{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RM735OMOAQRNEVJQHAMSHGTEWU","short_pith_number":"pith:RM735OMO","canonical_record":{"source":{"id":"2607.02516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"a63299cf659522d0ed195eabbc03f27a1d2a5d55acebf4ee472f5558bdb9d24e","abstract_canon_sha256":"16e8723d8d74cefc4b1fc2b2ce058e964a3692b8e4e324e50e78439195862bc5"},"schema_version":"1.0"},"canonical_sha256":"8b3fbeb98e0422d255303819239a64b53fd855d197dbba3c31fd3249e73dcb61","source":{"kind":"arxiv","id":"2607.02516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02516","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02516v1","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02516","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"RM735OMOAQRN","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"RM735OMOAQRNEVJQ","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"RM735OMO","created_at":"2026-07-03T01:18:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RM735OMOAQRNEVJQHAMSHGTEWU","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"a63299cf659522d0ed195eabbc03f27a1d2a5d55acebf4ee472f5558bdb9d24e","abstract_canon_sha256":"16e8723d8d74cefc4b1fc2b2ce058e964a3692b8e4e324e50e78439195862bc5"},"schema_version":"1.0"},"canonical_sha256":"8b3fbeb98e0422d255303819239a64b53fd855d197dbba3c31fd3249e73dcb61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:18:01.642988Z","signature_b64":"HlsK+vbhXtclglPg8LovrCoDvJzOh72H+2TMADWNhLGIw37x5Jxi7mJM7yiktPz1DFs3fPm/iztIFW7pDk27Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3fbeb98e0422d255303819239a64b53fd855d197dbba3c31fd3249e73dcb61","last_reissued_at":"2026-07-03T01:18:01.642623Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:18:01.642623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02516","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":"2026-07-03T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kwHP4Awi00PXmjziI/A4vwSXKtu6DFyOJkMLQKW1Bpib0brNYU7N4OPEO0WSBWN3EsCDV12eH3UhCMg/9E/RBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T23:27:35.937583Z"},"content_sha256":"0950bdd82abae623de37a7916a2453b5a064610c605c163aab90fb9517ac2e8f","schema_version":"1.0","event_id":"sha256:0950bdd82abae623de37a7916a2453b5a064610c605c163aab90fb9517ac2e8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RM735OMOAQRNEVJQHAMSHGTEWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Alignment Is All You Need For X-to-4D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kehan Li, Qiaowei Miao, Yawei Luo, Yi Yang","submitted_at":"2026-07-02T17:59:57Z","abstract_excerpt":"Generative diffusion models excel at synthesizing high-quality images, videos, and 3D content under multimodal control. However, arbitrary user-defined modality-to-4D (X-to-4D) generation remains challenging due to the high cost of constructing diverse datasets and the limited scalability of existing methods. This paper presents Align4D, a flexible framework that translates any-modal input into coherent video-3D pairs, using video to guide 4D motion and 3D data to shape 4D geometry. Align4D introduces three key techniques: (1) Object Distance Alignment, which searches Video-Aligned and Multivi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02516","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/2607.02516/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":"2026-07-03T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDlDGj02wuI9vSGVgKYWLlJbsaFyDGTb8Gq6Ssv4nyrNk4NmT8cV2SXjuWRTdMrA/T9VLgtrh3UxynL5JZXfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T23:27:35.937947Z"},"content_sha256":"0fd150695fda7b2bfc23b83d5292ff6d90e79e3a0ad0857ecd3a6c0676af5a6f","schema_version":"1.0","event_id":"sha256:0fd150695fda7b2bfc23b83d5292ff6d90e79e3a0ad0857ecd3a6c0676af5a6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RM735OMOAQRNEVJQHAMSHGTEWU/bundle.json","state_url":"https://pith.science/pith/RM735OMOAQRNEVJQHAMSHGTEWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RM735OMOAQRNEVJQHAMSHGTEWU/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":"2026-07-03T23:27:35Z","links":{"resolver":"https://pith.science/pith/RM735OMOAQRNEVJQHAMSHGTEWU","bundle":"https://pith.science/pith/RM735OMOAQRNEVJQHAMSHGTEWU/bundle.json","state":"https://pith.science/pith/RM735OMOAQRNEVJQHAMSHGTEWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RM735OMOAQRNEVJQHAMSHGTEWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RM735OMOAQRNEVJQHAMSHGTEWU","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":"16e8723d8d74cefc4b1fc2b2ce058e964a3692b8e4e324e50e78439195862bc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:59:57Z","title_canon_sha256":"a63299cf659522d0ed195eabbc03f27a1d2a5d55acebf4ee472f5558bdb9d24e"},"schema_version":"1.0","source":{"id":"2607.02516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02516","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02516v1","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02516","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"RM735OMOAQRN","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"RM735OMOAQRNEVJQ","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"RM735OMO","created_at":"2026-07-03T01:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:0fd150695fda7b2bfc23b83d5292ff6d90e79e3a0ad0857ecd3a6c0676af5a6f","target":"graph","created_at":"2026-07-03T01:18:01Z","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/2607.02516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative diffusion models excel at synthesizing high-quality images, videos, and 3D content under multimodal control. However, arbitrary user-defined modality-to-4D (X-to-4D) generation remains challenging due to the high cost of constructing diverse datasets and the limited scalability of existing methods. This paper presents Align4D, a flexible framework that translates any-modal input into coherent video-3D pairs, using video to guide 4D motion and 3D data to shape 4D geometry. Align4D introduces three key techniques: (1) Object Distance Alignment, which searches Video-Aligned and Multivi","authors_text":"Kehan Li, Qiaowei Miao, Yawei Luo, Yi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:59:57Z","title":"Alignment Is All You Need For X-to-4D Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02516","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":"sha256:0950bdd82abae623de37a7916a2453b5a064610c605c163aab90fb9517ac2e8f","target":"record","created_at":"2026-07-03T01:18:01Z","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":"16e8723d8d74cefc4b1fc2b2ce058e964a3692b8e4e324e50e78439195862bc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:59:57Z","title_canon_sha256":"a63299cf659522d0ed195eabbc03f27a1d2a5d55acebf4ee472f5558bdb9d24e"},"schema_version":"1.0","source":{"id":"2607.02516","kind":"arxiv","version":1}},"canonical_sha256":"8b3fbeb98e0422d255303819239a64b53fd855d197dbba3c31fd3249e73dcb61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b3fbeb98e0422d255303819239a64b53fd855d197dbba3c31fd3249e73dcb61","first_computed_at":"2026-07-03T01:18:01.642623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:18:01.642623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HlsK+vbhXtclglPg8LovrCoDvJzOh72H+2TMADWNhLGIw37x5Jxi7mJM7yiktPz1DFs3fPm/iztIFW7pDk27Dg==","signature_status":"signed_v1","signed_at":"2026-07-03T01:18:01.642988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0950bdd82abae623de37a7916a2453b5a064610c605c163aab90fb9517ac2e8f","sha256:0fd150695fda7b2bfc23b83d5292ff6d90e79e3a0ad0857ecd3a6c0676af5a6f"],"state_sha256":"f0624d77ed4a44adbca35bc9a18b0b35ff2c0664c9deb7a9284485d7bec88a6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g4ogXRBfBaFPZYRjQgydj28qtQeEg3ZvAE2boh/kRkz+3FgBnxiQlwZlCUK56xPZipLtbEcr+b5GEYDsnaEUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T23:27:35.939987Z","bundle_sha256":"acc1c2af18e22636afa42fb13c8417bd5d327c762e35ab14fc21db114fb83a8d"}}