{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N45ONFMYFOOQDGXBHBQWYX6X67","short_pith_number":"pith:N45ONFMY","schema_version":"1.0","canonical_sha256":"6f3ae695982b9d019ae138616c5fd7f7c96b7bfb7803aeeafac5fab9baf6bc93","source":{"kind":"arxiv","id":"2607.01465","version":1},"attestation_state":"computed","paper":{"title":"Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Mukherji, Ananya Mantravadi, Harshit Rajgarhia, Karthikeya Aditya Vissa, Sankalp Mane","submitted_at":"2026-07-01T20:55:07Z","abstract_excerpt":"Large language models are trained to predict the next token, not to act inside a specific API. In niche enterprise SaaS workflows -- where success means hitting the right endpoint with the right nested arguments in the right order -- this objective mismatch shows up as silent failures: dropped required fields, hallucinated tools, or early stops after a single read. We ask whether Reinforcement Learning with Verifiable Rewards (RLVR), applied directly in the target environment, closes the gap. As a proof of concept we build a suite of five synthetic environments emulating the Jira REST v3 and C"},"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":"2607.01465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T20:55:07Z","cross_cats_sorted":[],"title_canon_sha256":"35b4bf6d8d0bad6c50b237870a8b04004ced812b8eea7b18444d3eedd1288b97","abstract_canon_sha256":"89af1e199dc35ff78418d297dac2afe4f455425926490275a08d2059996988f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:17:00.944695Z","signature_b64":"xQLSE+MfnAfHUB2uRKCtUYLNBNiYAANca1U02PKToK+6XZNFPg2+mi4vO2zI2iaD6R+B0X1WqR1/yiTW4hfNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f3ae695982b9d019ae138616c5fd7f7c96b7bfb7803aeeafac5fab9baf6bc93","last_reissued_at":"2026-07-03T00:17:00.944285Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:17:00.944285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Mukherji, Ananya Mantravadi, Harshit Rajgarhia, Karthikeya Aditya Vissa, Sankalp Mane","submitted_at":"2026-07-01T20:55:07Z","abstract_excerpt":"Large language models are trained to predict the next token, not to act inside a specific API. In niche enterprise SaaS workflows -- where success means hitting the right endpoint with the right nested arguments in the right order -- this objective mismatch shows up as silent failures: dropped required fields, hallucinated tools, or early stops after a single read. We ask whether Reinforcement Learning with Verifiable Rewards (RLVR), applied directly in the target environment, closes the gap. As a proof of concept we build a suite of five synthetic environments emulating the Jira REST v3 and C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01465","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/2607.01465/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":"2607.01465","created_at":"2026-07-03T00:17:00.944350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01465v1","created_at":"2026-07-03T00:17:00.944350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01465","created_at":"2026-07-03T00:17:00.944350+00:00"},{"alias_kind":"pith_short_12","alias_value":"N45ONFMYFOOQ","created_at":"2026-07-03T00:17:00.944350+00:00"},{"alias_kind":"pith_short_16","alias_value":"N45ONFMYFOOQDGXB","created_at":"2026-07-03T00:17:00.944350+00:00"},{"alias_kind":"pith_short_8","alias_value":"N45ONFMY","created_at":"2026-07-03T00:17:00.944350+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/N45ONFMYFOOQDGXBHBQWYX6X67","json":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67.json","graph_json":"https://pith.science/api/pith-number/N45ONFMYFOOQDGXBHBQWYX6X67/graph.json","events_json":"https://pith.science/api/pith-number/N45ONFMYFOOQDGXBHBQWYX6X67/events.json","paper":"https://pith.science/paper/N45ONFMY"},"agent_actions":{"view_html":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67","download_json":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67.json","view_paper":"https://pith.science/paper/N45ONFMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01465&json=true","fetch_graph":"https://pith.science/api/pith-number/N45ONFMYFOOQDGXBHBQWYX6X67/graph.json","fetch_events":"https://pith.science/api/pith-number/N45ONFMYFOOQDGXBHBQWYX6X67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67/action/storage_attestation","attest_author":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67/action/author_attestation","sign_citation":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67/action/citation_signature","submit_replication":"https://pith.science/pith/N45ONFMYFOOQDGXBHBQWYX6X67/action/replication_record"}},"created_at":"2026-07-03T00:17:00.944350+00:00","updated_at":"2026-07-03T00:17:00.944350+00:00"}