{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IWKN5E3CJIHBTPGT5I3YUX3NTE","short_pith_number":"pith:IWKN5E3C","schema_version":"1.0","canonical_sha256":"4594de93624a0e19bcd3ea378a5f6d99028688c12e7c4181a4bbe0b903dcf493","source":{"kind":"arxiv","id":"2505.10922","version":1},"attestation_state":"computed","paper":{"title":"Vaiage: A Multi-Agent Solution to Personalized Travel Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Binwen Liu, Jiamin Wang, Jiexi Ge","submitted_at":"2025-05-16T06:54:52Z","abstract_excerpt":"Planning trips is a cognitively intensive task involving conflicting user preferences, dynamic external information, and multi-step temporal-spatial optimization. Traditional platforms often fall short - they provide static results, lack contextual adaptation, and fail to support real-time interaction or intent refinement.\n  Our approach, Vaiage, addresses these challenges through a graph-structured multi-agent framework built around large language models (LLMs) that serve as both goal-conditioned recommenders and sequential planners. LLMs infer user intent, suggest personalized destinations a"},"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":"2505.10922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-05-16T06:54:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc3f67eda846c57ab81a4c2c436bd4e1983b549d2c0a01b75bb7fe4a0a67955c","abstract_canon_sha256":"b7349d4802cf508b1700f6ef44b3268e3edfdce45b7c4f9ace78a477ef13cb4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:08.047921Z","signature_b64":"u9/9YJD1ovTtUiy8j+qqEZtXYv5h6nWcdNHYPYLq4IpekQrQwd9OvNcgrQVcxvQm4f/Du5gD5V40iAKktcv/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4594de93624a0e19bcd3ea378a5f6d99028688c12e7c4181a4bbe0b903dcf493","last_reissued_at":"2026-07-05T11:04:08.047514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:08.047514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vaiage: A Multi-Agent Solution to Personalized Travel Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Binwen Liu, Jiamin Wang, Jiexi Ge","submitted_at":"2025-05-16T06:54:52Z","abstract_excerpt":"Planning trips is a cognitively intensive task involving conflicting user preferences, dynamic external information, and multi-step temporal-spatial optimization. Traditional platforms often fall short - they provide static results, lack contextual adaptation, and fail to support real-time interaction or intent refinement.\n  Our approach, Vaiage, addresses these challenges through a graph-structured multi-agent framework built around large language models (LLMs) that serve as both goal-conditioned recommenders and sequential planners. LLMs infer user intent, suggest personalized destinations a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10922","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/2505.10922/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":"2505.10922","created_at":"2026-07-05T11:04:08.047576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10922v1","created_at":"2026-07-05T11:04:08.047576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10922","created_at":"2026-07-05T11:04:08.047576+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWKN5E3CJIHB","created_at":"2026-07-05T11:04:08.047576+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWKN5E3CJIHBTPGT","created_at":"2026-07-05T11:04:08.047576+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWKN5E3C","created_at":"2026-07-05T11:04:08.047576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18633","citing_title":"PersonalPlan: Planning Multi-Agent Systems for Personalized Programming Learning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE","json":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE.json","graph_json":"https://pith.science/api/pith-number/IWKN5E3CJIHBTPGT5I3YUX3NTE/graph.json","events_json":"https://pith.science/api/pith-number/IWKN5E3CJIHBTPGT5I3YUX3NTE/events.json","paper":"https://pith.science/paper/IWKN5E3C"},"agent_actions":{"view_html":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE","download_json":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE.json","view_paper":"https://pith.science/paper/IWKN5E3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10922&json=true","fetch_graph":"https://pith.science/api/pith-number/IWKN5E3CJIHBTPGT5I3YUX3NTE/graph.json","fetch_events":"https://pith.science/api/pith-number/IWKN5E3CJIHBTPGT5I3YUX3NTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE/action/storage_attestation","attest_author":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE/action/author_attestation","sign_citation":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE/action/citation_signature","submit_replication":"https://pith.science/pith/IWKN5E3CJIHBTPGT5I3YUX3NTE/action/replication_record"}},"created_at":"2026-07-05T11:04:08.047576+00:00","updated_at":"2026-07-05T11:04:08.047576+00:00"}