{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RQSSUUHVPSHUYPO5USVR4QQ6HB","short_pith_number":"pith:RQSSUUHV","schema_version":"1.0","canonical_sha256":"8c252a50f57c8f4c3ddda4ab1e421e387c86896577c2b17484031ce4a9c54641","source":{"kind":"arxiv","id":"2607.21625","version":1},"attestation_state":"computed","paper":{"title":"Trajectory-Aware Retrieval Agents for Temporal Decision- Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Shen, Jing Wang, Xing Niu","submitted_at":"2026-07-07T16:28:38Z","abstract_excerpt":"We study the problem of decision-making from long-form, temporally structured text using large language model (LLM) agents. Standard retrievalaugmented generation (RAG) pipelines fragment chronological context into isolated snippets, discarding the temporal structure that is often critical for correct downstream decisions. We introduce TLM (Trajectory Language Model), a closed-loop agentic framework that iteratively refines the evidence set using SHAP-guided feedback. The key technical contribution is the latent growth curve model (LGCM) over retrieved chunk embeddings, which provides an inter"},"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":"2607.21625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T16:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"acb602b3959604a9302164125162b144b2de084e0a45061f6380e904ee50faf6","abstract_canon_sha256":"e95e9b9e5c0c0c3bf9e9b0daf4c336272bdf2c6278f5db2052ad696d097e98a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:11.756824Z","signature_b64":"kZbPjzYLDRR4v1otILKn4VhM5/HB58Jht2wQHD1W2Qtuw1kx72AuWLkEWpJwRm5qNH0LRin9tjr1LEla9q7NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c252a50f57c8f4c3ddda4ab1e421e387c86896577c2b17484031ce4a9c54641","last_reissued_at":"2026-07-27T00:20:11.755902Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:11.755902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajectory-Aware Retrieval Agents for Temporal Decision- Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Shen, Jing Wang, Xing Niu","submitted_at":"2026-07-07T16:28:38Z","abstract_excerpt":"We study the problem of decision-making from long-form, temporally structured text using large language model (LLM) agents. Standard retrievalaugmented generation (RAG) pipelines fragment chronological context into isolated snippets, discarding the temporal structure that is often critical for correct downstream decisions. We introduce TLM (Trajectory Language Model), a closed-loop agentic framework that iteratively refines the evidence set using SHAP-guided feedback. The key technical contribution is the latent growth curve model (LGCM) over retrieved chunk embeddings, which provides an inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21625","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/2607.21625/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":"2607.21625","created_at":"2026-07-27T00:20:11.756390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21625v1","created_at":"2026-07-27T00:20:11.756390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21625","created_at":"2026-07-27T00:20:11.756390+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQSSUUHVPSHU","created_at":"2026-07-27T00:20:11.756390+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQSSUUHVPSHUYPO5","created_at":"2026-07-27T00:20:11.756390+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQSSUUHV","created_at":"2026-07-27T00:20:11.756390+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/RQSSUUHVPSHUYPO5USVR4QQ6HB","json":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB.json","graph_json":"https://pith.science/api/pith-number/RQSSUUHVPSHUYPO5USVR4QQ6HB/graph.json","events_json":"https://pith.science/api/pith-number/RQSSUUHVPSHUYPO5USVR4QQ6HB/events.json","paper":"https://pith.science/paper/RQSSUUHV"},"agent_actions":{"view_html":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB","download_json":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB.json","view_paper":"https://pith.science/paper/RQSSUUHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21625&json=true","fetch_graph":"https://pith.science/api/pith-number/RQSSUUHVPSHUYPO5USVR4QQ6HB/graph.json","fetch_events":"https://pith.science/api/pith-number/RQSSUUHVPSHUYPO5USVR4QQ6HB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB/action/storage_attestation","attest_author":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB/action/author_attestation","sign_citation":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB/action/citation_signature","submit_replication":"https://pith.science/pith/RQSSUUHVPSHUYPO5USVR4QQ6HB/action/replication_record"}},"created_at":"2026-07-27T00:20:11.756390+00:00","updated_at":"2026-07-27T00:20:11.756390+00:00"}