{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JOWYC7KCYVPBXHB5FX4VDQYWAF","short_pith_number":"pith:JOWYC7KC","canonical_record":{"source":{"id":"2106.06998","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T13:54:02Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"b4e35fde61d6b3ae5f6541b48d74821cd7a408902dd0889b78084084aed0cf64","abstract_canon_sha256":"75aec6179d91e96c6d59ef58fada4eb8b5f123923d4d5a7ea6602a01871e4db0"},"schema_version":"1.0"},"canonical_sha256":"4bad817d42c55e1b9c3d2df951c31601634737f52e4ff2a2b3b45a5c966ae8f6","source":{"kind":"arxiv","id":"2106.06998","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06998","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06998v4","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06998","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"JOWYC7KCYVPB","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"JOWYC7KCYVPBXHB5","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"JOWYC7KC","created_at":"2026-06-23T03:14:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JOWYC7KCYVPBXHB5FX4VDQYWAF","target":"record","payload":{"canonical_record":{"source":{"id":"2106.06998","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T13:54:02Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"b4e35fde61d6b3ae5f6541b48d74821cd7a408902dd0889b78084084aed0cf64","abstract_canon_sha256":"75aec6179d91e96c6d59ef58fada4eb8b5f123923d4d5a7ea6602a01871e4db0"},"schema_version":"1.0"},"canonical_sha256":"4bad817d42c55e1b9c3d2df951c31601634737f52e4ff2a2b3b45a5c966ae8f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:26.642919Z","signature_b64":"kM9UgJjJP2R8o16j1RlqUcOQYyrdBrPXL/YCSFvr3P4s2ZqeJJkxZQuY50Sxe4mV1FDiLbq02R7T9eLa/d8KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bad817d42c55e1b9c3d2df951c31601634737f52e4ff2a2b3b45a5c966ae8f6","last_reissued_at":"2026-06-23T03:14:26.642402Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:26.642402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.06998","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:14:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kg9K6ly8OoId6DLVTeSzNPckKkxK7D/rTODdO4S9KJ/yfjSoicGtOUeTJl5tIB384CGUk97jSt9D+2TFxGiWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T03:46:56.539017Z"},"content_sha256":"a6becfae50b3ff6360dd59ad801b2d5bc095dea62bee9af310d1856e446703d3","schema_version":"1.0","event_id":"sha256:a6becfae50b3ff6360dd59ad801b2d5bc095dea62bee9af310d1856e446703d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JOWYC7KCYVPBXHB5FX4VDQYWAF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XConv: Low-memory stochastic backpropagation for convolutional layers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Ali Siahkoohi, Anirudh Thatipelli, Felix J. Herrmann, Jeffrey Sam, Mathias Louboutin, Rongrong Wang","submitted_at":"2021-06-13T13:54:02Z","abstract_excerpt":"Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation. Existing remedies (checkpointing, invertible architectures, or gradient-approximation methods such as randomized automatic differentiation) either add significant computation, impose architectural constraints, or require non-trivial code changes. We propose XConv, a near-drop-in replacement for standard 2D and 3D convolutional layers that addresses all three: it preserves standard backpropagation, imposes no architectural constraints, and inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06998","kind":"arxiv","version":4},"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/2106.06998/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":"2026-06-23T03:14:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDiCcL70/vjb0MWyGCBhiPijBHdETlS7nON+haRT2brcTLqOfgblrs814A5tFddy60PVaSIKuHbr6lt+zFyVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T03:46:56.539402Z"},"content_sha256":"748d62a35d4a3496c03b7b14b6137ae68bc4f681e37bfa0d9d65cf8c04ae0f65","schema_version":"1.0","event_id":"sha256:748d62a35d4a3496c03b7b14b6137ae68bc4f681e37bfa0d9d65cf8c04ae0f65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOWYC7KCYVPBXHB5FX4VDQYWAF/bundle.json","state_url":"https://pith.science