{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2EOSHQLH2FVRMIE5C6SGCNTCCA","short_pith_number":"pith:2EOSHQLH","schema_version":"1.0","canonical_sha256":"d11d23c167d16b16209d17a461366210109fbec52691ec88eac85c3f37726400","source":{"kind":"arxiv","id":"2412.15701","version":6},"attestation_state":"computed","paper":{"title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Diyi Yang, John Yang, Vinay Samuel, Yijia Shao, Yucheng Jiang","submitted_at":"2024-12-20T09:21:15Z","abstract_excerpt":"While the advancement of large language models has spurred the development of AI agents to automate tasks, numerous use cases inherently require agents to collaborate with humans due to humans' latent preferences, domain expertise, or the need for control. To facilitate the study of human-agent collaboration, we introduce Collaborative Gym (Co-Gym), an open framework for developing and evaluating collaborative agents that engage in bidirectional communication with humans while interacting with task environments. We describe how the framework enables the implementation of new task environments "},"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":"2412.15701","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T09:21:15Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"7ce71d4c7954d183c0847a49d8a4972be398a2d6a4b897c9e3b949426b3e7ad0","abstract_canon_sha256":"0b52dd442028ded794dc2ff68482878988ebedce7b096fd1b14fd813cfd31e2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:16:02.109858Z","signature_b64":"uGCZomM2HsdnXawQ2SiuMrdHh2KKfABOhk+JjWeD/DEy/kjDp+cYyzEPUSblFMFvp6v6/th8HY0AFpqWI0y4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d11d23c167d16b16209d17a461366210109fbec52691ec88eac85c3f37726400","last_reissued_at":"2026-08-11T01:16:02.106803Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:16:02.106803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Diyi Yang, John Yang, Vinay Samuel, Yijia Shao, Yucheng Jiang","submitted_at":"2024-12-20T09:21:15Z","abstract_excerpt":"While the advancement of large language models has spurred the development of AI agents to automate tasks, numerous use cases inherently require agents to collaborate with humans due to humans' latent preferences, domain expertise, or the need for control. To facilitate the study of human-agent collaboration, we introduce Collaborative Gym (Co-Gym), an open framework for developing and evaluating collaborative agents that engage in bidirectional communication with humans while interacting with task environments. We describe how the framework enables the implementation of new task environments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15701","kind":"arxiv","version":6},"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/2412.15701/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":"2412.15701","created_at":"2026-08-11T01:16:02.107726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15701v6","created_at":"2026-08-11T01:16:02.107726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15701","created_at":"2026-08-11T01:16:02.107726+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EOSHQLH2FVR","created_at":"2026-08-11T01:16:02.107726+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EOSHQLH2FVRMIE5","created_at":"2026-08-11T01:16:02.107726+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EOSHQLH","created_at":"2026-08-11T01:16:02.107726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"2606.04273","citing_title":"Human agency in initial human-AI proof formalization workflows","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21296","citing_title":"Discriminatory Compliance: How LLMs Answer Queries from Protected Groups","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2510.05307","citing_title":"When Should Users Check? Modeling Confirmation Frequency inMulti-Step Agentic AI Tasks","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08178","citing_title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25905","citing_title":"A paradox of AI fluency","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23283","citing_title":"Revisable by Design: A Theory of Streaming LLM Agent Execution","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21827","citing_title":"Alignment has a Fantasia Problem","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08178","citing_title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15607","citing_title":"Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21354","citing_title":"Decoupled Travel Planning with Behavior Forest","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA","json":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA.json","graph_json":"https://pith.science/api/pith-number/2EOSHQLH2FVRMIE5C6SGCNTCCA/graph.json","events_json":"https://pith.science/api/pith-number/2EOSHQLH2FVRMIE5C6SGCNTCCA/events.json","paper":"https://pith.science/paper/2EOSHQLH"},"agent_actions":{"view_html":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA","download_json":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA.json","view_paper":"https://pith.science/paper/2EOSHQLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15701&json=true","fetch_graph":"https://pith.science/api/pith-number/2EOSHQLH2FVRMIE5C6SGCNTCCA/graph.json","fetch_events":"https://pith.science/api/pith-number/2EOSHQLH2FVRMIE5C6SGCNTCCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA/action/storage_attestation","attest_author":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA/action/author_attestation","sign_citation":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA/action/citation_signature","submit_replication":"https://pith.science/pith/2EOSHQLH2FVRMIE5C6SGCNTCCA/action/replication_record"}},"created_at":"2026-08-11T01:16:02.107726+00:00","updated_at":"2026-08-11T01:16:02.107726+00:00"}