{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A4RJXUGANMDM2PZI4JLKXNQWXN","short_pith_number":"pith:A4RJXUGA","canonical_record":{"source":{"id":"2412.11475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T06:38:00Z","cross_cats_sorted":[],"title_canon_sha256":"362a36f97be49aebefcb36379c78afae4fa476f15f6c095a56b015b86019b7cf","abstract_canon_sha256":"785be02752cce821674a82cf00cab6900538a80cf368510f556184bc8b81afe4"},"schema_version":"1.0"},"canonical_sha256":"07229bd0c06b06cd3f28e256abb616bb4104f48e12162c8fcd89f386b3b964ce","source":{"kind":"arxiv","id":"2412.11475","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11475","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11475v2","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11475","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"A4RJXUGANMDM","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_16","alias_value":"A4RJXUGANMDM2PZI","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_8","alias_value":"A4RJXUGA","created_at":"2026-07-05T09:54:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A4RJXUGANMDM2PZI4JLKXNQWXN","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T06:38:00Z","cross_cats_sorted":[],"title_canon_sha256":"362a36f97be49aebefcb36379c78afae4fa476f15f6c095a56b015b86019b7cf","abstract_canon_sha256":"785be02752cce821674a82cf00cab6900538a80cf368510f556184bc8b81afe4"},"schema_version":"1.0"},"canonical_sha256":"07229bd0c06b06cd3f28e256abb616bb4104f48e12162c8fcd89f386b3b964ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:06.594407Z","signature_b64":"IxCngKj8Kk+eQYp1sCr3agMZyrEQYSekDiFcovVw8KYimohElCZ4npgDlNFBx/zPcoVluTsufVFSL2sij7D7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07229bd0c06b06cd3f28e256abb616bb4104f48e12162c8fcd89f386b3b964ce","last_reissued_at":"2026-07-05T09:54:06.593864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:06.593864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11475","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":"2026-07-05T09:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CiP63Fv9rSWkgNGUQAs9iUfMaYikGRU+PsgvxUMaC17QCdi2DLCjIxDkJoJYarsxkqTHqsUtwMOhlOj0kcrkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:51:25.917061Z"},"content_sha256":"559eca74c96159f71a55a2e8c6cbfb5a8b1e3aee3e4b2fe8682030931b5b6d65","schema_version":"1.0","event_id":"sha256:559eca74c96159f71a55a2e8c6cbfb5a8b1e3aee3e4b2fe8682030931b5b6d65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A4RJXUGANMDM2PZI4JLKXNQWXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuo Xin, Wei Chen, Zhiyuan Li","submitted_at":"2024-12-16T06:38:00Z","abstract_excerpt":"We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequence length from 729 to 81 tokens, significantly reducing computational overhead while preserving visual-semantic fidelity. Through a multi-stage training pipeline of pretraining, supervised fine-tuning, and minimal-edit Direct Preference Optimization (DPO), OmniVLM matches the performance of larger models. On multiple benchmarks including ScienceQA, POPE, and MMMU, OmniVLM outperforms existing baselines like nanoLLA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11475","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/2412.11475/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":"2026-07-05T09:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQgawdRAD+6T3afq5EyuEhphRajj+xq/O8p3bKpzelnkGHiGGZy5O3AAMIHQeo+JNJwD+CUD9DnyO8kMohC+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:51:25.917585Z"},"content_sha256":"2899d9fdca1499fb1d6e34467e6248f5f7a92b7e33edcf614fd2d13cbf1d8b47","schema_version":"1.0","event_id":"sha256:2899d9fdca1499fb1d6e34467e6248f5f7a92b7e33edcf614fd2d13cbf1d8b47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4RJXUGANMDM2PZI4JLKXNQWXN/bundle.json","state_url":"https://pith.science/pith/A4RJXUGANMDM2PZI4JLKXNQWXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4RJXUGANMDM2PZI4JLKXNQWXN/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":"2026-08-21T04:51:25Z","links":{"resolver":"https://pith.science/pith/A4RJXUGANMDM2PZI4JLKXNQWXN","bundle":"https://pith.science/pith/A4RJXUGANMDM2PZI4JLKXNQWXN/bundle.json","state":"https://pith.science/pith/A4RJXUGANMDM2PZI4JLKXNQWXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4RJXUGANMDM2PZI4JLKXNQWXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A4RJXUGANMDM2PZI4JLKXNQWXN","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":"785be02752cce821674a82cf00cab6900538a80cf368510f556184bc8b81afe4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T06:38:00Z","title_canon_sha256":"362a36f97be49aebefcb36379c78afae4fa476f15f6c095a56b015b86019b7cf"},"schema_version":"1.0","source":{"id":"2412.11475","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11475","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11475v2","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11475","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"A4RJXUGANMDM","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_16","alias_value":"A4RJXUGANMDM2PZI","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_8","alias_value":"A4RJXUGA","created_at":"2026-07-05T09:54:06Z"}],"graph_snapshots":[{"event_id":"sha256:2899d9fdca1499fb1d6e34467e6248f5f7a92b7e33edcf614fd2d13cbf1d8b47","target":"graph","created_at":"2026-07-05T09:54:06Z","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/2412.11475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequence length from 729 to 81 tokens, significantly reducing computational overhead while preserving visual-semantic fidelity. Through a multi-stage training pipeline of pretraining, supervised fine-tuning, and minimal-edit Direct Preference Optimization (DPO), OmniVLM matches the performance of larger models. On multiple benchmarks including ScienceQA, POPE, and MMMU, OmniVLM outperforms existing baselines like nanoLLA","authors_text":"Shuo Xin, Wei Chen, Zhiyuan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T06:38:00Z","title":"OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11475","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":"sha256:559eca74c96159f71a55a2e8c6cbfb5a8b1e3aee3e4b2fe8682030931b5b6d65","target":"record","created_at":"2026-07-05T09:54:06Z","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":"785be02752cce821674a82cf00cab6900538a80cf368510f556184bc8b81afe4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T06:38:00Z","title_canon_sha256":"362a36f97be49aebefcb36379c78afae4fa476f15f6c095a56b015b86019b7cf"},"schema_version":"1.0","source":{"id":"2412.11475","kind":"arxiv","version":2}},"canonical_sha256":"07229bd0c06b06cd3f28e256abb616bb4104f48e12162c8fcd89f386b3b964ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07229bd0c06b06cd3f28e256abb616bb4104f48e12162c8fcd89f386b3b964ce","first_computed_at":"2026-07-05T09:54:06.593864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:06.593864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IxCngKj8Kk+eQYp1sCr3agMZyrEQYSekDiFcovVw8KYimohElCZ4npgDlNFBx/zPcoVluTsufVFSL2sij7D7Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:06.594407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11475","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:559eca74c96159f71a55a2e8c6cbfb5a8b1e3aee3e4b2fe8682030931b5b6d65","sha256:2899d9fdca1499fb1d6e34467e6248f5f7a92b7e33edcf614fd2d13cbf1d8b47"],"state_sha256":"7a552de6a572e20f24b2c1e550089c5b8e8925893a8f67ab7f17138686e83753"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTX5O7cpLzGOd1xFzJsgcHhtk69nlYsAITExDwlva0l7su9O4aYuoh4di1JZ4sn8SyfY4yl57A0awh7uvAkzBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T04:51:25.923038Z","bundle_sha256":"fe1d8a4274fcd4b59d3597f3965360f01f5854015473e9d8fcbc1c641c74bb45"}}