{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ST72OZ27VVT6YN5Q7GI4TNQNWP","short_pith_number":"pith:ST72OZ27","schema_version":"1.0","canonical_sha256":"94ffa7675fad67ec37b0f991c9b60db3d7d59b5c85fd913127b89bc9ef44bc10","source":{"kind":"arxiv","id":"2605.13179","version":1},"attestation_state":"computed","paper":{"title":"Does Engram Do Memory Retrieval in Autoregressive Image Generation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The Engram module in autoregressive image generation acts as a gated side-pathway rather than a content-addressed memory retriever.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunbin Gu, Jinghao Wang, Pheng-Ann Heng, Qiyuan He","submitted_at":"2026-05-13T08:40:46Z","abstract_excerpt":"The Engram module -- a hash-keyed, O(1) associative memory injected into Transformer layers -- was recently shown to improve large language model pretraining, with the appealing interpretation that it provides a content-addressed shortcut to recurring local token patterns. We ask whether this interpretation transfers to autoregressive (AR) image generation, or whether the observed gains, if any, come from a different mechanism. We adapt the Engram module to vision with 2D spatial $n$-gram hashing, gated fusion, and KV-cache-compatible incremental inference, and inject it into a class-condition"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:40:46Z","cross_cats_sorted":[],"title_canon_sha256":"e9da8adc981aafb886a763f45d2312e71bb6b1248acf040732c3c48d6e592140","abstract_canon_sha256":"c5febe5cd2b72b0f2bf9fb9dcbaa6d7931bd6d335f183aa191ac84ac3bb5009a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:56.439978Z","signature_b64":"CuiXyIf5pVz9fACZSyOGiX7u6v+1jS6GxpL5iOQBSWGakW3brodXVGQ0ElLL3d7Spwy2BhoZwbhiO2zdRc0mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94ffa7675fad67ec37b0f991c9b60db3d7d59b5c85fd913127b89bc9ef44bc10","last_reissued_at":"2026-05-18T03:08:56.439157Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:56.439157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Engram Do Memory Retrieval in Autoregressive Image Generation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The Engram module in autoregressive image generation acts as a gated side-pathway rather than a content-addressed memory retriever.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunbin Gu, Jinghao Wang, Pheng-Ann Heng, Qiyuan He","submitted_at":"2026-05-13T08:40:46Z","abstract_excerpt":"The Engram module -- a hash-keyed, O(1) associative memory injected into Transformer layers -- was recently shown to improve large language model pretraining, with the appealing interpretation that it provides a content-addressed shortcut to recurring local token patterns. We ask whether this interpretation transfers to autoregressive (AR) image generation, or whether the observed gains, if any, come from a different mechanism. We adapt the Engram module to vision with 2D spatial $n$-gram hashing, gated fusion, and KV-cache-compatible incremental inference, and inject it into a class-condition"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"these findings indicate that the Engram in AR image generation behaves not as a content-addressed retriever but as a gated architectural side-pathway: a hash-keyed residual stream whose benefit is dominated by the pathway itself, with the learned table contributing only a small distributional refinement.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 2D spatial n-gram hashing and gated fusion adaptations faithfully preserve the original Engram mechanism while allowing fair comparison to the pure AR baseline; if these changes fundamentally alter how the module operates, the mechanistic conclusions would not hold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Engram in AR image generation saves backbone FLOPs but trails pure AR baselines in FID and behaves as a gated side-pathway rather than a content-addressed retriever.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The Engram module in autoregressive image generation acts as a gated side-pathway rather than a content-addressed memory retriever.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ff39da7fea8e52fea58fc5852193896870475734db8b8cc6738898dda385a8d6"},"source":{"id":"2605.13179","kind":"arxiv","version":1},"verdict":{"id":"a365a755-4d3b-4811-8a83-6e8a9cd168c5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:30:04.590990Z","strongest_claim":"these findings indicate that the Engram in AR image generation behaves not as a content-addressed retriever but as a gated architectural side-pathway: a hash-keyed residual stream whose benefit is dominated by the pathway itself, with the learned table contributing only a small distributional refinement.","one_line_summary":"Engram in AR image generation saves backbone FLOPs but trails pure AR baselines in FID and behaves as a gated side-pathway rather than a content-addressed retriever.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 2D spatial n-gram hashing and gated fusion adaptations faithfully preserve the original Engram mechanism while allowing fair comparison to the pure AR baseline; if these changes fundamentally alter how the module operates, the mechanistic conclusions would not hold.","pith_extraction_headline":"The Engram module in autoregressive image generation acts as a gated side-pathway rather than a content-addressed memory retriever."},"references":{"count":19,"sample":[{"doi":"","year":2022,"title":"Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, and William T. Freeman. Maskgit: Masked generative image transformer. InCVPR, 2022","work_id":"021352e7-6e83-4d54-9e3f-99bdf6ccabc2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","work_id":"942d7453-d7f7-4ad9-8180-e04bd226f6e5","ref_index":2,"cited_arxiv_id":"2601.07372","is_internal_anchor":true},{"doi":"","year":2009,"title":"Imagenet: A large-scale hierarchical image database","work_id":"a54af14a-31f5-43fe-bd58-cc2bbda964d7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Taming transformers for high-resolution image synthesis","work_id":"0f792ff9-97c6-4511-9b2d-b30263cfe7f1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Neural Turing Machines","work_id":"0a5ce53c-9670-42b9-8be5-386de7eed50c","ref_index":5,"cited_arxiv_id":"1410.5401","is_internal_anchor":true}],"resolved_work":19,"snapshot_sha256":"dbeee697967ff6b6284a778dc78a0e545b109b7d7060b70b94900d010ab37b2a","internal_anchors":4},"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":"2605.13179","created_at":"2026-05-18T03:08:56.439323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13179v1","created_at":"2026-05-18T03:08:56.439323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13179","created_at":"2026-05-18T03:08:56.439323+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST72OZ27VVT6","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST72OZ27VVT6YN5Q","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST72OZ27","created_at":"2026-05-18T12:33:37.589309+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/ST72OZ27VVT6YN5Q7GI4TNQNWP","json":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP.json","graph_json":"https://pith.science/api/pith-number/ST72OZ27VVT6YN5Q7GI4TNQNWP/graph.json","events_json":"https://pith.science/api/pith-number/ST72OZ27VVT6YN5Q7GI4TNQNWP/events.json","paper":"https://pith.science/paper/ST72OZ27"},"agent_actions":{"view_html":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP","download_json":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP.json","view_paper":"https://pith.science/paper/ST72OZ27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13179&json=true","fetch_graph":"https://pith.science/api/pith-number/ST72OZ27VVT6YN5Q7GI4TNQNWP/graph.json","fetch_events":"https://pith.science/api/pith-number/ST72OZ27VVT6YN5Q7GI4TNQNWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP/action/storage_attestation","attest_author":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP/action/author_attestation","sign_citation":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP/action/citation_signature","submit_replication":"https://pith.science/pith/ST72OZ27VVT6YN5Q7GI4TNQNWP/action/replication_record"}},"created_at":"2026-05-18T03:08:56.439323+00:00","updated_at":"2026-05-18T03:08:56.439323+00:00"}