{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4IJQ5YIT57EYBO7BSNSRKD4QYH","short_pith_number":"pith:4IJQ5YIT","canonical_record":{"source":{"id":"2312.14233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:49:47Z","cross_cats_sorted":[],"title_canon_sha256":"6b3a72e12a0248db61160b3624413216e8d207bf9d7e1ff8decb6431bbe8345c","abstract_canon_sha256":"a559b0b60489392f359f9b6d493675961bcc4216445e0cc2505ba5935cb1bdd6"},"schema_version":"1.0"},"canonical_sha256":"e2130ee113efc980bbe19365150f90c1dc101ed7c0a20ca9153b2d99157c220b","source":{"kind":"arxiv","id":"2312.14233","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14233","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14233v1","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14233","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"pith_short_12","alias_value":"4IJQ5YIT57EY","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"pith_short_16","alias_value":"4IJQ5YIT57EYBO7B","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"pith_short_8","alias_value":"4IJQ5YIT","created_at":"2026-07-05T07:27:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4IJQ5YIT57EYBO7BSNSRKD4QYH","target":"record","payload":{"canonical_record":{"source":{"id":"2312.14233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:49:47Z","cross_cats_sorted":[],"title_canon_sha256":"6b3a72e12a0248db61160b3624413216e8d207bf9d7e1ff8decb6431bbe8345c","abstract_canon_sha256":"a559b0b60489392f359f9b6d493675961bcc4216445e0cc2505ba5935cb1bdd6"},"schema_version":"1.0"},"canonical_sha256":"e2130ee113efc980bbe19365150f90c1dc101ed7c0a20ca9153b2d99157c220b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:12.436517Z","signature_b64":"eHqzVBXl6OYHFyAjWr3F9FsgWQLEczWi9OR5y9kbX8C7KQDUz7ZcU6qvw9AsH2DuNKYTiTRGF1ypyfsxchd9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2130ee113efc980bbe19365150f90c1dc101ed7c0a20ca9153b2d99157c220b","last_reissued_at":"2026-07-05T07:27:12.436026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:12.436026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.14233","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":"2026-07-05T07:27:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1aXBK87EAQACpsqcmS1QhECI8ORGESTzapfcyWQxcZyTzXsrbKGFQHBZ7CR7HK+xHUMMp8x5qYhOQ9KmHXmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:45:03.573122Z"},"content_sha256":"2ba1c424da5bdf085d84e45e2adb83630174657c4905278c21b59f0c6f556e81","schema_version":"1.0","event_id":"sha256:2ba1c424da5bdf085d84e45e2adb83630174657c4905278c21b59f0c6f556e81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4IJQ5YIT57EYBO7BSNSRKD4QYH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Humphrey Shi, Jianwei Yang, Jitesh Jain","submitted_at":"2023-12-21T18:49:47Z","abstract_excerpt":"Humans possess the remarkable skill of Visual Perception, the ability to see and understand the seen, helping them make sense of the visual world and, in turn, reason. Multimodal Large Language Models (MLLM) have recently achieved impressive performance on vision-language tasks ranging from visual question-answering and image captioning to visual reasoning and image generation. However, when prompted to identify or count (perceive) the entities in a given image, existing MLLM systems fail. Working towards developing an accurate MLLM system for perception and reasoning, we propose using Versati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14233","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/2312.14233/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":"2026-07-05T07:27:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukOI1zxBVvm6pFII158yuIX6+KEChzVK4zStBctdR64vxUmr+2+QDwmCZ3cZB8t1tKY8J/SD2OiHooZ0JJEWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:45:03.573635Z"},"content_sha256":"5364cfecbdc6ffa0c048e2b2044c70701ccea9587773db79de3b81ee8ca3d027","schema_version":"1.0","event_id":"sha256:5364cfecbdc6ffa0c048e2b2044c70701ccea9587773db79de3b81ee8ca3d027"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4IJQ5YIT57EYBO7BSNSRKD4QYH/bundle.json","state_url":"