{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZX7ZCWZX4JUQDIU37BXB57GYKZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a9d15007bef5c10e269b09104c1ea800279e1dfad700894a984c73e7f34f6173","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T07:43:39Z","title_canon_sha256":"a47371019842cf3b9cb44358be1590843ee1b2bc15ba89e5ec7b0d5746399702"},"schema_version":"1.0","source":{"id":"2607.14682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14682","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14682v1","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14682","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZX7ZCWZX4JUQ","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZX7ZCWZX4JUQDIU3","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZX7ZCWZX","created_at":"2026-07-17T01:21:24Z"}],"graph_snapshots":[{"event_id":"sha256:85e5a786add339221eb478868075847beae93c6ea6e7893600c6fba54a02c731","target":"graph","created_at":"2026-07-17T01:21:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.14682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ganesh Parab, Goutham Vignesh, Harikrishnan P M, Rohit Agrawal, Saisubramaniam Gopalakrishnan, Varun V, Vishal Vaddina","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T07:43:39Z","title":"Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14682","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7be30afdb18c18cefc74ce10448a1c7fe33c3c8e70661eb108934e85509aa4f2","target":"record","created_at":"2026-07-17T01:21:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a9d15007bef5c10e269b09104c1ea800279e1dfad700894a984c73e7f34f6173","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T07:43:39Z","title_canon_sha256":"a47371019842cf3b9cb44358be1590843ee1b2bc15ba89e5ec7b0d5746399702"},"schema_version":"1.0","source":{"id":"2607.14682","kind":"arxiv","version":1}},"canonical_sha256":"cdff915b37e26901a29bf86e1efcd85663ca252dc803ab53adb04a835232dbd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdff915b37e26901a29bf86e1efcd85663ca252dc803ab53adb04a835232dbd9","first_computed_at":"2026-07-17T01:21:24.843015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:24.843015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8PXNuAckjVbjXCeKAQBwUIkCr+YyTCzGcLC9ZdTjHO6FnkK7vgdh3mz30mdH0OF2+e0YwBVlAq+IX/WJvgELCg==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:24.843890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7be30afdb18c18cefc74ce10448a1c7fe33c3c8e70661eb108934e85509aa4f2","sha256:85e5a786add339221eb478868075847beae93c6ea6e7893600c6fba54a02c731"],"state_sha256":"6bca7b40bb51127378880b84aa563e25b08813add9f74ee04b416bf7ff1dfa4e"}