{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZLFCBZKFJE3DOXHANVZQIYOOGR","short_pith_number":"pith:ZLFCBZKF","canonical_record":{"source":{"id":"2503.12446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T10:43:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b190988a12c1581c4fac46d308d7152bc648085f71763d2135b8c56e70b1ef89","abstract_canon_sha256":"fde2d6d8476f3b8298d96ef015f87e6fc7461838ab53107bfe3c7e83033641a7"},"schema_version":"1.0"},"canonical_sha256":"caca20e5454936375ce06d730461ce3469d7b00bfbb1fcdb236695c336c205fb","source":{"kind":"arxiv","id":"2503.12446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12446","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12446v1","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12446","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZLFCBZKFJE3D","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZLFCBZKFJE3DOXHA","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZLFCBZKF","created_at":"2026-07-05T10:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZLFCBZKFJE3DOXHANVZQIYOOGR","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T10:43:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b190988a12c1581c4fac46d308d7152bc648085f71763d2135b8c56e70b1ef89","abstract_canon_sha256":"fde2d6d8476f3b8298d96ef015f87e6fc7461838ab53107bfe3c7e83033641a7"},"schema_version":"1.0"},"canonical_sha256":"caca20e5454936375ce06d730461ce3469d7b00bfbb1fcdb236695c336c205fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:13.367646Z","signature_b64":"sPy+3D2vPrgrEuDd/K5MQFSJavvX8kupRhFMtq6DQzqPT+/O90pvh8bc/EDTWxprDNjbQQ7hn/d4pTEC8YbgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caca20e5454936375ce06d730461ce3469d7b00bfbb1fcdb236695c336c205fb","last_reissued_at":"2026-07-05T10:32:13.366702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:13.366702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12446","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":"2026-07-05T10:32:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uuQk2ah6WPxLrkNIKIcBm4dq1jf/Z3q0kciKhmcuHPUnelcCoTpS38nBfHSjJJxgPbS+By9SHn1ycqmegoSdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:49:33.582197Z"},"content_sha256":"3a0f691b75f016a167171b09cfac40284f102dea5d6614bfa85d142285b1eb22","schema_version":"1.0","event_id":"sha256:3a0f691b75f016a167171b09cfac40284f102dea5d6614bfa85d142285b1eb22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZLFCBZKFJE3DOXHANVZQIYOOGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Tianle Li, Winston Hu, Yongming Rao, Yu Cheng","submitted_at":"2025-03-16T10:43:14Z","abstract_excerpt":"Encoder-free multimodal large language models(MLLMs) eliminate the need for a well-trained vision encoder by directly processing image tokens before the language model. While this approach reduces computational overhead and model complexity, it often requires large amounts of training data to effectively capture the visual knowledge typically encoded by vision models like CLIP. The absence of a vision encoder implies that the model is likely to rely on substantial data to learn the necessary visual-semantic alignments. In this work, we present BREEN, a data-efficient encoder-free multimodal ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12446","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/2503.12446/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":"2026-07-05T10:32:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fhdcJnCctTPinMQ2jGU3q2nkp7EOuzdirFK3pg3aGt1x8AHzre+/r33TuX4vf2xQnAcI+stEZWHjJfq+FbUsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:49:33.582715Z"},"content_sha256":"96ad556e5937a9e06ea671cf6c1a9813e8f12ffbc4734240c3699e9288a4420e","schema_version":"1.0","event_id":"sha256:96ad556e5937a9e06ea671cf6c1a9813e8f12ffbc4734240c3699e9288a4420e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLFCBZKFJE3DOXHANVZQIYOOGR/bundle.json","state_url":"https://pith.science/pith/ZLFCBZKFJE3DOXHANVZQIYOOGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLFCBZKFJE3DOXHANVZQIYOOGR/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":"2026-08-12T13:49:33Z","links":{"resolver":"https://pith.science/pith/ZLFCBZKFJE3DOXHANVZQIYOOGR","bundle":"https://pith.science/pith/ZLFCBZKFJE3DOXHANVZQIYOOGR/bundle.json","state":"https://pith.science/pith/ZLFCBZKFJE3DOXHANVZQIYOOGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLFCBZKFJE3DOXHANVZQIYOOGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZLFCBZKFJE3DOXHANVZQIYOOGR","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":"fde2d6d8476f3b8298d96ef015f87e6fc7461838ab53107bfe3c7e83033641a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T10:43:14Z","title_canon_sha256":"b190988a12c1581c4fac46d308d7152bc648085f71763d2135b8c56e70b1ef89"},"schema_version":"1.0","source":{"id":"2503.12446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12446","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12446v1","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12446","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZLFCBZKFJE3D","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZLFCBZKFJE3DOXHA","created_at":"2026-07-05T10:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZLFCBZKF","created_at":"2026-07-05T10:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:96ad556e5937a9e06ea671cf6c1a9813e8f12ffbc4734240c3699e9288a4420e","target":"graph","created_at":"2026-07-05T10:32:13Z","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/2503.12446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Encoder-free multimodal large language models(MLLMs) eliminate the need for a well-trained vision encoder by directly processing image tokens before the language model. While this approach reduces computational overhead and model complexity, it often requires large amounts of training data to effectively capture the visual knowledge typically encoded by vision models like CLIP. The absence of a vision encoder implies that the model is likely to rely on substantial data to learn the necessary visual-semantic alignments. In this work, we present BREEN, a data-efficient encoder-free multimodal ar","authors_text":"Tianle Li, Winston Hu, Yongming Rao, Yu Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T10:43:14Z","title":"BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12446","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":"sha256:3a0f691b75f016a167171b09cfac40284f102dea5d6614bfa85d142285b1eb22","target":"record","created_at":"2026-07-05T10:32:13Z","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":"fde2d6d8476f3b8298d96ef015f87e6fc7461838ab53107bfe3c7e83033641a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T10:43:14Z","title_canon_sha256":"b190988a12c1581c4fac46d308d7152bc648085f71763d2135b8c56e70b1ef89"},"schema_version":"1.0","source":{"id":"2503.12446","kind":"arxiv","version":1}},"canonical_sha256":"caca20e5454936375ce06d730461ce3469d7b00bfbb1fcdb236695c336c205fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caca20e5454936375ce06d730461ce3469d7b00bfbb1fcdb236695c336c205fb","first_computed_at":"2026-07-05T10:32:13.366702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:13.366702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sPy+3D2vPrgrEuDd/K5MQFSJavvX8kupRhFMtq6DQzqPT+/O90pvh8bc/EDTWxprDNjbQQ7hn/d4pTEC8YbgAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:13.367646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a0f691b75f016a167171b09cfac40284f102dea5d6614bfa85d142285b1eb22","sha256:96ad556e5937a9e06ea671cf6c1a9813e8f12ffbc4734240c3699e9288a4420e"],"state_sha256":"17272c5b3dac9c99c9f89991ed797556f692137fb398a6b2cba8a58b99dfad2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GFor89in+NBttxF7I+Q+7qgmls5Mt9qpdoaWLTdMfCJ/u74KCGAM9Hpd5IDvt1/i8s+v5/qGwqhsHv2UCMVPBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:49:33.586537Z","bundle_sha256":"b04a90c8e779dc456fdd3fbef3168090727bfaf27cfdf09877f5eaef1bbe2666"}}