{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PQVEUYBKZZLIKESPQEKJN4LPFN","short_pith_number":"pith:PQVEUYBK","canonical_record":{"source":{"id":"2412.19806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T08:39:04Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"edb013e4fd45b3522538383387f771f62a40071a7f3784629ba8d4de5c809a78","abstract_canon_sha256":"7552bae0d1248b8b86daa2e8f6cbc1fa600c9e7279ccd5d77d55a2a2f935cd1b"},"schema_version":"1.0"},"canonical_sha256":"7c2a4a602ace5685124f811496f16f2b62e83ea91bb8bf8e7fcdd8b09b556f28","source":{"kind":"arxiv","id":"2412.19806","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19806","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19806v1","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19806","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_12","alias_value":"PQVEUYBKZZLI","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_16","alias_value":"PQVEUYBKZZLIKESP","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_8","alias_value":"PQVEUYBK","created_at":"2026-07-05T09:54:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PQVEUYBKZZLIKESPQEKJN4LPFN","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T08:39:04Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"edb013e4fd45b3522538383387f771f62a40071a7f3784629ba8d4de5c809a78","abstract_canon_sha256":"7552bae0d1248b8b86daa2e8f6cbc1fa600c9e7279ccd5d77d55a2a2f935cd1b"},"schema_version":"1.0"},"canonical_sha256":"7c2a4a602ace5685124f811496f16f2b62e83ea91bb8bf8e7fcdd8b09b556f28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:49.719489Z","signature_b64":"0BMg0hDwWs/eV2U22u1PyGnhYJJbYCcMRrGvr27SFhZ00zMyhBWLgKYuylT1cpEn1icuLI/yZqXX6VntLiIYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c2a4a602ace5685124f811496f16f2b62e83ea91bb8bf8e7fcdd8b09b556f28","last_reissued_at":"2026-07-05T09:54:49.719073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:49.719073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19806","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":"2026-07-05T09:54:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ppJcmFd8vpT57yBHN6OVtqBy9wvpQvLq0mxr3cgPp+NmjpqMGeBGGzoIlFvjNyJWxR+K5FxERrrYvSF0HlR9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:39:30.667418Z"},"content_sha256":"b96a34089c4334753e36089f4401634ca4b0f174a080f51cd344cbcff65345a3","schema_version":"1.0","event_id":"sha256:b96a34089c4334753e36089f4401634ca4b0f174a080f51cd344cbcff65345a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PQVEUYBKZZLIKESPQEKJN4LPFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Hao Fei, Shengqiong Wu, Shuicheng Yan, Tat-Seng Chua","submitted_at":"2024-10-08T08:39:04Z","abstract_excerpt":"Recent developments of vision large language models (LLMs) have seen remarkable progress, yet still encounter challenges towards multimodal generalists, such as coarse-grained instance-level understanding, lack of unified support for both images and videos, and insufficient coverage across various vision tasks. In this paper, we present VITRON, a universal pixel-level vision LLM designed for comprehensive understanding, generating, segmenting, and editing of both static images and dynamic videos. Building on top of an LLM backbone, VITRON incorporates encoders for images, videos, and pixel-lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19806","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/2412.19806/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":"2026-07-05T09:54:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdHDWV9nKamZo+EWXp7zr/c9HMRDzHEaYjnnub58iGHg2dwMMf2ApWeRgtPa1UjIiJI66Wg9eb1d1HJN7auYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:39:30.668037Z"},"content_sha256":"4222f986f1092e6b3401af46794559e758a28c4129a021d4a4f126ee1da5bdd9","schema_version":"1.0","event_id":"sha256:4222f986f1092e6b3401af46794559e758a28c4129a021d4a4f126ee1da5bdd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQVEUYBKZZLIKESPQEKJN4LPFN/bundle.json","state_url":"https://pith.science/pith/PQVEUYBKZZLIKESPQEKJN4LPFