{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GUXIJ24UUQMM7LIF2SZVISDKRC","short_pith_number":"pith:GUXIJ24U","canonical_record":{"source":{"id":"2411.17762","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:33:52Z","cross_cats_sorted":[],"title_canon_sha256":"55359d1538c498f6f77d28ea3108901a769896d4fa29a7df454d787fb6dbd4ea","abstract_canon_sha256":"c56883c2e5c91aeb751a4f8867cc7c242bddc0edaa22683cac82be3ff8014dd7"},"schema_version":"1.0"},"canonical_sha256":"352e84eb94a418cfad05d4b354486a889788cf242c716bed1f4f6f314334e6d0","source":{"kind":"arxiv","id":"2411.17762","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17762","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17762v4","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17762","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"GUXIJ24UUQMM","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"GUXIJ24UUQMM7LIF","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"GUXIJ24U","created_at":"2026-07-05T11:43:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GUXIJ24UUQMM7LIF2SZVISDKRC","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17762","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:33:52Z","cross_cats_sorted":[],"title_canon_sha256":"55359d1538c498f6f77d28ea3108901a769896d4fa29a7df454d787fb6dbd4ea","abstract_canon_sha256":"c56883c2e5c91aeb751a4f8867cc7c242bddc0edaa22683cac82be3ff8014dd7"},"schema_version":"1.0"},"canonical_sha256":"352e84eb94a418cfad05d4b354486a889788cf242c716bed1f4f6f314334e6d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:58.912084Z","signature_b64":"bCYK8MmA/GfSQoN6Vm9kjGK8UM93l8xqHlFYCm2tw3ODdOFxmml1xt5TzDx7t8aN/i2aHaABofKO1IK65lzsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"352e84eb94a418cfad05d4b354486a889788cf242c716bed1f4f6f314334e6d0","last_reissued_at":"2026-07-05T11:43:58.911602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:58.911602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17762","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ATSwZVDYzzsPHNyHyxEKXf1F7RUCw5/Z/GQl9R45GIEc9tU4Y2f2LXTUQDm0TKJZWMXzZwjMsN+95yzX4NeDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:47:46.448157Z"},"content_sha256":"fa658e4b99d656ded173ef62878500292bf4d25510b37aedfd77170ec166a5a8","schema_version":"1.0","event_id":"sha256:fa658e4b99d656ded173ef62878500292bf4d25510b37aedfd77170ec166a5a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GUXIJ24UUQMM7LIF2SZVISDKRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Chen Du, Ping Song, Rongchang Xie","submitted_at":"2024-11-26T03:33:52Z","abstract_excerpt":"We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exploring unified models for visual generation and understanding. However, existing vision tokenizers (e.g., VQGAN) only consider low-level information, which makes it difficult to align with language tokens. This results in high training complexity and necessitates a large amount of training data to achieve optimal performance. Additionally, their performance is still far from dedicated understanding models. This paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17762","kind":"arxiv","version":4},"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/2411.17762/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":"2026-07-05T11:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/+5QyD4qV/hRGTxCdeTq/uIusNyFj0XRha306J54VDByekuHV2BlRff0S3rjZcpqeLLbjBthzlr3n849svuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:47:46.448654Z"},"content_sha256":"40aecaef6e3a8ff59630cef244a454ce73bb80c677b18e51458a1e15e5f233cc","schema_version":"1.0","event_id":"sha256:40aecaef6e3a8ff59630cef244a454ce73bb80c677b18e51458a1e15e5f233cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUXIJ24UUQMM7LIF2SZVISDKRC/bundle.json","state_url":"https://pith.science/pith/GUXIJ24UUQMM7LIF2SZVISDKRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUXIJ24UUQMM7LIF2SZVISDKRC/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":"2026-08-05T20:47:46Z","links":{"resolver":"https://pith.science/pith/GUXIJ24UUQMM7LIF2SZVISDKRC","bundle":"https://pith.science/pith/GUXIJ24UUQMM7LIF2SZVISDKRC/bundle.json","state":"https://pith.science/pith/GUXIJ24UUQMM7LIF2SZVISDKRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUXIJ24UUQMM7LIF2SZVISDKRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GUXIJ24UUQMM7LIF2SZVISDKRC","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":"c56883c2e5c91aeb751a4f8867cc7c242bddc0edaa22683cac82be3ff8014dd7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:33:52Z","title_canon_sha256":"55359d1538c498f6f77d28ea3108901a769896d4fa29a7df454d787fb6dbd4ea"},"schema_version":"1.0","source":{"id":"2411.17762","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17762","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17762v4","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17762","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"GUXIJ24UUQMM","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"GUXIJ24UUQMM7LIF","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"GUXIJ24U","created_at":"2026-07-05T11:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:40aecaef6e3a8ff59630cef244a454ce73bb80c677b18e51458a1e15e5f233cc","target":"graph","created_at":"2026-07-05T11:43:58Z","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/2411.17762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exploring unified models for visual generation and understanding. However, existing vision tokenizers (e.g., VQGAN) only consider low-level information, which makes it difficult to align with language tokens. This results in high training complexity and necessitates a large amount of training data to achieve optimal performance. Additionally, their performance is still far from dedicated understanding models. This paper","authors_text":"Chang Liu, Chen Du, Ping Song, Rongchang Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:33:52Z","title":"MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17762","kind":"arxiv","version":4},"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:fa658e4b99d656ded173ef62878500292bf4d25510b37aedfd77170ec166a5a8","target":"record","created_at":"2026-07-05T11:43:58Z","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":"c56883c2e5c91aeb751a4f8867cc7c242bddc0edaa22683cac82be3ff8014dd7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:33:52Z","title_canon_sha256":"55359d1538c498f6f77d28ea3108901a769896d4fa29a7df454d787fb6dbd4ea"},"schema_version":"1.0","source":{"id":"2411.17762","kind":"arxiv","version":4}},"canonical_sha256":"352e84eb94a418cfad05d4b354486a889788cf242c716bed1f4f6f314334e6d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"352e84eb94a418cfad05d4b354486a889788cf242c716bed1f4f6f314334e6d0","first_computed_at":"2026-07-05T11:43:58.911602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:58.911602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bCYK8MmA/GfSQoN6Vm9kjGK8UM93l8xqHlFYCm2tw3ODdOFxmml1xt5TzDx7t8aN/i2aHaABofKO1IK65lzsBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:58.912084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17762","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa658e4b99d656ded173ef62878500292bf4d25510b37aedfd77170ec166a5a8","sha256:40aecaef6e3a8ff59630cef244a454ce73bb80c677b18e51458a1e15e5f233cc"],"state_sha256":"5d77f19fff824b89709c2b8da1a9298499dc2d60157da1164150d95be3408184"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mry3cc3Dmwd4NlDcXTC5yPUwQyXit9NIqiF4idlnb6ETz2RjsUY4MxLWDtK53asLKdinC6JgIgNIv5snFq40Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:47:46.453736Z","bundle_sha256":"27db1ebd50fc759ae405fc62cbc696a9ef81d40a2ec1dea25ab9e41565114bb3"}}