{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E72XMMUOZK7MJA72IIITGY6AGG","short_pith_number":"pith:E72XMMUO","canonical_record":{"source":{"id":"2502.09093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T09:04:28Z","cross_cats_sorted":[],"title_canon_sha256":"152c49b5724fff720cbfd6b948b93eefc5b0097b3a3960d569559b979a6cfece","abstract_canon_sha256":"b651d40a4f56eeb06ff79ce8a6ff286f36e630a46393c164a48b1f3c6090a39d"},"schema_version":"1.0"},"canonical_sha256":"27f576328ecabec483fa42113363c031987317d5815fad29e15553d3a54335c4","source":{"kind":"arxiv","id":"2502.09093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09093","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09093v1","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09093","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"pith_short_12","alias_value":"E72XMMUOZK7M","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"pith_short_16","alias_value":"E72XMMUOZK7MJA72","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"pith_short_8","alias_value":"E72XMMUO","created_at":"2026-07-05T10:13:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E72XMMUOZK7MJA72IIITGY6AGG","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T09:04:28Z","cross_cats_sorted":[],"title_canon_sha256":"152c49b5724fff720cbfd6b948b93eefc5b0097b3a3960d569559b979a6cfece","abstract_canon_sha256":"b651d40a4f56eeb06ff79ce8a6ff286f36e630a46393c164a48b1f3c6090a39d"},"schema_version":"1.0"},"canonical_sha256":"27f576328ecabec483fa42113363c031987317d5815fad29e15553d3a54335c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:52.431566Z","signature_b64":"OurtvdYcK9/h5uFhpB1fnbPG+OuiJwTwAosacLHjytJ0rte+K2AXqWe4OK2/yHk4IzbQ/4NurZNXC8aELK4cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27f576328ecabec483fa42113363c031987317d5815fad29e15553d3a54335c4","last_reissued_at":"2026-07-05T10:13:52.431015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:52.431015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09093","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":"2026-07-05T10:13:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gPPYhc6i5yRFr7aQmI6n7vD6mlgAK7vXh5A93QqPmwbZax2Q1iUdQ6OQkzSmxiJPdZp0mz2zOIr0y9E5z06Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T17:08:55.896209Z"},"content_sha256":"97de43e102e13a61cf410bcefb3620eafaf730dd5eca49584a6a2ef678a8225c","schema_version":"1.0","event_id":"sha256:97de43e102e13a61cf410bcefb3620eafaf730dd5eca49584a6a2ef678a8225c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E72XMMUOZK7MJA72IIITGY6AGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fang Qu, Mingxiao Li, Nan Du, Na Su, Xiaolong Li, Zhanpeng Chen, Zhizhou Zhong, Ziyang Chen","submitted_at":"2025-02-13T09:04:28Z","abstract_excerpt":"While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm for MLLMs. Utilizing dynamic embeddings from the MLP following the visual encoder, this approach supervises image hidden states and integrates image tokens into autoregressive training. Existing MLLMs primarily focused on recovering information from textual inputs, often neglecting the effective processing of image data. In contrast, the key improvement of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09093","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/2502.09093/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":"2026-07-05T10:13:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8y5xwr+ndAjD6Z3EZ/mtpQmEBPbBJ6xZ0m1Fp3gJzPnq4fmAmSh9XsW9WU85xHvCb6Sz8/9KRG4ZSKCXmPu5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T17:08:55.896609Z"},"content_sha256":"2324df1d4487c6df0ec77a6a4401759b84b8f1e6f791b292bcb3e91d230d3c13","schema_version":"1.0","event_id":"sha256:2324df1d4487c6df0ec77a6a4401759b84b8f1e6f791b292bcb3e91d230d3c13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E72XMMUOZK7MJA72IIITGY6AGG/bundle.json","state_url":"https://pith.science/pith/E72XMMUOZK7MJA72IIITGY6AGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E72XMMUOZK7MJA72IIITGY6AGG/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":"2026-07-22T17:08:55Z","links":{"resolver":"https://pith.science/pith/E72XMMUOZK7MJA72IIITGY6AGG","bundle":"https://pith.science/pith/E72XMMUOZK7MJA72IIITGY6AGG/bundle.json","state":"https://pith.science/pith/E72XMMUOZK7MJA72IIITGY6AGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E72XMMUOZK7MJA72IIITGY6AGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E72XMMUOZK7MJA72IIITGY6AGG","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":"b651d40a4f56eeb06ff79ce8a6ff286f36e630a46393c164a48b1f3c6090a39d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T09:04:28Z","title_canon_sha256":"152c49b5724fff720cbfd6b948b93eefc5b0097b3a3960d569559b979a6cfece"},"schema_version":"1.0","source":{"id":"2502.09093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09093","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09093v1","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09093","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"pith_short_12","alias_value":"E72XMMUOZK7M","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"pith_short_16","alias_value":"E72XMMUOZK7MJA72","created_at":"2026-07-05T10:13:52Z"},{"alias_kind":"pith_short_8","alias_value":"E72XMMUO","created_at":"2026-07-05T10:13:52Z"}],"graph_snapshots":[{"event_id":"sha256:2324df1d4487c6df0ec77a6a4401759b84b8f1e6f791b292bcb3e91d230d3c13","target":"graph","created_at":"2026-07-05T10:13:52Z","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/2502.09093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm for MLLMs. Utilizing dynamic embeddings from the MLP following the visual encoder, this approach supervises image hidden states and integrates image tokens into autoregressive training. Existing MLLMs primarily focused on recovering information from textual inputs, often neglecting the effective processing of image data. In contrast, the key improvement of t","authors_text":"Fang Qu, Mingxiao Li, Nan Du, Na Su, Xiaolong Li, Zhanpeng Chen, Zhizhou Zhong, Ziyang Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T09:04:28Z","title":"From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09093","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":"sha256:97de43e102e13a61cf410bcefb3620eafaf730dd5eca49584a6a2ef678a8225c","target":"record","created_at":"2026-07-05T10:13:52Z","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":"b651d40a4f56eeb06ff79ce8a6ff286f36e630a46393c164a48b1f3c6090a39d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T09:04:28Z","title_canon_sha256":"152c49b5724fff720cbfd6b948b93eefc5b0097b3a3960d569559b979a6cfece"},"schema_version":"1.0","source":{"id":"2502.09093","kind":"arxiv","version":1}},"canonical_sha256":"27f576328ecabec483fa42113363c031987317d5815fad29e15553d3a54335c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27f576328ecabec483fa42113363c031987317d5815fad29e15553d3a54335c4","first_computed_at":"2026-07-05T10:13:52.431015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:52.431015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OurtvdYcK9/h5uFhpB1fnbPG+OuiJwTwAosacLHjytJ0rte+K2AXqWe4OK2/yHk4IzbQ/4NurZNXC8aELK4cCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:52.431566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97de43e102e13a61cf410bcefb3620eafaf730dd5eca49584a6a2ef678a8225c","sha256:2324df1d4487c6df0ec77a6a4401759b84b8f1e6f791b292bcb3e91d230d3c13"],"state_sha256":"6fcecb14b11d5ed84aca0878cd45fd675963fd9aaa4957fad49762382941536d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+gTTe2MntoDLgnYrEmHKUTURNVv4ClGyPrGsLYW/KMwm47Ze3n92sK/hh1fBYtHsY7/ba6lCtCbXV4XOfuhgAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T17:08:55.898726Z","bundle_sha256":"e765ea028bf7fc9a116ba1893de25e7e84001328745a6a39306ed7d6862f38e8"}}