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQVEUYBKZZLIKESPQEKJN4LPFN/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":"2026-08-08T17:39:30Z","links":{"resolver":"https://pith.science/pith/PQVEUYBKZZLIKESPQEKJN4LPFN","bundle":"https://pith.science/pith/PQVEUYBKZZLIKESPQEKJN4LPFN/bundle.json","state":"https://pith.science/pith/PQVEUYBKZZLIKESPQEKJN4LPFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQVEUYBKZZLIKESPQEKJN4LPFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PQVEUYBKZZLIKESPQEKJN4LPFN","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":"7552bae0d1248b8b86daa2e8f6cbc1fa600c9e7279ccd5d77d55a2a2f935cd1b","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T08:39:04Z","title_canon_sha256":"edb013e4fd45b3522538383387f771f62a40071a7f3784629ba8d4de5c809a78"},"schema_version":"1.0","source":{"id":"2412.19806","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19806","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19806v1","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19806","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_12","alias_value":"PQVEUYBKZZLI","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_16","alias_value":"PQVEUYBKZZLIKESP","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_8","alias_value":"PQVEUYBK","created_at":"2026-07-05T09:54:49Z"}],"graph_snapshots":[{"event_id":"sha256:4222f986f1092e6b3401af46794559e758a28c4129a021d4a4f126ee1da5bdd9","target":"graph","created_at":"2026-07-05T09:54:49Z","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/2412.19806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent developments of vision large language models (LLMs) have seen remarkable progress, yet still encounter challenges towards multimodal generalists, such as coarse-grained instance-level understanding, lack of unified support for both images and videos, and insufficient coverage across various vision tasks. In this paper, we present VITRON, a universal pixel-level vision LLM designed for comprehensive understanding, generating, segmenting, and editing of both static images and dynamic videos. Building on top of an LLM backbone, VITRON incorporates encoders for images, videos, and pixel-lev","authors_text":"Hanwang Zhang, Hao Fei, Shengqiong Wu, Shuicheng Yan, Tat-Seng Chua","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T08:39:04Z","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19806","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:b96a34089c4334753e36089f4401634ca4b0f174a080f51cd344cbcff65345a3","target":"record","created_at":"2026-07-05T09:54:49Z","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":"7552bae0d1248b8b86daa2e8f6cbc1fa600c9e7279ccd5d77d55a2a2f935cd1b","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T08:39:04Z","title_canon_sha256":"edb013e4fd45b3522538383387f771f62a40071a7f3784629ba8d4de5c809a78"},"schema_version":"1.0","source":{"id":"2412.19806","kind":"arxiv","version":1}},"canonical_sha256":"7c2a4a602ace5685124f811496f16f2b62e83ea91bb8bf8e7fcdd8b09b556f28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c2a4a602ace5685124f811496f16f2b62e83ea91bb8bf8e7fcdd8b09b556f28","first_computed_at":"2026-07-05T09:54:49.719073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:49.719073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0BMg0hDwWs/eV2U22u1PyGnhYJJbYCcMRrGvr27SFhZ00zMyhBWLgKYuylT1cpEn1icuLI/yZqXX6VntLiIYDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:49.719489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19806","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b96a34089c4334753e36089f4401634ca4b0f174a080f51cd344cbcff65345a3","sha256:4222f986f1092e6b3401af46794559e758a28c4129a021d4a4f126ee1da5bdd9"],"state_sha256":"065f79f3847fa96943f429880c30d949e6b8e711d6d66152acc78d33aaa1ad5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OPpZSYw2GyrOm4/4abNZBXytkwZ2s+qjEk5jymx4x6qhUT8ejINzLEcy03qGYnCEDE/FZcFz6LmFpSCEOMV0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:39:30.676377Z","bundle_sha256":"25c786142d35b9f400e50ebfc57aa45ac47800737cd188c65136c7801c8bdcd3"}}