{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5D45XYU5HPDYABDAA2T5V5FLGU","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":"a07ea30e4de952ea1ddde696bbe68987e03505357f3baf9b796c7d06bf45e759","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-04T01:17:48Z","title_canon_sha256":"38714cd9a71ed936debcf3ac977d7e1ffd539188e7d664cd37b00bc06ea5d256"},"schema_version":"1.0","source":{"id":"2607.03657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03657","created_at":"2026-07-07T02:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03657v1","created_at":"2026-07-07T02:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03657","created_at":"2026-07-07T02:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"5D45XYU5HPDY","created_at":"2026-07-07T02:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"5D45XYU5HPDYABDA","created_at":"2026-07-07T02:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"5D45XYU5","created_at":"2026-07-07T02:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:3e4ed46082e6d6215f766e703575dc7ee334566dd2e795564bc4c3b106f77c2c","target":"graph","created_at":"2026-07-07T02:17:59Z","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/2607.03657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gloss-free Sign Language Translation (SLT) translates sign language videos into spoken-language sentences without gloss annotations, avoiding costly labeling but requiring fine-grained modeling of hands, body, and facial cues. Existing methods often use single-modality or weakly fused features, limiting performance. We propose ViPo-MLLM, a framework that integrates spatio-temporal RGB and human pose features. Dedicated encoders model intra-modal dynamics and cross-modal attention captures long-range dependencies. The fused representation is conditioned with a structured prompt and processed by","authors_text":"Ahmed Abul Hasanaath, Bicheng Xu, Hamzah Luqman, Leonid Sigal, Mir Rayat Imtiaz Hossain","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-04T01:17:48Z","title":"ViPo-MLLM: Visual-Pose Multimodal LLM for Gloss-Free Sign Language Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03657","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":"sha256:3922b77b83af4ff729bd6558d774a7b2efe2308b2b3aafaa433a9109988df069","target":"record","created_at":"2026-07-07T02:17:59Z","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":"a07ea30e4de952ea1ddde696bbe68987e03505357f3baf9b796c7d06bf45e759","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-04T01:17:48Z","title_canon_sha256":"38714cd9a71ed936debcf3ac977d7e1ffd539188e7d664cd37b00bc06ea5d256"},"schema_version":"1.0","source":{"id":"2607.03657","kind":"arxiv","version":1}},"canonical_sha256":"e8f9dbe29d3bc780046006a7daf4ab353fc8ab7d9ca30ca0f64318d78212f215","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8f9dbe29d3bc780046006a7daf4ab353fc8ab7d9ca30ca0f64318d78212f215","first_computed_at":"2026-07-07T02:17:59.749649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:59.749649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yzzfashqvl6K4TSsJtz05UrNl+gyy9lXm6Iz8cx0rWowrnyOFfWi6u7n0VIwwFKhb8GqPi1JoXk4xE0Xu6cYAg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:59.750419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3922b77b83af4ff729bd6558d774a7b2efe2308b2b3aafaa433a9109988df069","sha256:3e4ed46082e6d6215f766e703575dc7ee334566dd2e795564bc4c3b106f77c2c"],"state_sha256":"366dcffcf3566dd7a95fad4b024f95fd985669139390ac33eb67175639dabf7b"}