{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VZDOUBHRT3HVZJQQTRVXH5ZAOL","short_pith_number":"pith:VZDOUBHR","canonical_record":{"source":{"id":"2605.19842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:37:53Z","cross_cats_sorted":[],"title_canon_sha256":"c2c843144fa85a29e8574128725a4ce699a65d620a3f99ede6ac29d09fdd9a1d","abstract_canon_sha256":"cccfeb5afb211e7450a4efb8efc8f1ef1511bf8bcf4fdd5942846608577dfd16"},"schema_version":"1.0"},"canonical_sha256":"ae46ea04f19ecf5ca6109c6b73f72072f0cdbefc56e6db738f70f6e22451844c","source":{"kind":"arxiv","id":"2605.19842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19842","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19842v1","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19842","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"VZDOUBHRT3HV","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"VZDOUBHRT3HVZJQQ","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"VZDOUBHR","created_at":"2026-05-20T01:06:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VZDOUBHRT3HVZJQQTRVXH5ZAOL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:37:53Z","cross_cats_sorted":[],"title_canon_sha256":"c2c843144fa85a29e8574128725a4ce699a65d620a3f99ede6ac29d09fdd9a1d","abstract_canon_sha256":"cccfeb5afb211e7450a4efb8efc8f1ef1511bf8bcf4fdd5942846608577dfd16"},"schema_version":"1.0"},"canonical_sha256":"ae46ea04f19ecf5ca6109c6b73f72072f0cdbefc56e6db738f70f6e22451844c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:17.187404Z","signature_b64":"vVvT2qb6x2uh5OzUCOe0P8t2NgsMzgShzRrmhzVpVMHn6Fhs3Io+ICTPeFD8IuzbxK5tRGNWtRm5clFFNlerAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae46ea04f19ecf5ca6109c6b73f72072f0cdbefc56e6db738f70f6e22451844c","last_reissued_at":"2026-05-20T01:06:17.186738Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:17.186738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19842","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":"2026-05-20T01:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uolGvPPiCyNcsS98VO24XpsmdqpoJs1N29Z41/SmhNPco9MksjmXd41qzbPJis3w/12AODgG7NsdvB7GV3HvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:17:08.425283Z"},"content_sha256":"20466c73af436a944b9b46104bb1a3db23f559103d0d79e201f284e08969569e","schema_version":"1.0","event_id":"sha256:20466c73af436a944b9b46104bb1a3db23f559103d0d79e201f284e08969569e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VZDOUBHRT3HVZJQQTRVXH5ZAOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Tensorization of Neural Networks via Slice-wise Feature Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rom\\'an Or\\'us, Safa Hamreras, Sukhbinder Singh","submitted_at":"2026-05-19T13:37:53Z","abstract_excerpt":"We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomposition methods that rely on costly global finetuning, our approach decomposes the network into slices consisting of either individual layers or blocks (e.g., convolutional layers or MLPs), or small groups of consecutive layers, and tensorizes each slice independently to reproduce the intermediate representations of the original pretrained model. This modular strategy improves accuracy recovery, reduces data requirements, and enables efficient "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19842","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/2605.19842/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":"2026-05-20T01:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dA3hyxUwrjUwTA6kWZxOqUER7NHpISty9t/giQW/FrpRSNpf+ymyXLQC0MXZ6A7JOazRrqoq1DKxf3f4RWQxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:17:08.426078Z"},"content_sha256":"960e9afa53d703da05f1dffd2ac16884dc775026af13b73e5a38a2d05b30657a","schema_version":"1.0","event_id":"sha256:960e9afa53d703da05f1dffd2ac16884dc775026af13b73e5a38a2d05b30657a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZDOUBHRT3HVZJQQTRVXH5ZAOL/bundle.json","state_url":"https://pith.science/pith/VZDOUBHRT3HVZJQQTRVXH5ZAOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZDOUBHRT3HVZJQQTRVXH5ZAOL/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":"2026-05-22T03:17:08Z","links":{"resolver":"https://pith.science/pith/VZDOUBHRT3HVZJQQTRVXH5ZAOL","bundle":"https://pith.science/pith/VZDOUBHRT3HVZJQQTRVXH5ZAOL/bundle.json","state":"https://pith.science/pith/VZDOUBHRT3HVZJQQTRVXH5ZAOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZDOUBHRT3HVZJQQTRVXH5ZAOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VZDOUBHRT3HVZJQQTRVXH5ZAOL","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":"cccfeb5afb211e7450a4efb8efc8f1ef1511bf8bcf4fdd5942846608577dfd16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:37:53Z","title_canon_sha256":"c2c843144fa85a29e8574128725a4ce699a65d620a3f99ede6ac29d09fdd9a1d"},"schema_version":"1.0","source":{"id":"2605.19842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19842","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19842v1","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19842","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"VZDOUBHRT3HV","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"VZDOUBHRT3HVZJQQ","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"VZDOUBHR","created_at":"2026-05-20T01:06:17Z"}],"graph_snapshots":[{"event_id":"sha256:960e9afa53d703da05f1dffd2ac16884dc775026af13b73e5a38a2d05b30657a","target":"graph","created_at":"2026-05-20T01:06:17Z","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/2605.19842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomposition methods that rely on costly global finetuning, our approach decomposes the network into slices consisting of either individual layers or blocks (e.g., convolutional layers or MLPs), or small groups of consecutive layers, and tensorizes each slice independently to reproduce the intermediate representations of the original pretrained model. This modular strategy improves accuracy recovery, reduces data requirements, and enables efficient ","authors_text":"Rom\\'an Or\\'us, Safa Hamreras, Sukhbinder Singh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:37:53Z","title":"Fast Tensorization of Neural Networks via Slice-wise Feature Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19842","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":"sha256:20466c73af436a944b9b46104bb1a3db23f559103d0d79e201f284e08969569e","target":"record","created_at":"2026-05-20T01:06:17Z","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":"cccfeb5afb211e7450a4efb8efc8f1ef1511bf8bcf4fdd5942846608577dfd16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:37:53Z","title_canon_sha256":"c2c843144fa85a29e8574128725a4ce699a65d620a3f99ede6ac29d09fdd9a1d"},"schema_version":"1.0","source":{"id":"2605.19842","kind":"arxiv","version":1}},"canonical_sha256":"ae46ea04f19ecf5ca6109c6b73f72072f0cdbefc56e6db738f70f6e22451844c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae46ea04f19ecf5ca6109c6b73f72072f0cdbefc56e6db738f70f6e22451844c","first_computed_at":"2026-05-20T01:06:17.186738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:17.186738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vVvT2qb6x2uh5OzUCOe0P8t2NgsMzgShzRrmhzVpVMHn6Fhs3Io+ICTPeFD8IuzbxK5tRGNWtRm5clFFNlerAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:17.187404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20466c73af436a944b9b46104bb1a3db23f559103d0d79e201f284e08969569e","sha256:960e9afa53d703da05f1dffd2ac16884dc775026af13b73e5a38a2d05b30657a"],"state_sha256":"5b4a5a1b5ca9b6312dd2c48f9085c22b8e247fc62681dac9a590f99d7379e0a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5eJgHWwvB0vV+0jaa8XHOpQthZnqHQDufWOVkFs1X2HUjH5hhWYD6NWc2upeZUUn26dpsV2Q4m13NHekze1BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T03:17:08.429456Z","bundle_sha256":"ad53cfe8389e237da53db6348899001d375505a56ec316ad595809d3750020d7"}}