{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HDD6G3Q276LPRQCE6OS727O4U4","short_pith_number":"pith:HDD6G3Q2","canonical_record":{"source":{"id":"2503.21979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T20:50:38Z","cross_cats_sorted":[],"title_canon_sha256":"7028085c202708841c945b388e1cf6babd75c605e9798c5f0f3f71cf187f0352","abstract_canon_sha256":"b8cfb125576452fc1e7881a93981df0bb7c437450f6fcd734528ba53cd73721a"},"schema_version":"1.0"},"canonical_sha256":"38c7e36e1aff96f8c044f3a5fd7ddca718cd528c7df4576a5981b0354111fa3e","source":{"kind":"arxiv","id":"2503.21979","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21979","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21979v2","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21979","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"HDD6G3Q276LP","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"HDD6G3Q276LPRQCE","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"HDD6G3Q2","created_at":"2026-07-05T10:52:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HDD6G3Q276LPRQCE6OS727O4U4","target":"record","payload":{"canonical_record":{"source":{"id":"2503.21979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T20:50:38Z","cross_cats_sorted":[],"title_canon_sha256":"7028085c202708841c945b388e1cf6babd75c605e9798c5f0f3f71cf187f0352","abstract_canon_sha256":"b8cfb125576452fc1e7881a93981df0bb7c437450f6fcd734528ba53cd73721a"},"schema_version":"1.0"},"canonical_sha256":"38c7e36e1aff96f8c044f3a5fd7ddca718cd528c7df4576a5981b0354111fa3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:21.621535Z","signature_b64":"6zyEnfRPyhlil+HtFlHo25zh/HFBUNes1TtfFyo52y3pRgR3yKT/rcJsniV9WhOrAOXbdN9hhMqbxT2uMZdxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38c7e36e1aff96f8c044f3a5fd7ddca718cd528c7df4576a5981b0354111fa3e","last_reissued_at":"2026-07-05T10:52:21.621026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:21.621026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.21979","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":"2026-07-05T10:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6rEw4T+bVjhxCmjORZGO+O9w7zee0yLU8xgh/bGUTubs/ZT65Cwjz5CMP0MWEBXcjRlgJAnEnlO3tsb3kpK5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T16:58:36.182091Z"},"content_sha256":"e03eafe744ff2712e5e2f4cdf21c7a71843b1d4fa486b1a91a83b374607dd075","schema_version":"1.0","event_id":"sha256:e03eafe744ff2712e5e2f4cdf21c7a71843b1d4fa486b1a91a83b374607dd075"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HDD6G3Q276LPRQCE6OS727O4U4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Lumin Xu, Qingyi Tao, Sheng Jin, Size Wu, Wei Li, Wentao Liu, Wenwei Zhang, Zhonghua Wu","submitted_at":"2025-03-27T20:50:38Z","abstract_excerpt":"Unifying visual understanding and generation within a single multimodal framework remains a significant challenge, as the two inherently heterogeneous tasks require representations at different levels of granularity. Current approaches that utilize vector quantization (VQ) or variational autoencoders (VAE) for unified visual representation prioritize intrinsic imagery features over semantics, compromising understanding performance. In this work, we take inspiration from masked image modelling (MIM) that learns rich semantics via a mask-and-reconstruct pre-training and its successful extension "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21979","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/2503.21979/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":"2026-07-05T10:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pyz+aNqD/a0uftynNCNzUIqJH7EXeixAdRNfiyHGBTP3K/JgybNS36HQ/hTDHeqJ5h9OCriJa/lHf7W32tb4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T16:58:36.182566Z"},"content_sha256":"d097975e62a3ce1163637aaa353367555540a5c8f3a9b02368e552eae9b628b3","schema_version":"1.0","event_id":"sha256:d097975e62a3ce1163637aaa353367555540a5c8f3a9b02368e552eae9b628b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HDD6G3Q276LPRQCE6OS727O4U4/bundle.json","state_url":"https://pith.science/pith/HDD6G3Q276LPRQCE6OS727O4U4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HDD6G3Q276LPRQCE6OS727O4U4/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":"2026-08-02T16:58:36Z","links":{"resolver":"https://pith.science/pith/HDD6G3Q276LPRQCE6OS727O4U4","bundle":"https://pith.science/pith/HDD6G3Q276LPRQCE6OS727O4U4/bundle.json","state":"https://pith.science/pith/HDD6G3Q276LPRQCE6OS727O4U4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HDD6G3Q276LPRQCE6OS727O4U4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HDD6G3Q276LPRQCE6OS727O4U4","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":"b8cfb125576452fc1e7881a93981df0bb7c437450f6fcd734528ba53cd73721a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T20:50:38Z","title_canon_sha256":"7028085c202708841c945b388e1cf6babd75c605e9798c5f0f3f71cf187f0352"},"schema_version":"1.0","source":{"id":"2503.21979","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21979","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21979v2","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21979","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"HDD6G3Q276LP","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"HDD6G3Q276LPRQCE","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"HDD6G3Q2","created_at":"2026-07-05T10:52:21Z"}],"graph_snapshots":[{"event_id":"sha256:d097975e62a3ce1163637aaa353367555540a5c8f3a9b02368e552eae9b628b3","target":"graph","created_at":"2026-07-05T10:52:21Z","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/2503.21979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unifying visual understanding and generation within a single multimodal framework remains a significant challenge, as the two inherently heterogeneous tasks require representations at different levels of granularity. Current approaches that utilize vector quantization (VQ) or variational autoencoders (VAE) for unified visual representation prioritize intrinsic imagery features over semantics, compromising understanding performance. In this work, we take inspiration from masked image modelling (MIM) that learns rich semantics via a mask-and-reconstruct pre-training and its successful extension ","authors_text":"Chen Change Loy, Lumin Xu, Qingyi Tao, Sheng Jin, Size Wu, Wei Li, Wentao Liu, Wenwei Zhang, Zhonghua Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T20:50:38Z","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21979","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:e03eafe744ff2712e5e2f4cdf21c7a71843b1d4fa486b1a91a83b374607dd075","target":"record","created_at":"2026-07-05T10:52:21Z","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":"b8cfb125576452fc1e7881a93981df0bb7c437450f6fcd734528ba53cd73721a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T20:50:38Z","title_canon_sha256":"7028085c202708841c945b388e1cf6babd75c605e9798c5f0f3f71cf187f0352"},"schema_version":"1.0","source":{"id":"2503.21979","kind":"arxiv","version":2}},"canonical_sha256":"38c7e36e1aff96f8c044f3a5fd7ddca718cd528c7df4576a5981b0354111fa3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38c7e36e1aff96f8c044f3a5fd7ddca718cd528c7df4576a5981b0354111fa3e","first_computed_at":"2026-07-05T10:52:21.621026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:21.621026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6zyEnfRPyhlil+HtFlHo25zh/HFBUNes1TtfFyo52y3pRgR3yKT/rcJsniV9WhOrAOXbdN9hhMqbxT2uMZdxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:21.621535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21979","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e03eafe744ff2712e5e2f4cdf21c7a71843b1d4fa486b1a91a83b374607dd075","sha256:d097975e62a3ce1163637aaa353367555540a5c8f3a9b02368e552eae9b628b3"],"state_sha256":"888d160077c36bda7570055df5dde0c93e28f729a96f39760cb4a5ac1fb8c961"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GiRbA8WnEG9DGmB8dt8iYkFrdIlRBL/0xCY+Nwq1gtseOTwkCb9MSj0BFkPq8vZs74y2QgcqOGmO8c9IkXk1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T16:58:36.185512Z","bundle_sha256":"5a835b722c3baad180029cfe05dbfcfccfb2ae202b311b80e65ccf04f54f4820"}}