{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QM2AKLQ4PLSRAORLD2HFHDR5OR","short_pith_number":"pith:QM2AKLQ4","canonical_record":{"source":{"id":"2406.11832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:44Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"87208fc42ac897e55a14962f6a17a16e809161f805fd06e0747df1f3f890e3c4","abstract_canon_sha256":"aad977884969bb81986a90ca5a7ecf4f25e1a81eb3887119dfad0dec3378cf46"},"schema_version":"1.0"},"canonical_sha256":"8334052e1c7ae5103a2b1e8e538e3d74581b6908af22c909aff7d70b2e7b0efb","source":{"kind":"arxiv","id":"2406.11832","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11832","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11832v2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11832","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"QM2AKLQ4PLSR","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"QM2AKLQ4PLSRAORL","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"QM2AKLQ4","created_at":"2026-07-05T09:27:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QM2AKLQ4PLSRAORLD2HFHDR5OR","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:44Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"87208fc42ac897e55a14962f6a17a16e809161f805fd06e0747df1f3f890e3c4","abstract_canon_sha256":"aad977884969bb81986a90ca5a7ecf4f25e1a81eb3887119dfad0dec3378cf46"},"schema_version":"1.0"},"canonical_sha256":"8334052e1c7ae5103a2b1e8e538e3d74581b6908af22c909aff7d70b2e7b0efb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:23.171535Z","signature_b64":"3rHCr4JxcaJMKJPXIIqo+tqduMMrPFoAb3e1IiYgvHWmWomRoDqfEYrSl15+6qJlHoHmap91Y0YnVpFNRe+XBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8334052e1c7ae5103a2b1e8e538e3d74581b6908af22c909aff7d70b2e7b0efb","last_reissued_at":"2026-07-05T09:27:23.171061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:23.171061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11832","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vN/EvkMN/CqXX8ICvQ602isV/Gr+QdI79RlTXlI3T9X9K7OC/VSCnTJLwuyvJscxWfUIqL9IVmLjtNq5x3+NCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:36:58.507078Z"},"content_sha256":"c5f3b38fecf609d1e5e253eae12f48da7401613fa1ebfd41c6675dd8b8b4cc3c","schema_version":"1.0","event_id":"sha256:c5f3b38fecf609d1e5e253eae12f48da7401613fa1ebfd41c6675dd8b8b4cc3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QM2AKLQ4PLSRAORLD2HFHDR5OR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling Encoder-Free Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Haiwen Diao, Huchuan Lu, Xiaotong Li, Xinlong Wang, Yueze Wang, Yufeng Cui","submitted_at":"2024-06-17T17:59:44Z","abstract_excerpt":"Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting visual representation, e.g., resolution, aspect ratio, and semantic priors, which could impede the flexibility and efficiency of the VLMs. Training pure VLMs that accept the seamless vision and language inputs, i.e., without vision encoders, remains challenging and rarely explored. Empirical observations reveal that direct training without encoders results in s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11832","kind":"arxiv","version":2},"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/2406.11832/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":"2026-07-05T09:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoXysvdVRiXfdv+yeINUWGLYl/TE0gY2a1934XNFY00AQxRvAa5g4dovfK8+WFtKL7J03UJCXekdejcqqiOzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:36:58.507472Z"},"content_sha256":"e1fde06ea18cc97af22e6c532984fef0c28faa688652145064a543290385c188","schema_version":"1.0","event_id":"sha256:e1fde06ea18cc97af22e6c532984fef0c28faa688652145064a543290385c188"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QM2AKLQ4PLSRAORLD2HFHDR5OR/bundle.json","state_url":"https://pith.science/pith/QM2AKLQ4PLSRAORLD2HFHDR5OR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QM2AKLQ4PLSRAORLD2HFHDR5OR/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":"2026-08-04T05:36:58Z","links":{"resolver":"https://pith.science/pith/QM2AKLQ4PLSRAORLD2HFHDR5OR","bundle":"https://pith.science/pith/QM2AKLQ4PLSRAORLD2HFHDR5OR/bundle.json","state":"https://pith.science/pith/QM2AKLQ4PLSRAORLD2HFHDR5OR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QM2AKLQ4PLSRAORLD2HFHDR5OR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QM2AKLQ4PLSRAORLD2HFHDR5OR","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":"aad977884969bb81986a90ca5a7ecf4f25e1a81eb3887119dfad0dec3378cf46","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:44Z","title_canon_sha256":"87208fc42ac897e55a14962f6a17a16e809161f805fd06e0747df1f3f890e3c4"},"schema_version":"1.0","source":{"id":"2406.11832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11832","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11832v2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11832","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"QM2AKLQ4PLSR","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"QM2AKLQ4PLSRAORL","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"QM2AKLQ4","created_at":"2026-07-05T09:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:e1fde06ea18cc97af22e6c532984fef0c28faa688652145064a543290385c188","target":"graph","created_at":"2026-07-05T09:27:23Z","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/2406.11832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting visual representation, e.g., resolution, aspect ratio, and semantic priors, which could impede the flexibility and efficiency of the VLMs. Training pure VLMs that accept the seamless vision and language inputs, i.e., without vision encoders, remains challenging and rarely explored. Empirical observations reveal that direct training without encoders results in s","authors_text":"Haiwen Diao, Huchuan Lu, Xiaotong Li, Xinlong Wang, Yueze Wang, Yufeng Cui","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:44Z","title":"Unveiling Encoder-Free Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11832","kind":"arxiv","version":2},"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:c5f3b38fecf609d1e5e253eae12f48da7401613fa1ebfd41c6675dd8b8b4cc3c","target":"record","created_at":"2026-07-05T09:27:23Z","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":"aad977884969bb81986a90ca5a7ecf4f25e1a81eb3887119dfad0dec3378cf46","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:44Z","title_canon_sha256":"87208fc42ac897e55a14962f6a17a16e809161f805fd06e0747df1f3f890e3c4"},"schema_version":"1.0","source":{"id":"2406.11832","kind":"arxiv","version":2}},"canonical_sha256":"8334052e1c7ae5103a2b1e8e538e3d74581b6908af22c909aff7d70b2e7b0efb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8334052e1c7ae5103a2b1e8e538e3d74581b6908af22c909aff7d70b2e7b0efb","first_computed_at":"2026-07-05T09:27:23.171061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:23.171061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3rHCr4JxcaJMKJPXIIqo+tqduMMrPFoAb3e1IiYgvHWmWomRoDqfEYrSl15+6qJlHoHmap91Y0YnVpFNRe+XBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:23.171535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5f3b38fecf609d1e5e253eae12f48da7401613fa1ebfd41c6675dd8b8b4cc3c","sha256:e1fde06ea18cc97af22e6c532984fef0c28faa688652145064a543290385c188"],"state_sha256":"6ed20cda668cd6c85127664e46f2fec0fc2cd42d5837ca3701dd9265c77e19d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ht4OZD0kySuMKA2UjkRwCyOqRqokZEKPAYCm8ROh/WsF86Ki4axr0jvzuaGRHMsnDVIbUA/JGEb/cXRNMkapCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:36:58.510602Z","bundle_sha256":"2b21741cbee29a5a53cfa01f2d8aee124206e24a97f2f19eaff9f3958a366562"}}