{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZX7ZCWZX4JUQDIU37BXB57GYKZ","short_pith_number":"pith:ZX7ZCWZX","schema_version":"1.0","canonical_sha256":"cdff915b37e26901a29bf86e1efcd85663ca252dc803ab53adb04a835232dbd9","source":{"kind":"arxiv","id":"2607.14682","version":1},"attestation_state":"computed","paper":{"title":"Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ganesh Parab, Goutham Vignesh, Harikrishnan P M, Rohit Agrawal, Saisubramaniam Gopalakrishnan, Varun V, Vishal Vaddina","submitted_at":"2026-07-16T07:43:39Z","abstract_excerpt":"Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge. Current approaches bifurcate into Supervised Fine-Tuning (SFT), which requires large annotated datasets and reaches optimization plateaus, and reasoning-centric Reinforcement Learning (RL), which depends on verbose intermediate traces that inflate inference token cost without clear benefit. We introduce Perception-RFT, a training framework that applies Group Relative Policy Optimization (GRPO) to multimodal document QA, bypas"},"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":"2607.14682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T07:43:39Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a47371019842cf3b9cb44358be1590843ee1b2bc15ba89e5ec7b0d5746399702","abstract_canon_sha256":"a9d15007bef5c10e269b09104c1ea800279e1dfad700894a984c73e7f34f6173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:24.843890Z","signature_b64":"8PXNuAckjVbjXCeKAQBwUIkCr+YyTCzGcLC9ZdTjHO6FnkK7vgdh3mz30mdH0OF2+e0YwBVlAq+IX/WJvgELCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdff915b37e26901a29bf86e1efcd85663ca252dc803ab53adb04a835232dbd9","last_reissued_at":"2026-07-17T01:21:24.843015Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:24.843015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ganesh Parab, Goutham Vignesh, Harikrishnan P M, Rohit Agrawal, Saisubramaniam Gopalakrishnan, Varun V, Vishal Vaddina","submitted_at":"2026-07-16T07:43:39Z","abstract_excerpt":"Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge. Current approaches bifurcate into Supervised Fine-Tuning (SFT), which requires large annotated datasets and reaches optimization plateaus, and reasoning-centric Reinforcement Learning (RL), which depends on verbose intermediate traces that inflate inference token cost without clear benefit. We introduce Perception-RFT, a training framework that applies Group Relative Policy Optimization (GRPO) to multimodal document QA, bypas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14682","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/2607.14682/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":"2607.14682","created_at":"2026-07-17T01:21:24.843466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14682v1","created_at":"2026-07-17T01:21:24.843466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14682","created_at":"2026-07-17T01:21:24.843466+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZX7ZCWZX4JUQ","created_at":"2026-07-17T01:21:24.843466+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZX7ZCWZX4JUQDIU3","created_at":"2026-07-17T01:21:24.843466+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZX7ZCWZX","created_at":"2026-07-17T01:21:24.843466+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/ZX7ZCWZX4JUQDIU37BXB57GYKZ","json":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ.json","graph_json":"https://pith.science/api/pith-number/ZX7ZCWZX4JUQDIU37BXB57GYKZ/graph.json","events_json":"https://pith.science/api/pith-number/ZX7ZCWZX4JUQDIU37BXB57GYKZ/events.json","paper":"https://pith.science/paper/ZX7ZCWZX"},"agent_actions":{"view_html":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ","download_json":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ.json","view_paper":"https://pith.science/paper/ZX7ZCWZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14682&json=true","fetch_graph":"https://pith.science/api/pith-number/ZX7ZCWZX4JUQDIU37BXB57GYKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZX7ZCWZX4JUQDIU37BXB57GYKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZX7ZCWZX4JUQDIU37BXB57GYKZ/action/replication_record"}},"created_at":"2026-07-17T01:21:24.843466+00:00","updated_at":"2026-07-17T01:21:24.843466+00:00"}