{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IIQOOCVVLZBITMJ57YE4PYPNHD","short_pith_number":"pith:IIQOOCVV","schema_version":"1.0","canonical_sha256":"4220e70ab55e4289b13dfe09c7e1ed38d83a564cf43e950d8915d855edf9a05b","source":{"kind":"arxiv","id":"2502.13270","version":1},"attestation_state":"computed","paper":{"title":"REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adyasha Maharana, Dong-Ho Lee, Francesco Barbieri, Jay Pujara, Xiang Ren","submitted_at":"2025-02-18T20:29:01Z","abstract_excerpt":"Long-term, open-domain dialogue capabilities are essential for chatbots aiming to recall past interactions and demonstrate emotional intelligence (EI). Yet, most existing research relies on synthetic, LLM-generated data, leaving open questions about real-world conversational patterns. To address this gap, we introduce REALTALK, a 21-day corpus of authentic messaging app dialogues, providing a direct benchmark against genuine human interactions.\n  We first conduct a dataset analysis, focusing on EI attributes and persona consistency to understand the unique challenges posed by real-world dialog"},"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":"2502.13270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T20:29:01Z","cross_cats_sorted":[],"title_canon_sha256":"0413d76464cedb6b22673f5096b5fb7b3ae909141182cb8369217a29402ab3b1","abstract_canon_sha256":"d7acf67aa61753d9763144fe209eb3876d41f11d0280396b802041b679b8feb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:44.816074Z","signature_b64":"GsVt0V5viLgXN9upX5+1OrZRS0ttvvfOgYFSuwlXI01K/ThU4Us7OUHCgCRPUD2gos4pHlhg+u3C3I5gEsJ+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4220e70ab55e4289b13dfe09c7e1ed38d83a564cf43e950d8915d855edf9a05b","last_reissued_at":"2026-07-05T10:16:44.815602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:44.815602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adyasha Maharana, Dong-Ho Lee, Francesco Barbieri, Jay Pujara, Xiang Ren","submitted_at":"2025-02-18T20:29:01Z","abstract_excerpt":"Long-term, open-domain dialogue capabilities are essential for chatbots aiming to recall past interactions and demonstrate emotional intelligence (EI). Yet, most existing research relies on synthetic, LLM-generated data, leaving open questions about real-world conversational patterns. To address this gap, we introduce REALTALK, a 21-day corpus of authentic messaging app dialogues, providing a direct benchmark against genuine human interactions.\n  We first conduct a dataset analysis, focusing on EI attributes and persona consistency to understand the unique challenges posed by real-world dialog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13270","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/2502.13270/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":"2502.13270","created_at":"2026-07-05T10:16:44.815657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13270v1","created_at":"2026-07-05T10:16:44.815657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13270","created_at":"2026-07-05T10:16:44.815657+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIQOOCVVLZBI","created_at":"2026-07-05T10:16:44.815657+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIQOOCVVLZBITMJ5","created_at":"2026-07-05T10:16:44.815657+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIQOOCVV","created_at":"2026-07-05T10:16:44.815657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21649","citing_title":"EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06302","citing_title":"Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04315","citing_title":"Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02798","citing_title":"BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01223","citing_title":"Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17396","citing_title":"EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20833","citing_title":"MemGym: a Long-Horizon Memory Environment for LLM Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15701","citing_title":"H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12572","citing_title":"LMEB: Long-horizon Memory Embedding Benchmark","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14705","citing_title":"Towards Continuous Sign Language Conversation from Isolated Signs","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11814","citing_title":"MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23321","citing_title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD","json":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD.json","graph_json":"https://pith.science/api/pith-number/IIQOOCVVLZBITMJ57YE4PYPNHD/graph.json","events_json":"https://pith.science/api/pith-number/IIQOOCVVLZBITMJ57YE4PYPNHD/events.json","paper":"https://pith.science/paper/IIQOOCVV"},"agent_actions":{"view_html":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD","download_json":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD.json","view_paper":"https://pith.science/paper/IIQOOCVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13270&json=true","fetch_graph":"https://pith.science/api/pith-number/IIQOOCVVLZBITMJ57YE4PYPNHD/graph.json","fetch_events":"https://pith.science/api/pith-number/IIQOOCVVLZBITMJ57YE4PYPNHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD/action/storage_attestation","attest_author":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD/action/author_attestation","sign_citation":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD/action/citation_signature","submit_replication":"https://pith.science/pith/IIQOOCVVLZBITMJ57YE4PYPNHD/action/replication_record"}},"created_at":"2026-07-05T10:16:44.815657+00:00","updated_at":"2026-07-05T10:16:44.815657+00:00"}