{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F2GY6RTN7Q5X4QBJJWKN3M5O45","short_pith_number":"pith:F2GY6RTN","canonical_record":{"source":{"id":"2401.10208","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T18:50:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6a20e23035f5105db9f997a2a18ae7485f6e17cf4793fdc1dc95347fac8b1535","abstract_canon_sha256":"2109cd39d487eee2fb4b06f85d5ff1fa42ef88658c12c5d3d6f23a4e8b1542fb"},"schema_version":"1.0"},"canonical_sha256":"2e8d8f466dfc3b7e40294d94ddb3aee76bf7d2192396dbcd3a0b8befce9b63b3","source":{"kind":"arxiv","id":"2401.10208","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10208","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10208v2","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10208","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"F2GY6RTN7Q5X","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"F2GY6RTN7Q5X4QBJ","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"F2GY6RTN","created_at":"2026-07-05T08:03:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F2GY6RTN7Q5X4QBJJWKN3M5O45","target":"record","payload":{"canonical_record":{"source":{"id":"2401.10208","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T18:50:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6a20e23035f5105db9f997a2a18ae7485f6e17cf4793fdc1dc95347fac8b1535","abstract_canon_sha256":"2109cd39d487eee2fb4b06f85d5ff1fa42ef88658c12c5d3d6f23a4e8b1542fb"},"schema_version":"1.0"},"canonical_sha256":"2e8d8f466dfc3b7e40294d94ddb3aee76bf7d2192396dbcd3a0b8befce9b63b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:10.117533Z","signature_b64":"clXQ9I6XChmnYabO+g3gGLo3LBobml/d+380JHsS9Coez5KjW5wCI1T11qJ/uNrD9qxsvx+lykKX8IGTzgSDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e8d8f466dfc3b7e40294d94ddb3aee76bf7d2192396dbcd3a0b8befce9b63b3","last_reissued_at":"2026-07-05T08:03:10.117038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:10.117038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.10208","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":"2026-07-05T08:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wzd1La+VBEXwv4UYP3duifkEU90Qck8SMko/7ZpUvZ1Soda7Y3NpF3eUcCaMhM6uchQc/bkPJTmqP6g/We98BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:40:22.395315Z"},"content_sha256":"188efa91de9d9090baa6beab12c7821599f16b4fe8d84825521c68d4d62ffc18","schema_version":"1.0","event_id":"sha256:188efa91de9d9090baa6beab12c7821599f16b4fe8d84825521c68d4d62ffc18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F2GY6RTN7Q5X4QBJJWKN3M5O45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Hongsheng Li, Jie Zhou, Jifeng Dai, Lewei Lu, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yuntao Chen, Yu Qiao, Yuwen Xiong, Zhe Chen","submitted_at":"2024-01-18T18:50:16Z","abstract_excerpt":"Developing generative models for interleaved image-text data has both research and practical value. It requires models to understand the interleaved sequences and subsequently generate images and text. However, existing attempts are limited by the issue that the fixed number of visual tokens cannot efficiently capture image details, which is particularly problematic in the multi-image scenarios. To address this, this paper presents MM-Interleaved, an end-to-end generative model for interleaved image-text data. It introduces a multi-scale and multi-image feature synchronizer module, allowing di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10208","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/2401.10208/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":"2026-07-05T08:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z83+1/oz0xiQTz9mA5TYglscw1iIjygEEQ0VCAKu+H99Ee3oa5JUYrvMm3NMkXQaEq8jn8b90N02Tb68ZLeABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:40:22.395858Z"},"content_sha256":"79dde045a174393e3c95b39ddbd4333f800d03511e1561cca65a4a1eae18b268","schema_version":"1.0","event_id":"sha256:79dde045a174393e3c95b39ddbd4333f800d03511e1561cca65a4a1eae18b268"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F2GY6RTN7Q5X4QBJJWKN3M5O45/bundle.json","state_url":"https://pith.science/pith/F2GY6RTN7Q5