{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RAPHY2FJMVC6AKMYWAUFFGJ5T7","short_pith_number":"pith:RAPHY2FJ","schema_version":"1.0","canonical_sha256":"881e7c68a96545e02998b02852993d9fdf54533181a60b9a82e6dfc83f1f6430","source":{"kind":"arxiv","id":"2405.15881","version":1},"attestation_state":"computed","paper":{"title":"Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Shentong Mo, Yapeng Tian","submitted_at":"2024-05-24T18:50:27Z","abstract_excerpt":"In recent developments, the Mamba architecture, known for its selective state space approach, has shown potential in the efficient modeling of long sequences. However, its application in image generation remains underexplored. Traditional diffusion transformers (DiT), which utilize self-attention blocks, are effective but their computational complexity scales quadratically with the input length, limiting their use for high-resolution images. To address this challenge, we introduce a novel diffusion architecture, Diffusion Mamba (DiM), which foregoes traditional attention mechanisms in favor of"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.15881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T18:50:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e8b5521e6244ccdce960a568e9b131e3c03db5a86b1b3e20b8c3684992448a62","abstract_canon_sha256":"5b67987b117a544b8d783a2c83942cb3b51c61526399defda729242f525f62ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:57.904652Z","signature_b64":"nt3PXjlSYBA1lQuMJHxlXxHONravYyI752WnsWlATi2ktZCyeh9084L6JduV2wrtTMJcE2bp6lUddkSrIkDfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"881e7c68a96545e02998b02852993d9fdf54533181a60b9a82e6dfc83f1f6430","last_reissued_at":"2026-07-05T08:22:57.904160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:57.904160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Shentong Mo, Yapeng Tian","submitted_at":"2024-05-24T18:50:27Z","abstract_excerpt":"In recent developments, the Mamba architecture, known for its selective state space approach, has shown potential in the efficient modeling of long sequences. However, its application in image generation remains underexplored. Traditional diffusion transformers (DiT), which utilize self-attention blocks, are effective but their computational complexity scales quadratically with the input length, limiting their use for high-resolution images. To address this challenge, we introduce a novel diffusion architecture, Diffusion Mamba (DiM), which foregoes traditional attention mechanisms in favor of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15881","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/2405.15881/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.15881","created_at":"2026-07-05T08:22:57.904217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15881v1","created_at":"2026-07-05T08:22:57.904217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15881","created_at":"2026-07-05T08:22:57.904217+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAPHY2FJMVC6","created_at":"2026-07-05T08:22:57.904217+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAPHY2FJMVC6AKMY","created_at":"2026-07-05T08:22:57.904217+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAPHY2FJ","created_at":"2026-07-05T08:22:57.904217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7","json":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7.json","graph_json":"https://pith.science/api/pith-number/RAPHY2FJMVC6AKMYWAUFFGJ5T7/graph.json","events_json":"https://pith.science/api/pith-number/RAPHY2FJMVC6AKMYWAUFFGJ5T7/events.json","paper":"https://pith.science/paper/RAPHY2FJ"},"agent_actions":{"view_html":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7","download_json":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7.json","view_paper":"https://pith.science/paper/RAPHY2FJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15881&json=true","fetch_graph":"https://pith.science/api/pith-number/RAPHY2FJMVC6AKMYWAUFFGJ5T7/graph.json","fetch_events":"https://pith.science/api/pith-number/RAPHY2FJMVC6AKMYWAUFFGJ5T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7/action/storage_attestation","attest_author":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7/action/author_attestation","sign_citation":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7/action/citation_signature","submit_replication":"https://pith.science/pith/RAPHY2FJMVC6AKMYWAUFFGJ5T7/action/replication_record"}},"created_at":"2026-07-05T08:22:57.904217+00:00","updated_at":"2026-07-05T08:22:57.904217+00:00"}