{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G7K4MLSCHOKQFXOQPHWIIH5ARF","short_pith_number":"pith:G7K4MLSC","schema_version":"1.0","canonical_sha256":"37d5c62e423b9502ddd079ec841fa0895a0b14278235651c74e2c819478a17e0","source":{"kind":"arxiv","id":"2506.22056","version":1},"attestation_state":"computed","paper":{"title":"Universal Retrieval for Multimodal Trajectory Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dehan Kong, Rui Meng, Xuan Zhang, Yanyi Shang, Yifei Leng, Zhenbang Xiao, Ziyan Jiang, Zora Zhiruo Wang","submitted_at":"2025-06-27T09:50:38Z","abstract_excerpt":"Trajectory data, capturing human actions and environmental states across various modalities, holds significant potential for enhancing AI agent capabilities, particularly in GUI environments. However, how to model the representation of trajectory-level data presents a significant challenge that has not been systematically addressed amid explosive trajectory data growth. In this work, we introduce Multimodal Trajectory Retrieval, bridging the gap between universal retrieval and agent-centric trajectory modeling. We construct the Unified Agent Trajectory Dataset (UATD) from annotated demonstrati"},"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":"2506.22056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-27T09:50:38Z","cross_cats_sorted":[],"title_canon_sha256":"6ab7024d9eebd8729513c5cec5b275975480ff8a0bdf2ba01963b56768bb8ec1","abstract_canon_sha256":"050a552d4aef425b75f62d05af542777ffc17413cf8e25b6563b3754a2762743"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:21.262352Z","signature_b64":"JUdVnUiiqwZprVdzWNHNat+3OeBJTy2I+o0spPvtGjkL3wsUvcC8taJfInCoMlPsrycDN9kHUdD8sLjRa5cdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37d5c62e423b9502ddd079ec841fa0895a0b14278235651c74e2c819478a17e0","last_reissued_at":"2026-07-05T11:28:21.261906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:21.261906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Retrieval for Multimodal Trajectory Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dehan Kong, Rui Meng, Xuan Zhang, Yanyi Shang, Yifei Leng, Zhenbang Xiao, Ziyan Jiang, Zora Zhiruo Wang","submitted_at":"2025-06-27T09:50:38Z","abstract_excerpt":"Trajectory data, capturing human actions and environmental states across various modalities, holds significant potential for enhancing AI agent capabilities, particularly in GUI environments. However, how to model the representation of trajectory-level data presents a significant challenge that has not been systematically addressed amid explosive trajectory data growth. In this work, we introduce Multimodal Trajectory Retrieval, bridging the gap between universal retrieval and agent-centric trajectory modeling. We construct the Unified Agent Trajectory Dataset (UATD) from annotated demonstrati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22056","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/2506.22056/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":"2506.22056","created_at":"2026-07-05T11:28:21.261968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22056v1","created_at":"2026-07-05T11:28:21.261968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22056","created_at":"2026-07-05T11:28:21.261968+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7K4MLSCHOKQ","created_at":"2026-07-05T11:28:21.261968+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7K4MLSCHOKQFXOQ","created_at":"2026-07-05T11:28:21.261968+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7K4MLSC","created_at":"2026-07-05T11:28:21.261968+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/G7K4MLSCHOKQFXOQPHWIIH5ARF","json":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF.json","graph_json":"https://pith.science/api/pith-number/G7K4MLSCHOKQFXOQPHWIIH5ARF/graph.json","events_json":"https://pith.science/api/pith-number/G7K4MLSCHOKQFXOQPHWIIH5ARF/events.json","paper":"https://pith.science/paper/G7K4MLSC"},"agent_actions":{"view_html":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF","download_json":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF.json","view_paper":"https://pith.science/paper/G7K4MLSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22056&json=true","fetch_graph":"https://pith.science/api/pith-number/G7K4MLSCHOKQFXOQPHWIIH5ARF/graph.json","fetch_events":"https://pith.science/api/pith-number/G7K4MLSCHOKQFXOQPHWIIH5ARF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF/action/storage_attestation","attest_author":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF/action/author_attestation","sign_citation":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF/action/citation_signature","submit_replication":"https://pith.science/pith/G7K4MLSCHOKQFXOQPHWIIH5ARF/action/replication_record"}},"created_at":"2026-07-05T11:28:21.261968+00:00","updated_at":"2026-07-05T11:28:21.261968+00:00"}