{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AIEYFHHKLPNHCFD665SK4ZISGH","short_pith_number":"pith:AIEYFHHK","schema_version":"1.0","canonical_sha256":"0209829cea5bda71147ef764ae651231d31c0534161a4618e169f6fef6043b25","source":{"kind":"arxiv","id":"2506.21536","version":1},"attestation_state":"computed","paper":{"title":"PsyLite Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Chengye Xie, Fangjun Ding, Renyu Zhang, Xinyu Feng, Yanting Zhang, Zheng Zhang","submitted_at":"2025-06-26T17:54:42Z","abstract_excerpt":"With the rapid development of digital technology, AI-driven psychological counseling has gradually become an important research direction in the field of mental health. However, existing models still have deficiencies in dialogue safety, detailed scenario handling, and lightweight deployment. To address these issues, this study proposes PsyLite, a lightweight psychological counseling large language model agent developed based on the base model InternLM2.5-7B-chat. Through a two-stage training strategy (hybrid distillation data fine-tuning and ORPO preference optimization), PsyLite enhances the"},"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":"2506.21536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-26T17:54:42Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"dece62df33a79473aaf1e7cda62f1561d20e47fa621fe69c70e7816ed6fe5c6b","abstract_canon_sha256":"18f5cba3d0c5b868be6f7b57c9b8a1da756799371ba6930aca050eecf9615d46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:08.213344Z","signature_b64":"9uxIVNevq4nMXejzV88WcLLWC9p9dac+2Y+6ETWkNWgucS428jltixL6+AtMYFQvOtAyJ/VZK9IdseNaoVCjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0209829cea5bda71147ef764ae651231d31c0534161a4618e169f6fef6043b25","last_reissued_at":"2026-07-05T11:38:08.212703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:08.212703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PsyLite Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Chengye Xie, Fangjun Ding, Renyu Zhang, Xinyu Feng, Yanting Zhang, Zheng Zhang","submitted_at":"2025-06-26T17:54:42Z","abstract_excerpt":"With the rapid development of digital technology, AI-driven psychological counseling has gradually become an important research direction in the field of mental health. However, existing models still have deficiencies in dialogue safety, detailed scenario handling, and lightweight deployment. To address these issues, this study proposes PsyLite, a lightweight psychological counseling large language model agent developed based on the base model InternLM2.5-7B-chat. Through a two-stage training strategy (hybrid distillation data fine-tuning and ORPO preference optimization), PsyLite enhances the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21536","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/2506.21536/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":"2506.21536","created_at":"2026-07-05T11:38:08.212853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21536v1","created_at":"2026-07-05T11:38:08.212853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21536","created_at":"2026-07-05T11:38:08.212853+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIEYFHHKLPNH","created_at":"2026-07-05T11:38:08.212853+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIEYFHHKLPNHCFD6","created_at":"2026-07-05T11:38:08.212853+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIEYFHHK","created_at":"2026-07-05T11:38:08.212853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH","json":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH.json","graph_json":"https://pith.science/api/pith-number/AIEYFHHKLPNHCFD665SK4ZISGH/graph.json","events_json":"https://pith.science/api/pith-number/AIEYFHHKLPNHCFD665SK4ZISGH/events.json","paper":"https://pith.science/paper/AIEYFHHK"},"agent_actions":{"view_html":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH","download_json":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH.json","view_paper":"https://pith.science/paper/AIEYFHHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21536&json=true","fetch_graph":"https://pith.science/api/pith-number/AIEYFHHKLPNHCFD665SK4ZISGH/graph.json","fetch_events":"https://pith.science/api/pith-number/AIEYFHHKLPNHCFD665SK4ZISGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH/action/storage_attestation","attest_author":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH/action/author_attestation","sign_citation":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH/action/citation_signature","submit_replication":"https://pith.science/pith/AIEYFHHKLPNHCFD665SK4ZISGH/action/replication_record"}},"created_at":"2026-07-05T11:38:08.212853+00:00","updated_at":"2026-07-05T11:38:08.212853+00:00"}