{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2E6HAYERSR3PWGC3EIU2IGTD2U","short_pith_number":"pith:2E6HAYER","canonical_record":{"source":{"id":"2412.08781","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T21:23:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d248e554658e825c7cbae84c4ac20f432a86e120da26e522c93bd3b27c4f57a7","abstract_canon_sha256":"80e6416e4ee390b156bd842ea4f141b4c5c1b9572e86930d0ee64afba7b0bbba"},"schema_version":"1.0"},"canonical_sha256":"d13c7060919476fb185b2229a41a63d514dc5b0a3b1bb81cd6fa7bdbd7d09d13","source":{"kind":"arxiv","id":"2412.08781","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08781","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08781v2","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08781","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"2E6HAYERSR3P","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"2E6HAYERSR3PWGC3","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"2E6HAYER","created_at":"2026-07-05T10:13:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2E6HAYERSR3PWGC3EIU2IGTD2U","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08781","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T21:23:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d248e554658e825c7cbae84c4ac20f432a86e120da26e522c93bd3b27c4f57a7","abstract_canon_sha256":"80e6416e4ee390b156bd842ea4f141b4c5c1b9572e86930d0ee64afba7b0bbba"},"schema_version":"1.0"},"canonical_sha256":"d13c7060919476fb185b2229a41a63d514dc5b0a3b1bb81cd6fa7bdbd7d09d13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:06.430466Z","signature_b64":"bV/c2h6ndg0EpezxTOGRUraJY9tmq6F5iOu5T4JDg8yp0QWXaTdolgEyqyFf9RvLkbkRbzolQO9WCyYACVqqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d13c7060919476fb185b2229a41a63d514dc5b0a3b1bb81cd6fa7bdbd7d09d13","last_reissued_at":"2026-07-05T10:13:06.429971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:06.429971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08781","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":"2026-07-05T10:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6xpP8k+eaoJYjqdDbuU9w66Gz9NI3g9KynG4p9WC43WQL8kPQkCP34CKPtu63qbrcZpC3AjmweVlQTT7Zg54BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:22:04.146843Z"},"content_sha256":"6f82770235d272b2223e60db36d26508c18c0dac91207b931a534b2be6246136","schema_version":"1.0","event_id":"sha256:6f82770235d272b2223e60db36d26508c18c0dac91207b931a534b2be6246136"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2E6HAYERSR3PWGC3EIU2IGTD2U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Peng Sun, Tao Lin, Yi Tang, Zhenglin Cheng","submitted_at":"2024-12-11T21:23:24Z","abstract_excerpt":"Recent studies indicate that the denoising process in deep generative diffusion models implicitly learns and memorizes semantic information from the data distribution. These findings suggest that capturing more complex data distributions requires larger neural networks, leading to a substantial increase in computational demands, which in turn become the primary bottleneck in both training and inference of diffusion models. To this end, we introduce GMem: A Modular Approach for Ultra-Efficient Generative Models. Our approach GMem decouples the memory capacity from model and implements it as a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08781","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/2412.08781/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":"2026-07-05T10:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8TW4DYrFbVZXUtqL136ppFhRmtI8M5z46WLBILE1XBGT4yzIKE/37zgL+oGXTe9C+8VaHqrzNnjY/pjXFnUwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:22:04.147481Z"},"content_sha256":"d2b033bbae8e14e707d9ed24ed424f4422f2b99af4ce71e841279c593a5f9d41","schema_version":"1.0","event_id":"sha256:d2b033bbae8e14e707d9ed24ed424f4422f2b99af4ce71e841279c593a5f9d41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2E6HAYERSR3PWGC3EIU2IGTD2U/bundle.json","state_url":"https://pith.science/pith/2E6HAYERSR3PWGC3EIU2IGTD2U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2E6HAYERSR3PWGC3EIU2IGTD2U/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":"2026-08-12T06:22:04Z","links":{"resolver":"https://pith.science/pith/2E6HAYERSR3PWGC3EIU2IGTD2U","bundle":"https://pith.science/pith/2E6HAYERSR3PWGC3EIU2IGTD2U/bundle.json","state":"https://pith.science/pith/2E6HAYERSR3PWGC3EIU2IGTD2U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2E6HAYERSR3PWGC3EIU2IGTD2U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2E6HAYERSR3PWGC3EIU2IGTD2U","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":"80e6416e4ee390b156bd842ea4f141b4c5c1b9572e86930d0ee64afba7b0bbba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T21:23:24Z","title_canon_sha256":"d248e554658e825c7cbae84c4ac20f432a86e120da26e522c93bd3b27c4f57a7"},"schema_version":"1.0","source":{"id":"2412.08781","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08781","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08781v2","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08781","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"2E6HAYERSR3P","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"2E6HAYERSR3PWGC3","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"2E6HAYER","created_at":"2026-07-05T10:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:d2b033bbae8e14e707d9ed24ed424f4422f2b99af4ce71e841279c593a5f9d41","target":"graph","created_at":"2026-07-05T10:13:06Z","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/2412.08781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies indicate that the denoising process in deep generative diffusion models implicitly learns and memorizes semantic information from the data distribution. These findings suggest that capturing more complex data distributions requires larger neural networks, leading to a substantial increase in computational demands, which in turn become the primary bottleneck in both training and inference of diffusion models. To this end, we introduce GMem: A Modular Approach for Ultra-Efficient Generative Models. Our approach GMem decouples the memory capacity from model and implements it as a s","authors_text":"Peng Sun, Tao Lin, Yi Tang, Zhenglin Cheng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08781","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":"sha256:6f82770235d272b2223e60db36d26508c18c0dac91207b931a534b2be6246136","target":"record","created_at":"2026-07-05T10:13:06Z","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":"80e6416e4ee390b156bd842ea4f141b4c5c1b9572e86930d0ee64afba7b0bbba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T21:23:24Z","title_canon_sha256":"d248e554658e825c7cbae84c4ac20f432a86e120da26e522c93bd3b27c4f57a7"},"schema_version":"1.0","source":{"id":"2412.08781","kind":"arxiv","version":2}},"canonical_sha256":"d13c7060919476fb185b2229a41a63d514dc5b0a3b1bb81cd6fa7bdbd7d09d13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d13c7060919476fb185b2229a41a63d514dc5b0a3b1bb81cd6fa7bdbd7d09d13","first_computed_at":"2026-07-05T10:13:06.429971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:06.429971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bV/c2h6ndg0EpezxTOGRUraJY9tmq6F5iOu5T4JDg8yp0QWXaTdolgEyqyFf9RvLkbkRbzolQO9WCyYACVqqDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:06.430466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08781","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f82770235d272b2223e60db36d26508c18c0dac91207b931a534b2be6246136","sha256:d2b033bbae8e14e707d9ed24ed424f4422f2b99af4ce71e841279c593a5f9d41"],"state_sha256":"c956d8ffe90f0bcd703b966688c3cb8ddb1313f0f2ded2e910f684a71c4c8205"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fV8weQncv2dzCTmB0iJqI+y8r6k+cJbWWYK4ZxMOqJD9W86XjA4FBBpZW5uyQhLIvRB38rnR2CvVQ9r2sRA0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:22:04.152707Z","bundle_sha256":"74362efaae8ec0bf793ab7a363b5a599cb84ce0e0ed20a57e069ca7e2e9b3b0f"}}