{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DSTWCYB3KG2DT5MQPORVFF2QJB","short_pith_number":"pith:DSTWCYB3","canonical_record":{"source":{"id":"2606.23208","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T11:53:42Z","cross_cats_sorted":[],"title_canon_sha256":"ca72ecd532bb893c317707b31dbe7ca9c82d012a65d03678cdbc0452322e4603","abstract_canon_sha256":"16e9812bf8a683594111874379e6767cf33356d10be38a6e5170b4319bde22b2"},"schema_version":"1.0"},"canonical_sha256":"1ca761603b51b439f5907ba352975048629aa316a945c7081ad8f80f2b13b535","source":{"kind":"arxiv","id":"2606.23208","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23208","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23208v1","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23208","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"pith_short_12","alias_value":"DSTWCYB3KG2D","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"pith_short_16","alias_value":"DSTWCYB3KG2DT5MQ","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"pith_short_8","alias_value":"DSTWCYB3","created_at":"2026-06-23T03:14:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DSTWCYB3KG2DT5MQPORVFF2QJB","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23208","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T11:53:42Z","cross_cats_sorted":[],"title_canon_sha256":"ca72ecd532bb893c317707b31dbe7ca9c82d012a65d03678cdbc0452322e4603","abstract_canon_sha256":"16e9812bf8a683594111874379e6767cf33356d10be38a6e5170b4319bde22b2"},"schema_version":"1.0"},"canonical_sha256":"1ca761603b51b439f5907ba352975048629aa316a945c7081ad8f80f2b13b535","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:13.810259Z","signature_b64":"NGtkafRWy4l3ieeQJCM8XIH34SjcclHvh93YTuxumC5tUSu3fq8k0jTlh2E6PVkjq3fO+A/ewzAqlHpkxlsnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca761603b51b439f5907ba352975048629aa316a945c7081ad8f80f2b13b535","last_reissued_at":"2026-06-23T03:14:13.809860Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:13.809860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23208","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:14:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTFbryAzwAIfHaT5vG3rSSv8EVyujEaB0gQ9zcUC6J8kHCHXZWim55JLr62nrCWydrsmTBk5zjuAsSLuTfY7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T08:44:18.593920Z"},"content_sha256":"7c9cfa82cd821b838216ac296c377869a64bce4fbfc94546d25f7929d70a854f","schema_version":"1.0","event_id":"sha256:7c9cfa82cd821b838216ac296c377869a64bce4fbfc94546d25f7929d70a854f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DSTWCYB3KG2DT5MQPORVFF2QJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Leona Hennig, Marius Lindauer","submitted_at":"2026-06-22T11:53:42Z","abstract_excerpt":"Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep Shift Neural Networks (DSNNs) present a solution by leveraging shift operations to reduce computational complexity at inference. Compared to common DNNs, DSNNs are still less well understood and less well optimized. By leveraging AutoML techniques, we provide valuable insights into the potential of DSNNs and how to design them in a better way. We focus on image classification, a core task in computer "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23208","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/2606.23208/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":"2026-06-23T03:14:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mtEDmVebdea84cFLk3IHHSfCkoyGHvShscnuHbaGFR2xdQg/0ykUXP0FsWR+c9lAJcDQMw6dv7P1ijoDK8q7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T08:44:18.594299Z"},"content_sha256":"fdace15768c1251e032083231b8ce97595ea502094f91ef1e7026d39b58c7e95","schema_version":"1.0","event_id":"sha256:fdace15768c1251e032083231b8ce97595ea502094f91ef1e7026d39b58c7e95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSTWCYB3KG2DT5MQPORVFF2QJB/bundle.json","state_url":"https://pith.science/pith/DSTWCYB3KG2DT5MQPORVFF2QJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSTWCYB3KG2DT5MQPORVFF2QJB/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":"2026-06-25T08:44:18Z","links":{"resolver":"https://pith.science/pith/DSTWCYB3KG2DT5MQPORVFF2QJB","bundle":"https://pith.science/pith/DSTWCYB3KG2DT5MQPORVFF2QJB/bundle.json","state":"https://pith.science/pith/DSTWCYB3KG2DT5MQPORVFF2QJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSTWCYB3KG2DT5MQPORVFF2QJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DSTWCYB3KG2DT5MQPORVFF2QJB","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":"16e9812bf8a683594111874379e6767cf33356d10be38a6e5170b4319bde22b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T11:53:42Z","title_canon_sha256":"ca72ecd532bb893c317707b31dbe7ca9c82d012a65d03678cdbc0452322e4603"},"schema_version":"1.0","source":{"id":"2606.23208","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23208","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23208v1","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23208","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"pith_short_12","alias_value":"DSTWCYB3KG2D","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"pith_short_16","alias_value":"DSTWCYB3KG2DT5MQ","created_at":"2026-06-23T03:14:13Z"},{"alias_kind":"pith_short_8","alias_value":"DSTWCYB3","created_at":"2026-06-23T03:14:13Z"}],"graph_snapshots":[{"event_id":"sha256:fdace15768c1251e032083231b8ce97595ea502094f91ef1e7026d39b58c7e95","target":"graph","created_at":"2026-06-23T03:14:13Z","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/2606.23208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep Shift Neural Networks (DSNNs) present a solution by leveraging shift operations to reduce computational complexity at inference. Compared to common DNNs, DSNNs are still less well understood and less well optimized. By leveraging AutoML techniques, we provide valuable insights into the potential of DSNNs and how to design them in a better way. We focus on image classification, a core task in computer ","authors_text":"Leona Hennig, Marius Lindauer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T11:53:42Z","title":"Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23208","kind":"arxiv","version":1},"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":"sha256:7c9cfa82cd821b838216ac296c377869a64bce4fbfc94546d25f7929d70a854f","target":"record","created_at":"2026-06-23T03:14:13Z","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":"16e9812bf8a683594111874379e6767cf33356d10be38a6e5170b4319bde22b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T11:53:42Z","title_canon_sha256":"ca72ecd532bb893c317707b31dbe7ca9c82d012a65d03678cdbc0452322e4603"},"schema_version":"1.0","source":{"id":"2606.23208","kind":"arxiv","version":1}},"canonical_sha256":"1ca761603b51b439f5907ba352975048629aa316a945c7081ad8f80f2b13b535","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ca761603b51b439f5907ba352975048629aa316a945c7081ad8f80f2b13b535","first_computed_at":"2026-06-23T03:14:13.809860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:13.809860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NGtkafRWy4l3ieeQJCM8XIH34SjcclHvh93YTuxumC5tUSu3fq8k0jTlh2E6PVkjq3fO+A/ewzAqlHpkxlsnCw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:13.810259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23208","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c9cfa82cd821b838216ac296c377869a64bce4fbfc94546d25f7929d70a854f","sha256:fdace15768c1251e032083231b8ce97595ea502094f91ef1e7026d39b58c7e95"],"state_sha256":"222b03a95e4de9835d8593b0d71ac7543e8e63640e70e241b95cb741fd92f363"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1IMHlrT/Lfm8MUg8GdhYCbguN2zHpiY75t/ZoFdol7jEl0EriRgfpgfmGRz7d+czq9L+CBwiKxtw4+NSobpIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T08:44:18.596363Z","bundle_sha256":"e0b2d951175ed27b3595495dc795c844244ae32c9b5fe4014f4d8c9b0b4eec71"}}