{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JWAMCQKA64PMFRIAZWM5I4NYCT","short_pith_number":"pith:JWAMCQKA","canonical_record":{"source":{"id":"2412.10758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:04:32Z","cross_cats_sorted":[],"title_canon_sha256":"2c0267fc556844023210ba5f2788d1eaf97941c6b55df1eb9839092f7213ca53","abstract_canon_sha256":"13cecc8bfe7efedcdcd59dbc79cb760ee9cf78ce97960daa6d15acd97d058987"},"schema_version":"1.0"},"canonical_sha256":"4d80c14140f71ec2c500cd99d471b814c52455a985f39fd11a1b8d419d3c3b4b","source":{"kind":"arxiv","id":"2412.10758","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10758","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10758v1","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10758","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_12","alias_value":"JWAMCQKA64PM","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_16","alias_value":"JWAMCQKA64PMFRIA","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_8","alias_value":"JWAMCQKA","created_at":"2026-07-05T09:49:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JWAMCQKA64PMFRIAZWM5I4NYCT","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:04:32Z","cross_cats_sorted":[],"title_canon_sha256":"2c0267fc556844023210ba5f2788d1eaf97941c6b55df1eb9839092f7213ca53","abstract_canon_sha256":"13cecc8bfe7efedcdcd59dbc79cb760ee9cf78ce97960daa6d15acd97d058987"},"schema_version":"1.0"},"canonical_sha256":"4d80c14140f71ec2c500cd99d471b814c52455a985f39fd11a1b8d419d3c3b4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:21.134994Z","signature_b64":"7kH1uCH/MxEqb5FZs6qIYJJrsvGloXrou/PpqBTenQMgooK5tjOxKzSpUh7APg/GxbHb49u4c/9KmPUmc9A/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d80c14140f71ec2c500cd99d471b814c52455a985f39fd11a1b8d419d3c3b4b","last_reissued_at":"2026-07-05T09:49:21.134474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:21.134474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10758","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":"2026-07-05T09:49:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0A6GbuQoyP5QEW1O+3ZmXoPQ5L6NEipQXDIEA8/IKp9el4w+IY6+I+5YJ3giXL5tEi6TQbfJtEtjCQFLiXUzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:34:11.605264Z"},"content_sha256":"62ace7bbe63ddcea56f44552ecbd03851d1f3afc78f25aa6fa29d26bf8addd22","schema_version":"1.0","event_id":"sha256:62ace7bbe63ddcea56f44552ecbd03851d1f3afc78f25aa6fa29d26bf8addd22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JWAMCQKA64PMFRIAZWM5I4NYCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Vision-Language Interactions Through Decoder-Only Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Tan, Brian Wong, Kaito Tanaka","submitted_at":"2024-12-14T09:04:32Z","abstract_excerpt":"Vision-Language Models (VLMs) have emerged as key enablers for multimodal tasks, but their reliance on separate visual encoders introduces challenges in efficiency, scalability, and modality alignment. To address these limitations, we propose MUDAIF (Multimodal Unified Decoder with Adaptive Input Fusion), a decoder-only vision-language model that seamlessly integrates visual and textual inputs through a novel Vision-Token Adapter (VTA) and adaptive co-attention mechanism. By eliminating the need for a visual encoder, MUDAIF achieves enhanced efficiency, flexibility, and cross-modal understandi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10758","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/2412.10758/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":"2026-07-05T09:49:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mVCuqcK/P1CJazdC3q9haGZnBFfYI60kKUyo4xx98tP09DruVhYdxEDUS6bi506HVPHS3QYzfMxQfj1faV3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:34:11.605779Z"},"content_sha256":"6b187c3e4d060193e056801102d4cd6ff23b93f16536445254c857100a305ecd","schema_version":"1.0","event_id":"sha256:6b187c3e4d060193e056801102d4cd6ff23b93f16536445254c857100a305ecd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JWAMCQKA64PMFRIAZWM5I4NYCT/bundle.json","state_url":"https://pith.science/pith/JWAMCQKA64PMFRIAZWM5I4NYCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JWAMCQKA64PMFRIAZWM5I4NYCT/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":"2026-08-12T10:34:11Z","links":{"resolver":"https://pith.science/pith/JWAMCQKA64PMFRIAZWM5I4NYCT","bundle":"https://pith.science/pith/JWAMCQKA64PMFRIAZWM5I4NYCT/bundle.json","state":"https://pith.science/pith/JWAMCQKA64PMFRIAZWM5I4NYCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JWAMCQKA64PMFRIAZWM5I4NYCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JWAMCQKA64PMFRIAZWM5I4NYCT","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":"13cecc8bfe7efedcdcd59dbc79cb760ee9cf78ce97960daa6d15acd97d058987","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:04:32Z","title_canon_sha256":"2c0267fc556844023210ba5f2788d1eaf97941c6b55df1eb9839092f7213ca53"},"schema_version":"1.0","source":{"id":"2412.10758","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10758","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10758v1","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10758","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_12","alias_value":"JWAMCQKA64PM","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_16","alias_value":"JWAMCQKA64PMFRIA","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_8","alias_value":"JWAMCQKA","created_at":"2026-07-05T09:49:21Z"}],"graph_snapshots":[{"event_id":"sha256:6b187c3e4d060193e056801102d4cd6ff23b93f16536445254c857100a305ecd","target":"graph","created_at":"2026-07-05T09:49:21Z","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/2412.10758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have emerged as key enablers for multimodal tasks, but their reliance on separate visual encoders introduces challenges in efficiency, scalability, and modality alignment. To address these limitations, we propose MUDAIF (Multimodal Unified Decoder with Adaptive Input Fusion), a decoder-only vision-language model that seamlessly integrates visual and textual inputs through a novel Vision-Token Adapter (VTA) and adaptive co-attention mechanism. By eliminating the need for a visual encoder, MUDAIF achieves enhanced efficiency, flexibility, and cross-modal understandi","authors_text":"Benjamin Tan, Brian Wong, Kaito Tanaka","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:04:32Z","title":"Optimizing Vision-Language Interactions Through Decoder-Only Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10758","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":"sha256:62ace7bbe63ddcea56f44552ecbd03851d1f3afc78f25aa6fa29d26bf8addd22","target":"record","created_at":"2026-07-05T09:49:21Z","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":"13cecc8bfe7efedcdcd59dbc79cb760ee9cf78ce97960daa6d15acd97d058987","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:04:32Z","title_canon_sha256":"2c0267fc556844023210ba5f2788d1eaf97941c6b55df1eb9839092f7213ca53"},"schema_version":"1.0","source":{"id":"2412.10758","kind":"arxiv","version":1}},"canonical_sha256":"4d80c14140f71ec2c500cd99d471b814c52455a985f39fd11a1b8d419d3c3b4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d80c14140f71ec2c500cd99d471b814c52455a985f39fd11a1b8d419d3c3b4b","first_computed_at":"2026-07-05T09:49:21.134474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:21.134474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7kH1uCH/MxEqb5FZs6qIYJJrsvGloXrou/PpqBTenQMgooK5tjOxKzSpUh7APg/GxbHb49u4c/9KmPUmc9A/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:21.134994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10758","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62ace7bbe63ddcea56f44552ecbd03851d1f3afc78f25aa6fa29d26bf8addd22","sha256:6b187c3e4d060193e056801102d4cd6ff23b93f16536445254c857100a305ecd"],"state_sha256":"c1d0e55fad77fa732cba65fe2463294cd9da2f7470ba8de789d59826c80141ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+HwsAnchNbgEScPqHA+KU5CIfSv9TVoYOXZWvvUsGyfTjsKIoOhd8SxEYELjRB1oSKwrbL/TQ4yCZJ1Jd4YDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T10:34:11.609958Z","bundle_sha256":"f1c048c88a47a05273c433d7e7cd97237a7ed021ed63bd30d13dd44fccfbeeeb"}}