X4QBJJWKN3M5O45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F2GY6RTN7Q5X4QBJJWKN3M5O45/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":"2026-08-10T02:40:22Z","links":{"resolver":"https://pith.science/pith/F2GY6RTN7Q5X4QBJJWKN3M5O45","bundle":"https://pith.science/pith/F2GY6RTN7Q5X4QBJJWKN3M5O45/bundle.json","state":"https://pith.science/pith/F2GY6RTN7Q5X4QBJJWKN3M5O45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F2GY6RTN7Q5X4QBJJWKN3M5O45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F2GY6RTN7Q5X4QBJJWKN3M5O45","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":"2109cd39d487eee2fb4b06f85d5ff1fa42ef88658c12c5d3d6f23a4e8b1542fb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T18:50:16Z","title_canon_sha256":"6a20e23035f5105db9f997a2a18ae7485f6e17cf4793fdc1dc95347fac8b1535"},"schema_version":"1.0","source":{"id":"2401.10208","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10208","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10208v2","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10208","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"F2GY6RTN7Q5X","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"F2GY6RTN7Q5X4QBJ","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"F2GY6RTN","created_at":"2026-07-05T08:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:79dde045a174393e3c95b39ddbd4333f800d03511e1561cca65a4a1eae18b268","target":"graph","created_at":"2026-07-05T08:03:10Z","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/2401.10208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing generative models for interleaved image-text data has both research and practical value. It requires models to understand the interleaved sequences and subsequently generate images and text. However, existing attempts are limited by the issue that the fixed number of visual tokens cannot efficiently capture image details, which is particularly problematic in the multi-image scenarios. To address this, this paper presents MM-Interleaved, an end-to-end generative model for interleaved image-text data. It introduces a multi-scale and multi-image feature synchronizer module, allowing di","authors_text":"Changyao Tian, Hongsheng Li, Jie Zhou, Jifeng Dai, Lewei Lu, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yuntao Chen, Yu Qiao, Yuwen Xiong, Zhe Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T18:50:16Z","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10208","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":"sha256:188efa91de9d9090baa6beab12c7821599f16b4fe8d84825521c68d4d62ffc18","target":"record","created_at":"2026-07-05T08:03:10Z","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":"2109cd39d487eee2fb4b06f85d5ff1fa42ef88658c12c5d3d6f23a4e8b1542fb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T18:50:16Z","title_canon_sha256":"6a20e23035f5105db9f997a2a18ae7485f6e17cf4793fdc1dc95347fac8b1535"},"schema_version":"1.0","source":{"id":"2401.10208","kind":"arxiv","version":2}},"canonical_sha256":"2e8d8f466dfc3b7e40294d94ddb3aee76bf7d2192396dbcd3a0b8befce9b63b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e8d8f466dfc3b7e40294d94ddb3aee76bf7d2192396dbcd3a0b8befce9b63b3","first_computed_at":"2026-07-05T08:03:10.117038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:10.117038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"clXQ9I6XChmnYabO+g3gGLo3LBobml/d+380JHsS9Coez5KjW5wCI1T11qJ/uNrD9qxsvx+lykKX8IGTzgSDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:10.117533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.10208","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:188efa91de9d9090baa6beab12c7821599f16b4fe8d84825521c68d4d62ffc18","sha256:79dde045a174393e3c95b39ddbd4333f800d03511e1561cca65a4a1eae18b268"],"state_sha256":"924fbdc5ecf4a6a7c0b4a53ac7fb72457d32483bcea57accaf9768eb542ecfb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1PrI/7Y02fs9BS1bjqlZhu70hmlkquNbmJ0C/dM5zJ5xlc8VBiL8wEBLo9Nvu0dvJS36Kwwb6HL2Sz9vWhgDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:40:22.401805Z","bundle_sha256":"abc2842c4ee6774e02ea068ffb18a53b25df54272dc33b775e03b3e657d7de17"}}