{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:67Z3F5FZ67P44G2ARDW6VJHWBD","short_pith_number":"pith:67Z3F5FZ","canonical_record":{"source":{"id":"1801.00315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-31T16:53:12Z","cross_cats_sorted":["cond-mat.stat-mech","cond-mat.str-el","cs.LG"],"title_canon_sha256":"7e5bf72d0f6f1309d819adbf98e0dd9bdbcb47010e32a5276a341a6b3d18f499","abstract_canon_sha256":"6e5fc944b038a12340a561dc0dcac794d446ad77a897753a199f5de7d4d2bc68"},"schema_version":"1.0"},"canonical_sha256":"f7f3b2f4b9f7dfce1b4088edeaa4f608cf506057e71c6090d46862029f3996f5","source":{"kind":"arxiv","id":"1801.00315","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00315","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00315v1","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00315","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"67Z3F5FZ67P4","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"67Z3F5FZ67P44G2A","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"67Z3F5FZ","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:67Z3F5FZ67P44G2ARDW6VJHWBD","target":"record","payload":{"canonical_record":{"source":{"id":"1801.00315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-31T16:53:12Z","cross_cats_sorted":["cond-mat.stat-mech","cond-mat.str-el","cs.LG"],"title_canon_sha256":"7e5bf72d0f6f1309d819adbf98e0dd9bdbcb47010e32a5276a341a6b3d18f499","abstract_canon_sha256":"6e5fc944b038a12340a561dc0dcac794d446ad77a897753a199f5de7d4d2bc68"},"schema_version":"1.0"},"canonical_sha256":"f7f3b2f4b9f7dfce1b4088edeaa4f608cf506057e71c6090d46862029f3996f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:18.774449Z","signature_b64":"xLyX/C9XnTToteOpwN+wWcRN2DRmkQm5ZyiK2GKe4YguWWWpnUr4ObZ+EcjUe+grX70ngIeXGe8ujez2gVrrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7f3b2f4b9f7dfce1b4088edeaa4f608cf506057e71c6090d46862029f3996f5","last_reissued_at":"2026-05-18T00:17:18.773905Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:18.773905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.00315","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":"2026-05-18T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zG+viKnpLkvVU4yjMx4BjECR79n3g3aZHn7fhDKmEKQTp2g6Gm0GhHqxf0ng0p3Cb7SdlBEvK46DHhzuig97Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:28:41.316757Z"},"content_sha256":"b7d85ebc648eec9496ed8f2a6130f431d23e06ae2e6f5be31c7c2051d9159128","schema_version":"1.0","event_id":"sha256:b7d85ebc648eec9496ed8f2a6130f431d23e06ae2e6f5be31c7c2051d9159128"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:67Z3F5FZ67P44G2ARDW6VJHWBD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Relevant Features of Data with Multi-scale Tensor Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cond-mat.str-el","cs.LG"],"primary_cat":"stat.ML","authors_text":"E.M. Stoudenmire","submitted_at":"2017-12-31T16:53:12Z","abstract_excerpt":"Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion-MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00315","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":""},"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":"2026-05-18T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvU0P1XQQrk6oQSBiFE6MleTBI7AGQF4UW+nUVZp8ZNGrzxwCX0ZHTWWKbIR0tAKDCqP/ynGQyC9aXdbWs6sAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:28:41.317437Z"},"content_sha256":"5aa63ab72504b6c73d45be60e6ae42f9e25f2e7d5e83726684c0d4aea7472f40","schema_version":"1.0","event_id":"sha256:5aa63ab72504b6c73d45be60e6ae42f9e25f2e7d5e83726684c0d4aea7472f40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67Z3F5FZ67P44G2ARDW6VJHWBD/bundle.json","state_url":"https://pith.science/pith/67Z3F5FZ67P44G2ARDW6VJHWBD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67Z3F5FZ67P44G2ARDW6VJHWBD/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":"2026-05-25T22:28:41Z","links":{"resolver":"https://pith.science/pith/67Z3F5FZ67P44G2ARDW6VJHWBD","bundle":"https://pith.science/pith/67Z3F5FZ67P44G2ARDW6VJHWBD/bundle.json","state":"https://pith.science/pith/67Z3F5FZ67P44G2ARDW6VJHWBD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67Z3F5FZ67P44G2ARDW6VJHWBD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:67Z3F5FZ67P44G2ARDW6VJHWBD","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":"6e5fc944b038a12340a561dc0dcac794d446ad77a897753a199f5de7d4d2bc68","cross_cats_sorted":["cond-mat.stat-mech","cond-mat.str-el","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-31T16:53:12Z","title_canon_sha256":"7e5bf72d0f6f1309d819adbf98e0dd9bdbcb47010e32a5276a341a6b3d18f499"},"schema_version":"1.0","source":{"id":"1801.00315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00315","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00315v1","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00315","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"67Z3F5FZ67P4","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"67Z3F5FZ67P44G2A","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"67Z3F5FZ","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:5aa63ab72504b6c73d45be60e6ae42f9e25f2e7d5e83726684c0d4aea7472f40","target":"graph","created_at":"2026-05-18T00:17:18Z","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"},"paper":{"abstract_excerpt":"Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion-MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of","authors_text":"E.M. Stoudenmire","cross_cats":["cond-mat.stat-mech","cond-mat.str-el","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-31T16:53:12Z","title":"Learning Relevant Features of Data with Multi-scale Tensor Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00315","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:b7d85ebc648eec9496ed8f2a6130f431d23e06ae2e6f5be31c7c2051d9159128","target":"record","created_at":"2026-05-18T00:17:18Z","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":"6e5fc944b038a12340a561dc0dcac794d446ad77a897753a199f5de7d4d2bc68","cross_cats_sorted":["cond-mat.stat-mech","cond-mat.str-el","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-31T16:53:12Z","title_canon_sha256":"7e5bf72d0f6f1309d819adbf98e0dd9bdbcb47010e32a5276a341a6b3d18f499"},"schema_version":"1.0","source":{"id":"1801.00315","kind":"arxiv","version":1}},"canonical_sha256":"f7f3b2f4b9f7dfce1b4088edeaa4f608cf506057e71c6090d46862029f3996f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7f3b2f4b9f7dfce1b4088edeaa4f608cf506057e71c6090d46862029f3996f5","first_computed_at":"2026-05-18T00:17:18.773905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:18.773905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xLyX/C9XnTToteOpwN+wWcRN2DRmkQm5ZyiK2GKe4YguWWWpnUr4ObZ+EcjUe+grX70ngIeXGe8ujez2gVrrBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:18.774449Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.00315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7d85ebc648eec9496ed8f2a6130f431d23e06ae2e6f5be31c7c2051d9159128","sha256:5aa63ab72504b6c73d45be60e6ae42f9e25f2e7d5e83726684c0d4aea7472f40"],"state_sha256":"5b1145f01c68695101d404d8ffd2c4b769be94a6439da2e82412e6840542e1c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T1JkDSuFSvPaqMli/XaQq6TV5Zx+D5so+3sFApAglre/5ic50gsEci0yiTiybshP695qfJTFMvTea7G1jqqyBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:28:41.321207Z","bundle_sha256":"2db39d54bb5c97ea8bab11304393f88d17e427fca36a4d3532e74b974d345d04"}}