2306.05949","created_at":"2026-07-05T10:45:03.487361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05949v4","created_at":"2026-07-05T10:45:03.487361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05949","created_at":"2026-07-05T10:45:03.487361+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGRV6AVUXS4E","created_at":"2026-07-05T10:45:03.487361+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGRV6AVUXS4EABTH","created_at":"2026-07-05T10:45:03.487361+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGRV6AVU","created_at":"2026-07-05T10:45:03.487361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18555","citing_title":"Rethinking Text-to-Image as Semantic-Aware Data Augmentation for Indoor Scene Recognition","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12088","citing_title":"Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23684","citing_title":"Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12172","citing_title":"SEAL: Semantic Aware Image Watermarking","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10015","citing_title":"The coordination gap in frontier AI safety policies","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22073","citing_title":"A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2509.10652","citing_title":"Vibe Coding in Product Teams: Reconfiguring AI-Assisted Workflows, Prototyping, and Collaboration","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06806","citing_title":"Big AI's Regulatory Capture: Mapping Industry Interference and Government Complicity","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15829","citing_title":"Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR","json":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR.json","graph_json":"https://pith.science/api/pith-number/WGRV6AVUXS4EABTHYXIEGE5IWR/graph.json","events_json":"https://pith.science/api/pith-number/WGRV6AVUXS4EABTHYXIEGE5IWR/events.json","paper":"https://pith.science/paper/WGRV6AVU"},"agent_actions":{"view_html":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR","download_json":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR.json","view_paper":"https://pith.science/paper/WGRV6AVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05949&json=true","fetch_graph":"https://pith.science/api/pith-number/WGRV6AVUXS4EABTHYXIEGE5IWR/graph.json","fetch_events":"https://pith.science/api/pith-number/WGRV6AVUXS4EABTHYXIEGE5IWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR/action/storage_attestation","attest_author":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR/action/author_attestation","sign_citation":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR/action/citation_signature","submit_replication":"https://pith.science/pith/WGRV6AVUXS4EABTHYXIEGE5IWR/action/replication_record"}},"created_at":"2026-07-05T10:45:03.487361+00:00","updated_at":"2026-07-05T10:45:03.487361+00:00"}