{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XQQCCYU7VGKYKGKJXCJ64X7LJ7","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":"15f550f5128a41995973657342132eef40954c7633906189a1f305994ea1584b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T11:34:28Z","title_canon_sha256":"eaf5647196fa2c5d178ecf79dab5b1ce15ec4db95abf3780fa2759b7200bf7b6"},"schema_version":"1.0","source":{"id":"2606.24447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24447","created_at":"2026-06-24T01:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24447v1","created_at":"2026-06-24T01:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24447","created_at":"2026-06-24T01:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"XQQCCYU7VGKY","created_at":"2026-06-24T01:15:30Z"},{"alias_kind":"pith_short_16","alias_value":"XQQCCYU7VGKYKGKJ","created_at":"2026-06-24T01:15:30Z"},{"alias_kind":"pith_short_8","alias_value":"XQQCCYU7","created_at":"2026-06-24T01:15:30Z"}],"graph_snapshots":[{"event_id":"sha256:22e435bb7d87ca4bb2163de36cd5fd26cf0edb22dfce593e64c1b94679cec09f","target":"graph","created_at":"2026-06-24T01:15:30Z","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/2606.24447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have revolutionized document parsing by enabling end-to-end mapping from images to structured text, imposing a significant latency bottleneck, particularly for token-dense documents. While Multi-Token Prediction (MTP) has emerged as a promising approach for accelerating inference, its potential is constrained by optimization instability when scaling to deeper look-ahead depth. In this paper, we propose \\textbf{P-MTP}, a framework that leverages \\textbf{Progressive Multi-Token Prediction} with a lightweight MTP module to scale the look-ahead depth for high-throughp","authors_text":"Chenxi Zhai, Jingjing Wu, Kunbin Chen, Le Xiang, Qunyi Xie, Shu Wei, Wei He, Xiao Tan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T11:34:28Z","title":"P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24447","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":"sha256:5a53591bdb758eb25b4e87b8dafac3f0a66c0cbe4c415ae0c7230a742937df3d","target":"record","created_at":"2026-06-24T01:15:30Z","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":"15f550f5128a41995973657342132eef40954c7633906189a1f305994ea1584b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T11:34:28Z","title_canon_sha256":"eaf5647196fa2c5d178ecf79dab5b1ce15ec4db95abf3780fa2759b7200bf7b6"},"schema_version":"1.0","source":{"id":"2606.24447","kind":"arxiv","version":1}},"canonical_sha256":"bc2021629fa995851949b893ee5feb4fd2f2ac1009cabf8418c4e6636acf73b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc2021629fa995851949b893ee5feb4fd2f2ac1009cabf8418c4e6636acf73b8","first_computed_at":"2026-06-24T01:15:30.657217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:30.657217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CP6nX9aTZ/vX5sh3XQ1fzSbfoZiwSCg7cggxIzvGAdhTpHvHiM6gI7D+re45XGxI8gfqvjD2vUt9PbuxbHoOCA==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:30.657577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a53591bdb758eb25b4e87b8dafac3f0a66c0cbe4c415ae0c7230a742937df3d","sha256:22e435bb7d87ca4bb2163de36cd5fd26cf0edb22dfce593e64c1b94679cec09f"],"state_sha256":"f0d7837a1b1a1610c564ed59c3f47f8f881d7cc29f009814ace9d05a53af9061"}