{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FQ4WLK7P3WTSDZBOLGFVEUERHR","short_pith_number":"pith:FQ4WLK7P","canonical_record":{"source":{"id":"2412.16524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T08:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"a715041428bb0fa5dd1a57588f7da1d513c6fec3cccbb773649ce835546b013a","abstract_canon_sha256":"4cc2c3f80ba0c8f2d1a0fd141c78bd89ae13b1afc53403fd1d52350ef262c0b6"},"schema_version":"1.0"},"canonical_sha256":"2c3965abefdda721e42e598b5250913c644f85b0a20e72febd300f737b2c973c","source":{"kind":"arxiv","id":"2412.16524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16524","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16524v1","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16524","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"FQ4WLK7P3WTS","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"FQ4WLK7P3WTSDZBO","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"FQ4WLK7P","created_at":"2026-07-05T09:52:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FQ4WLK7P3WTSDZBOLGFVEUERHR","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T08:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"a715041428bb0fa5dd1a57588f7da1d513c6fec3cccbb773649ce835546b013a","abstract_canon_sha256":"4cc2c3f80ba0c8f2d1a0fd141c78bd89ae13b1afc53403fd1d52350ef262c0b6"},"schema_version":"1.0"},"canonical_sha256":"2c3965abefdda721e42e598b5250913c644f85b0a20e72febd300f737b2c973c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:49.091266Z","signature_b64":"ZPCNSeQVWOAbOkQFmxt2z1Ux6og+JEHaWVGD2f3qnHh6agWuazXP/sQtpNvMqA+hJBNuh/plGXo/NU2AuPluCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c3965abefdda721e42e598b5250913c644f85b0a20e72febd300f737b2c973c","last_reissued_at":"2026-07-05T09:52:49.090826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:49.090826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16524","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q3g+RbYGV7CV3Ai/R1RyDSeaIXaOEkJ7KpsBjlUr3WE1aNa866xgkXmrGaFvozz1DOB4BGmRfVBDBvKAt5rDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:11:02.521604Z"},"content_sha256":"3e7d19b0ffc8bd329ba431a0721569c4a57e5ac632ecd537d521ad910714534e","schema_version":"1.0","event_id":"sha256:3e7d19b0ffc8bd329ba431a0721569c4a57e5ac632ecd537d521ad910714534e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FQ4WLK7P3WTSDZBOLGFVEUERHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-SLT: Visual Language Tuning for Sign Language Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Tang, Chengyu Huang, Han Liang, Jingyi Yu, Juze Zhang, Lan Xu, Weicai Ye, Xin Chen, Yuecheng Xu","submitted_at":"2024-12-21T08:01:08Z","abstract_excerpt":"In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based approaches in terms of translation accuracy. To narrow this performance gap, we introduce LLaVA-SLT, a pioneering Large Multimodal Model (LMM) framework designed to leverage the power of Large Language Models (LLMs) through effectively learned visual language embeddings. Our model is trained through a trilogy. First, we propose linguistic continued pretraining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16524","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/2412.16524/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+se6aQJLlUI6pZdBcNC+R60ea089eQ5IE1i/hoPow8JB+cVv4p9RbYYksM8kIF826eZJwNGRK6x8Y/w84h3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:11:02.522512Z"},"content_sha256":"5f766024c95fd7f2a49e5b9b1e3d9687473045f2e895fa2af0a119e176840ce0","schema_version":"1.0","event_id":"sha256:5f766024c95fd7f2a49e5b9b1e3d9687473045f2e895fa2af0a119e176840ce0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/bundle.json","state_url":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T11:11:02Z","links":{"resolver":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR","bundle":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/bundle.json","state":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FQ4WLK7P3WTSDZBOLGFVEUERHR","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":"4cc2c3f80ba0c8f2d1a0fd141c78bd89ae13b1afc53403fd1d52350ef262c0b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T08:01:08Z","title_canon_sha256":"a715041428bb0fa5dd1a57588f7da1d513c6fec3cccbb773649ce835546b013a"},"schema_version":"1.0","source":{"id":"2412.16524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16524","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16524v1","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16524","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"FQ4WLK7P3WTS","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"FQ4WLK7P3WTSDZBO","created_at":"2026-07-05T09:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"FQ4WLK7P","created_at":"2026-07-05T09:52:49Z"}],"graph_snapshots":[{"event_id":"sha256:5f766024c95fd7f2a49e5b9b1e3d9687473045f2e895fa2af0a119e176840ce0","target":"graph","created_at":"2026-07-05T09:52:49Z","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/2412.16524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based approaches in terms of translation accuracy. To narrow this performance gap, we introduce LLaVA-SLT, a pioneering Large Multimodal Model (LMM) framework designed to leverage the power of Large Language Models (LLMs) through effectively learned visual language embeddings. Our model is trained through a trilogy. First, we propose linguistic continued pretraining","authors_text":"Cheng Tang, Chengyu Huang, Han Liang, Jingyi Yu, Juze Zhang, Lan Xu, Weicai Ye, Xin Chen, Yuecheng Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T08:01:08Z","title":"LLaVA-SLT: Visual Language Tuning for Sign Language Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16524","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":"sha256:3e7d19b0ffc8bd329ba431a0721569c4a57e5ac632ecd537d521ad910714534e","target":"record","created_at":"2026-07-05T09:52:49Z","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":"4cc2c3f80ba0c8f2d1a0fd141c78bd89ae13b1afc53403fd1d52350ef262c0b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T08:01:08Z","title_canon_sha256":"a715041428bb0fa5dd1a57588f7da1d513c6fec3cccbb773649ce835546b013a"},"schema_version":"1.0","source":{"id":"2412.16524","kind":"arxiv","version":1}},"canonical_sha256":"2c3965abefdda721e42e598b5250913c644f85b0a20e72febd300f737b2c973c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c3965abefdda721e42e598b5250913c644f85b0a20e72febd300f737b2c973c","first_computed_at":"2026-07-05T09:52:49.090826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:49.090826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZPCNSeQVWOAbOkQFmxt2z1Ux6og+JEHaWVGD2f3qnHh6agWuazXP/sQtpNvMqA+hJBNuh/plGXo/NU2AuPluCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:49.091266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e7d19b0ffc8bd329ba431a0721569c4a57e5ac632ecd537d521ad910714534e","sha256:5f766024c95fd7f2a49e5b9b1e3d9687473045f2e895fa2af0a119e176840ce0"],"state_sha256":"c8895fc5c9266d4d91ac51fd1dab3236240c795a07379a289d468e51c56b2dfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FeI7ivQ/oLZvzL5nHaAMEEHUAwOo/m7OsjkI2C3Jlw276jN9yM+iMRyOGl7ka7/L6AIhguNUUuSw2hWyqddYDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:11:02.528178Z","bundle_sha256":"504ae48ea72bdf5aca73ad2ca8658e9ab8efdf248522e8eb196c42316337662f"}}