https://pith.science/pith/4IJQ5YIT57EYBO7BSNSRKD4QYH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4IJQ5YIT57EYBO7BSNSRKD4QYH/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":"2026-08-10T08:45:03Z","links":{"resolver":"https://pith.science/pith/4IJQ5YIT57EYBO7BSNSRKD4QYH","bundle":"https://pith.science/pith/4IJQ5YIT57EYBO7BSNSRKD4QYH/bundle.json","state":"https://pith.science/pith/4IJQ5YIT57EYBO7BSNSRKD4QYH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4IJQ5YIT57EYBO7BSNSRKD4QYH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4IJQ5YIT57EYBO7BSNSRKD4QYH","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":"a559b0b60489392f359f9b6d493675961bcc4216445e0cc2505ba5935cb1bdd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:49:47Z","title_canon_sha256":"6b3a72e12a0248db61160b3624413216e8d207bf9d7e1ff8decb6431bbe8345c"},"schema_version":"1.0","source":{"id":"2312.14233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14233","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14233v1","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14233","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"pith_short_12","alias_value":"4IJQ5YIT57EY","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"pith_short_16","alias_value":"4IJQ5YIT57EYBO7B","created_at":"2026-07-05T07:27:12Z"},{"alias_kind":"pith_short_8","alias_value":"4IJQ5YIT","created_at":"2026-07-05T07:27:12Z"}],"graph_snapshots":[{"event_id":"sha256:5364cfecbdc6ffa0c048e2b2044c70701ccea9587773db79de3b81ee8ca3d027","target":"graph","created_at":"2026-07-05T07:27:12Z","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/2312.14233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans possess the remarkable skill of Visual Perception, the ability to see and understand the seen, helping them make sense of the visual world and, in turn, reason. Multimodal Large Language Models (MLLM) have recently achieved impressive performance on vision-language tasks ranging from visual question-answering and image captioning to visual reasoning and image generation. However, when prompted to identify or count (perceive) the entities in a given image, existing MLLM systems fail. Working towards developing an accurate MLLM system for perception and reasoning, we propose using Versati","authors_text":"Humphrey Shi, Jianwei Yang, Jitesh Jain","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:49:47Z","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14233","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":"sha256:2ba1c424da5bdf085d84e45e2adb83630174657c4905278c21b59f0c6f556e81","target":"record","created_at":"2026-07-05T07:27:12Z","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":"a559b0b60489392f359f9b6d493675961bcc4216445e0cc2505ba5935cb1bdd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:49:47Z","title_canon_sha256":"6b3a72e12a0248db61160b3624413216e8d207bf9d7e1ff8decb6431bbe8345c"},"schema_version":"1.0","source":{"id":"2312.14233","kind":"arxiv","version":1}},"canonical_sha256":"e2130ee113efc980bbe19365150f90c1dc101ed7c0a20ca9153b2d99157c220b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2130ee113efc980bbe19365150f90c1dc101ed7c0a20ca9153b2d99157c220b","first_computed_at":"2026-07-05T07:27:12.436026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:12.436026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eHqzVBXl6OYHFyAjWr3F9FsgWQLEczWi9OR5y9kbX8C7KQDUz7ZcU6qvw9AsH2DuNKYTiTRGF1ypyfsxchd9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:12.436517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ba1c424da5bdf085d84e45e2adb83630174657c4905278c21b59f0c6f556e81","sha256:5364cfecbdc6ffa0c048e2b2044c70701ccea9587773db79de3b81ee8ca3d027"],"state_sha256":"20002aa7eeed30040989ff731568d1333b41b7c91117c3880f10f219784a825f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LW1aqum4anaUCkm1HQphU1vRAJezZPO/mh9MdT7jmQ4Gpk7ZUPAKgUIgdZHvwEhFjXR2Tyv4qgZLwO3HL/A3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:45:03.577220Z","bundle_sha256":"48afcfcedfeb7d7dd7eebfe60bd8cd1202b85a95f6a140256d24830268ef5cb1"}}