{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X42MHDVBMBBIOUH7X4JRTSIP6F","short_pith_number":"pith:X42MHDVB","schema_version":"1.0","canonical_sha256":"bf34c38ea160428750ffbf1319c90ff17fc9013089da9f845fd775a096e3ccd8","source":{"kind":"arxiv","id":"2411.12663","version":1},"attestation_state":"computed","paper":{"title":"PoM: Efficient Image and Video Generation with the Polynomial Mixer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Picard, Nicolas Dufour","submitted_at":"2024-11-19T17:16:31Z","abstract_excerpt":"Diffusion models based on Multi-Head Attention (MHA) have become ubiquitous to generate high quality images and videos. However, encoding an image or a video as a sequence of patches results in costly attention patterns, as the requirements both in terms of memory and compute grow quadratically. To alleviate this problem, we propose a drop-in replacement for MHA called the Polynomial Mixer (PoM) that has the benefit of encoding the entire sequence into an explicit state. PoM has a linear complexity with respect to the number of tokens. This explicit state also allows us to generate frames in a"},"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":"2411.12663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-19T17:16:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a70adee538debe3d3531e1e7bf5face313e303e703118e0b3366fdd494b924e6","abstract_canon_sha256":"739a60d531d677a6ff4a84675148f85aad29cfbaa186d8b886e9b2fa2cbf1336"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:46.350830Z","signature_b64":"jG9UP/cg34pA1gHOoaBrULBwsIHHNsm7BYLw5qTeW9ZCGBFxqYDnfI+P75WzyeRJSZNTrqU0BWosnZyBXLbaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf34c38ea160428750ffbf1319c90ff17fc9013089da9f845fd775a096e3ccd8","last_reissued_at":"2026-07-05T09:37:46.350102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:46.350102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoM: Efficient Image and Video Generation with the Polynomial Mixer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Picard, Nicolas Dufour","submitted_at":"2024-11-19T17:16:31Z","abstract_excerpt":"Diffusion models based on Multi-Head Attention (MHA) have become ubiquitous to generate high quality images and videos. However, encoding an image or a video as a sequence of patches results in costly attention patterns, as the requirements both in terms of memory and compute grow quadratically. To alleviate this problem, we propose a drop-in replacement for MHA called the Polynomial Mixer (PoM) that has the benefit of encoding the entire sequence into an explicit state. PoM has a linear complexity with respect to the number of tokens. This explicit state also allows us to generate frames in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12663","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/2411.12663/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":"2411.12663","created_at":"2026-07-05T09:37:46.350213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12663v1","created_at":"2026-07-05T09:37:46.350213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12663","created_at":"2026-07-05T09:37:46.350213+00:00"},{"alias_kind":"pith_short_12","alias_value":"X42MHDVBMBBI","created_at":"2026-07-05T09:37:46.350213+00:00"},{"alias_kind":"pith_short_16","alias_value":"X42MHDVBMBBIOUH7","created_at":"2026-07-05T09:37:46.350213+00:00"},{"alias_kind":"pith_short_8","alias_value":"X42MHDVB","created_at":"2026-07-05T09:37:46.350213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F","json":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F.json","graph_json":"https://pith.science/api/pith-number/X42MHDVBMBBIOUH7X4JRTSIP6F/graph.json","events_json":"https://pith.science/api/pith-number/X42MHDVBMBBIOUH7X4JRTSIP6F/events.json","paper":"https://pith.science/paper/X42MHDVB"},"agent_actions":{"view_html":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F","download_json":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F.json","view_paper":"https://pith.science/paper/X42MHDVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12663&json=true","fetch_graph":"https://pith.science/api/pith-number/X42MHDVBMBBIOUH7X4JRTSIP6F/graph.json","fetch_events":"https://pith.science/api/pith-number/X42MHDVBMBBIOUH7X4JRTSIP6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F/action/storage_attestation","attest_author":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F/action/author_attestation","sign_citation":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F/action/citation_signature","submit_replication":"https://pith.science/pith/X42MHDVBMBBIOUH7X4JRTSIP6F/action/replication_record"}},"created_at":"2026-07-05T09:37:46.350213+00:00","updated_at":"2026-07-05T09:37:46.350213+00:00"}