{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IRX5WUIEDA3FVLNYHL7S7TWFBA","short_pith_number":"pith:IRX5WUIE","schema_version":"1.0","canonical_sha256":"446fdb510418365aadb83aff2fcec50810b4a98e46508933d2d0397a1ca7a6a9","source":{"kind":"arxiv","id":"2502.09369","version":1},"attestation_state":"computed","paper":{"title":"Language Agents as Digital Representatives in Collective Decision-Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.LG","authors_text":"Andrea Tacchetti, Christopher Summerfield, Daniel Jarrett, Jan Balaguer, Michael Henry Tessler, Michiel A. Bakker, Miruna P\\^islar, Raphael K\\\"oster, Romuald Elie","submitted_at":"2025-02-13T14:35:40Z","abstract_excerpt":"Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, \"representation\" is the activity of making an individual's preferences present in the process via participation by a proxy agent -- i.e. their \"representative\". To this end, learned models of human behavior have the potential to fill this role, with practical implications for multi-agent scenario studies and mechanism design. In this work, we investigate the possibility of training \\textit{language agents} to behave"},"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":"2502.09369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T14:35:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"title_canon_sha256":"659de181002408292d1626b0adaf64063286a2127043d5b708847f20edfeae5b","abstract_canon_sha256":"b54ab5e015c96232c7a45e65b9cf3a9991a3db8209f477d2d75357110bd9be6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:56.556207Z","signature_b64":"CarduJjUqbr2EHN7vh30uvePtkAHY1KvDjHQ05D0SaBJosptu611vTXuMEd91D+pdq+5oaUYs5mqxXiVWoH6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446fdb510418365aadb83aff2fcec50810b4a98e46508933d2d0397a1ca7a6a9","last_reissued_at":"2026-07-05T10:13:56.555735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:56.555735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Agents as Digital Representatives in Collective Decision-Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.LG","authors_text":"Andrea Tacchetti, Christopher Summerfield, Daniel Jarrett, Jan Balaguer, Michael Henry Tessler, Michiel A. Bakker, Miruna P\\^islar, Raphael K\\\"oster, Romuald Elie","submitted_at":"2025-02-13T14:35:40Z","abstract_excerpt":"Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, \"representation\" is the activity of making an individual's preferences present in the process via participation by a proxy agent -- i.e. their \"representative\". To this end, learned models of human behavior have the potential to fill this role, with practical implications for multi-agent scenario studies and mechanism design. In this work, we investigate the possibility of training \\textit{language agents} to behave"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09369","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/2502.09369/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":"2502.09369","created_at":"2026-07-05T10:13:56.555791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09369v1","created_at":"2026-07-05T10:13:56.555791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09369","created_at":"2026-07-05T10:13:56.555791+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRX5WUIEDA3F","created_at":"2026-07-05T10:13:56.555791+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRX5WUIEDA3FVLNY","created_at":"2026-07-05T10:13:56.555791+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRX5WUIE","created_at":"2026-07-05T10:13:56.555791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.07339","citing_title":"Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06548","citing_title":"Continuous Latent Diffusion Language Model","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05368","citing_title":"AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA","json":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA.json","graph_json":"https://pith.science/api/pith-number/IRX5WUIEDA3FVLNYHL7S7TWFBA/graph.json","events_json":"https://pith.science/api/pith-number/IRX5WUIEDA3FVLNYHL7S7TWFBA/events.json","paper":"https://pith.science/paper/IRX5WUIE"},"agent_actions":{"view_html":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA","download_json":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA.json","view_paper":"https://pith.science/paper/IRX5WUIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09369&json=true","fetch_graph":"https://pith.science/api/pith-number/IRX5WUIEDA3FVLNYHL7S7TWFBA/graph.json","fetch_events":"https://pith.science/api/pith-number/IRX5WUIEDA3FVLNYHL7S7TWFBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA/action/storage_attestation","attest_author":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA/action/author_attestation","sign_citation":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA/action/citation_signature","submit_replication":"https://pith.science/pith/IRX5WUIEDA3FVLNYHL7S7TWFBA/action/replication_record"}},"created_at":"2026-07-05T10:13:56.555791+00:00","updated_at":"2026-07-05T10:13:56.555791+00:00"}