/pith/JOWYC7KCYVPBXHB5FX4VDQYWAF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOWYC7KCYVPBXHB5FX4VDQYWAF/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":"2026-06-27T03:46:56Z","links":{"resolver":"https://pith.science/pith/JOWYC7KCYVPBXHB5FX4VDQYWAF","bundle":"https://pith.science/pith/JOWYC7KCYVPBXHB5FX4VDQYWAF/bundle.json","state":"https://pith.science/pith/JOWYC7KCYVPBXHB5FX4VDQYWAF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOWYC7KCYVPBXHB5FX4VDQYWAF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JOWYC7KCYVPBXHB5FX4VDQYWAF","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":"75aec6179d91e96c6d59ef58fada4eb8b5f123923d4d5a7ea6602a01871e4db0","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T13:54:02Z","title_canon_sha256":"b4e35fde61d6b3ae5f6541b48d74821cd7a408902dd0889b78084084aed0cf64"},"schema_version":"1.0","source":{"id":"2106.06998","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06998","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06998v4","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06998","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"JOWYC7KCYVPB","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"JOWYC7KCYVPBXHB5","created_at":"2026-06-23T03:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"JOWYC7KC","created_at":"2026-06-23T03:14:26Z"}],"graph_snapshots":[{"event_id":"sha256:748d62a35d4a3496c03b7b14b6137ae68bc4f681e37bfa0d9d65cf8c04ae0f65","target":"graph","created_at":"2026-06-23T03:14:26Z","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/2106.06998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation. Existing remedies (checkpointing, invertible architectures, or gradient-approximation methods such as randomized automatic differentiation) either add significant computation, impose architectural constraints, or require non-trivial code changes. We propose XConv, a near-drop-in replacement for standard 2D and 3D convolutional layers that addresses all three: it preserves standard backpropagation, imposes no architectural constraints, and inte","authors_text":"Ali Siahkoohi, Anirudh Thatipelli, Felix J. Herrmann, Jeffrey Sam, Mathias Louboutin, Rongrong Wang","cross_cats":["cs.NA","math.NA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T13:54:02Z","title":"XConv: Low-memory stochastic backpropagation for convolutional layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06998","kind":"arxiv","version":4},"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:a6becfae50b3ff6360dd59ad801b2d5bc095dea62bee9af310d1856e446703d3","target":"record","created_at":"2026-06-23T03:14:26Z","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":"75aec6179d91e96c6d59ef58fada4eb8b5f123923d4d5a7ea6602a01871e4db0","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T13:54:02Z","title_canon_sha256":"b4e35fde61d6b3ae5f6541b48d74821cd7a408902dd0889b78084084aed0cf64"},"schema_version":"1.0","source":{"id":"2106.06998","kind":"arxiv","version":4}},"canonical_sha256":"4bad817d42c55e1b9c3d2df951c31601634737f52e4ff2a2b3b45a5c966ae8f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bad817d42c55e1b9c3d2df951c31601634737f52e4ff2a2b3b45a5c966ae8f6","first_computed_at":"2026-06-23T03:14:26.642402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:26.642402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kM9UgJjJP2R8o16j1RlqUcOQYyrdBrPXL/YCSFvr3P4s2ZqeJJkxZQuY50Sxe4mV1FDiLbq02R7T9eLa/d8KDw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:26.642919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06998","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6becfae50b3ff6360dd59ad801b2d5bc095dea62bee9af310d1856e446703d3","sha256:748d62a35d4a3496c03b7b14b6137ae68bc4f681e37bfa0d9d65cf8c04ae0f65"],"state_sha256":"4574b72c37be4a120fec800fcbba34dc1fbeaacd1be6ef7e94b88197ca417f9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"krhJxxcmlkfYj0e0f9B7PLjAbRmj5mg3VO0q7VNlb87pal1ySGGGgcPJNbtW73HKHbl6ebckQe9D+egHZ7qbDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T03:46:56.541321Z","bundle_sha256":"c7951f1704088a3b2b7a57bb9344a13b507ed0ce76c01b6667bb95adbcdaa7e4"}}