{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7P5JZYJLSLNCO5O6N2QSC6MIJJ","short_pith_number":"pith:7P5JZYJL","schema_version":"1.0","canonical_sha256":"fbfa9ce12b92da2775de6ea12179884a5520bf9a2a77ec41c03fa9e401e89419","source":{"kind":"arxiv","id":"2601.14230","version":2},"attestation_state":"computed","paper":{"title":"MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Alex Cabral, Josiah Hester, Yiqiao Jin, Yiyang Wang","submitted_at":"2026-01-20T18:44:04Z","abstract_excerpt":"Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from persona collapse, where agents revert to generic, homogenized assistant behaviors, and social sycophancy, where agents produce redundant, non-constructive dialogue. We propose MASCOT, a multi-agent framework for multi-perspective socio-collaborative companions. MASCOT introduces a novel bi-level optimization strategy to harmonize individual and collective behaviors: 1) Persona-Aware Behavioral Alignment, an RLAIF-driven pipelin"},"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":"2601.14230","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T18:44:04Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"36e6c3f17a7f9e6dd44400291b0ea6896bc8aa1fac405aabab111ad5fdb9cd4a","abstract_canon_sha256":"c5a7382a8c6a4fde06a10550d864eb33e8c54756ef00aeae098c520bcdbe347f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:15.401866Z","signature_b64":"Gvmatwe8u6L8STmLbB/MUYsRfu38uw5WnDI9LIOxjx3gt4py5DZ3mcrzGmdmf2Y69gHghzWpwN54hRIknmVYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbfa9ce12b92da2775de6ea12179884a5520bf9a2a77ec41c03fa9e401e89419","last_reissued_at":"2026-06-02T01:04:15.401406Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:15.401406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Alex Cabral, Josiah Hester, Yiqiao Jin, Yiyang Wang","submitted_at":"2026-01-20T18:44:04Z","abstract_excerpt":"Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from persona collapse, where agents revert to generic, homogenized assistant behaviors, and social sycophancy, where agents produce redundant, non-constructive dialogue. We propose MASCOT, a multi-agent framework for multi-perspective socio-collaborative companions. MASCOT introduces a novel bi-level optimization strategy to harmonize individual and collective behaviors: 1) Persona-Aware Behavioral Alignment, an RLAIF-driven pipelin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14230","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/2601.14230/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":"2601.14230","created_at":"2026-06-02T01:04:15.401470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.14230v2","created_at":"2026-06-02T01:04:15.401470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14230","created_at":"2026-06-02T01:04:15.401470+00:00"},{"alias_kind":"pith_short_12","alias_value":"7P5JZYJLSLNC","created_at":"2026-06-02T01:04:15.401470+00:00"},{"alias_kind":"pith_short_16","alias_value":"7P5JZYJLSLNCO5O6","created_at":"2026-06-02T01:04:15.401470+00:00"},{"alias_kind":"pith_short_8","alias_value":"7P5JZYJL","created_at":"2026-06-02T01:04:15.401470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.23193","citing_title":"CultivAgents: Cultivating Relationship-Centered Multi-Agent Systems for Personalized Gardening","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06597","citing_title":"UniSD: Towards a Unified Self-Distillation Framework for Large Language Models","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21318","citing_title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06597","citing_title":"UniSD: Towards a Unified Self-Distillation Framework for Large Language Models","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ","json":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ.json","graph_json":"https://pith.science/api/pith-number/7P5JZYJLSLNCO5O6N2QSC6MIJJ/graph.json","events_json":"https://pith.science/api/pith-number/7P5JZYJLSLNCO5O6N2QSC6MIJJ/events.json","paper":"https://pith.science/paper/7P5JZYJL"},"agent_actions":{"view_html":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ","download_json":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ.json","view_paper":"https://pith.science/paper/7P5JZYJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.14230&json=true","fetch_graph":"https://pith.science/api/pith-number/7P5JZYJLSLNCO5O6N2QSC6MIJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7P5JZYJLSLNCO5O6N2QSC6MIJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ/action/storage_attestation","attest_author":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ/action/author_attestation","sign_citation":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ/action/citation_signature","submit_replication":"https://pith.science/pith/7P5JZYJLSLNCO5O6N2QSC6MIJJ/action/replication_record"}},"created_at":"2026-06-02T01:04:15.401470+00:00","updated_at":"2026-06-02T01:04:15.401470+00:00"}