{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EV5CM2VVXHNQ5KACWHT4UN5FLM","short_pith_number":"pith:EV5CM2VV","schema_version":"1.0","canonical_sha256":"257a266ab5b9db0ea802b1e7ca37a55b075638f568f0e054b1f43b9c0c71c609","source":{"kind":"arxiv","id":"2411.18915","version":5},"attestation_state":"computed","paper":{"title":"MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Gregory Senay, Luis Mart\\'i, Vishnou Vinayagame","submitted_at":"2024-11-28T05:12:17Z","abstract_excerpt":"Business documents often contain substantial tabular and textual information with numerical values, requiring mathematical reasoning for effective document understanding. While Small Language Models (SLMs) still struggle at this task, tool-augmented multi-step agents perform better, at the cost of relying on closed-source or larger models, external data, or extensive prompt-engineering. This work introduces MATATA, a novel weakly supervised end-to-end approach to train multi-step reasoning language agents for document tabular applications. MATATA presents an annotation-free paradigm for each 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":"2411.18915","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-28T05:12:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8af8842b2a4e8a119a1e684c5adfca1bc53c84b07d6f153aa62da5b265cc54e1","abstract_canon_sha256":"87c48d28a3ec44ea5bd1f53ee56d74bcbeefe8c3329fd709c56c48c7361976bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:51.224810Z","signature_b64":"TPgKWc92t+X1IbRUaYxYe18Ep8ioZnzcC3XETq/SiwYrpHoi6TXm/wxbPOdPGOenxnONTwBopvli49uK1a0/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"257a266ab5b9db0ea802b1e7ca37a55b075638f568f0e054b1f43b9c0c71c609","last_reissued_at":"2026-07-05T11:56:51.224234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:51.224234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Gregory Senay, Luis Mart\\'i, Vishnou Vinayagame","submitted_at":"2024-11-28T05:12:17Z","abstract_excerpt":"Business documents often contain substantial tabular and textual information with numerical values, requiring mathematical reasoning for effective document understanding. While Small Language Models (SLMs) still struggle at this task, tool-augmented multi-step agents perform better, at the cost of relying on closed-source or larger models, external data, or extensive prompt-engineering. This work introduces MATATA, a novel weakly supervised end-to-end approach to train multi-step reasoning language agents for document tabular applications. MATATA presents an annotation-free paradigm for each a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18915","kind":"arxiv","version":5},"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/2411.18915/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":"2411.18915","created_at":"2026-07-05T11:56:51.224302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18915v5","created_at":"2026-07-05T11:56:51.224302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18915","created_at":"2026-07-05T11:56:51.224302+00:00"},{"alias_kind":"pith_short_12","alias_value":"EV5CM2VVXHNQ","created_at":"2026-07-05T11:56:51.224302+00:00"},{"alias_kind":"pith_short_16","alias_value":"EV5CM2VVXHNQ5KAC","created_at":"2026-07-05T11:56:51.224302+00:00"},{"alias_kind":"pith_short_8","alias_value":"EV5CM2VV","created_at":"2026-07-05T11:56:51.224302+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/EV5CM2VVXHNQ5KACWHT4UN5FLM","json":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM.json","graph_json":"https://pith.science/api/pith-number/EV5CM2VVXHNQ5KACWHT4UN5FLM/graph.json","events_json":"https://pith.science/api/pith-number/EV5CM2VVXHNQ5KACWHT4UN5FLM/events.json","paper":"https://pith.science/paper/EV5CM2VV"},"agent_actions":{"view_html":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM","download_json":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM.json","view_paper":"https://pith.science/paper/EV5CM2VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18915&json=true","fetch_graph":"https://pith.science/api/pith-number/EV5CM2VVXHNQ5KACWHT4UN5FLM/graph.json","fetch_events":"https://pith.science/api/pith-number/EV5CM2VVXHNQ5KACWHT4UN5FLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM/action/storage_attestation","attest_author":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM/action/author_attestation","sign_citation":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM/action/citation_signature","submit_replication":"https://pith.science/pith/EV5CM2VVXHNQ5KACWHT4UN5FLM/action/replication_record"}},"created_at":"2026-07-05T11:56:51.224302+00:00","updated_at":"2026-07-05T11:56:51.224302+00:00"}