{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MK3E665NBPMDXOGFVNGM46MU4J","short_pith_number":"pith:MK3E665N","schema_version":"1.0","canonical_sha256":"62b64f7bad0bd83bb8c5ab4cce7994e27688146c277aef68a099eb895d3f7fe7","source":{"kind":"arxiv","id":"2412.13471","version":1},"attestation_state":"computed","paper":{"title":"Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jianwen Sun, Jintian Feng, Mengqi Wei, Qian Wan, Rui Zou, Sannyuya Liu","submitted_at":"2024-12-18T03:36:08Z","abstract_excerpt":"In recent years, large language models have shown exceptional performance in fulfilling diverse human needs. However, their training data can introduce harmful content, underscoring the necessity for robust value alignment. Mainstream methods, which depend on feedback learning and supervised training, are resource-intensive and may constrain the full potential of the models. Multi-Agent Debate (MAD) offers a more efficient and innovative solution by enabling the generation of reliable answers through agent interactions. To apply MAD to value alignment, we examine the relationship between the h"},"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":"2412.13471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-18T03:36:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"577f5671d374eb90a91a0028cb325c4a7e4c0c59a8a1e537ae1b364e02ba7667","abstract_canon_sha256":"a6b3ecb65efa123f9ef27c61852b953d84ad55193afaeb60182a8981d95b91e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:02.287830Z","signature_b64":"Ym2WanRz4/LkceuJ2IFSHrWE53wX9LyBBsvAHtf7ciz22xN5WPaTMxZwWqaxA3/1PxDp7vf3lhIIwth2Nf2iBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62b64f7bad0bd83bb8c5ab4cce7994e27688146c277aef68a099eb895d3f7fe7","last_reissued_at":"2026-07-05T09:51:02.287350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:02.287350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jianwen Sun, Jintian Feng, Mengqi Wei, Qian Wan, Rui Zou, Sannyuya Liu","submitted_at":"2024-12-18T03:36:08Z","abstract_excerpt":"In recent years, large language models have shown exceptional performance in fulfilling diverse human needs. However, their training data can introduce harmful content, underscoring the necessity for robust value alignment. Mainstream methods, which depend on feedback learning and supervised training, are resource-intensive and may constrain the full potential of the models. Multi-Agent Debate (MAD) offers a more efficient and innovative solution by enabling the generation of reliable answers through agent interactions. To apply MAD to value alignment, we examine the relationship between the h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13471","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/2412.13471/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":"2412.13471","created_at":"2026-07-05T09:51:02.287403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13471v1","created_at":"2026-07-05T09:51:02.287403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13471","created_at":"2026-07-05T09:51:02.287403+00:00"},{"alias_kind":"pith_short_12","alias_value":"MK3E665NBPMD","created_at":"2026-07-05T09:51:02.287403+00:00"},{"alias_kind":"pith_short_16","alias_value":"MK3E665NBPMDXOGF","created_at":"2026-07-05T09:51:02.287403+00:00"},{"alias_kind":"pith_short_8","alias_value":"MK3E665N","created_at":"2026-07-05T09:51:02.287403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09656","citing_title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","ref_index":179,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J","json":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J.json","graph_json":"https://pith.science/api/pith-number/MK3E665NBPMDXOGFVNGM46MU4J/graph.json","events_json":"https://pith.science/api/pith-number/MK3E665NBPMDXOGFVNGM46MU4J/events.json","paper":"https://pith.science/paper/MK3E665N"},"agent_actions":{"view_html":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J","download_json":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J.json","view_paper":"https://pith.science/paper/MK3E665N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13471&json=true","fetch_graph":"https://pith.science/api/pith-number/MK3E665NBPMDXOGFVNGM46MU4J/graph.json","fetch_events":"https://pith.science/api/pith-number/MK3E665NBPMDXOGFVNGM46MU4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J/action/storage_attestation","attest_author":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J/action/author_attestation","sign_citation":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J/action/citation_signature","submit_replication":"https://pith.science/pith/MK3E665NBPMDXOGFVNGM46MU4J/action/replication_record"}},"created_at":"2026-07-05T09:51:02.287403+00:00","updated_at":"2026-07-05T09:51:02.287403+00:00"}