{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:6KZ7NCQA7KFPS6VMOOHVZHFFCP","short_pith_number":"pith:6KZ7NCQA","canonical_record":{"source":{"id":"1606.00611","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-02T10:37:46Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e98cdf3f8afe2b6a8816e3106b7190d6db140dde0004d41cb1ccf3c877b4a1c4","abstract_canon_sha256":"a612fa7518d2883adfd915e7ffbc5f34650ec01eef2774242df2d5ac4cc7a6ac"},"schema_version":"1.0"},"canonical_sha256":"f2b3f68a00fa8af97aac738f5c9ca513c04701ae3cdd75d31116529a679da0a0","source":{"kind":"arxiv","id":"1606.00611","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00611","created_at":"2026-05-18T00:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00611v2","created_at":"2026-05-18T00:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00611","created_at":"2026-05-18T00:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"6KZ7NCQA7KFP","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6KZ7NCQA7KFPS6VM","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6KZ7NCQA","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:6KZ7NCQA7KFPS6VMOOHVZHFFCP","target":"record","payload":{"canonical_record":{"source":{"id":"1606.00611","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-02T10:37:46Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e98cdf3f8afe2b6a8816e3106b7190d6db140dde0004d41cb1ccf3c877b4a1c4","abstract_canon_sha256":"a612fa7518d2883adfd915e7ffbc5f34650ec01eef2774242df2d5ac4cc7a6ac"},"schema_version":"1.0"},"canonical_sha256":"f2b3f68a00fa8af97aac738f5c9ca513c04701ae3cdd75d31116529a679da0a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:59.011108Z","signature_b64":"f9WlKhM6YRRptR60fAGlUlouYoxA9AzWMN2VHqrm01pAaCLT5igzzOYXruOglSzHrOjTBeeGX9orY/t5zv2MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2b3f68a00fa8af97aac738f5c9ca513c04701ae3cdd75d31116529a679da0a0","last_reissued_at":"2026-05-18T00:47:59.010623Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:59.010623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.00611","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":"2026-05-18T00:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"97y6yr861+s3DdBcNmGFOct7HjPtjWFdmOu9MQdUIgzfFqpIiwWGZMm5UCc1nn/5nfbl8SkoW9tqUIUvpBOJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:29:37.162419Z"},"content_sha256":"9c1f52b88a8b52eea2fdcdac533d768373eac79fa4b60042cd7534c7041f6b03","schema_version":"1.0","event_id":"sha256:9c1f52b88a8b52eea2fdcdac533d768373eac79fa4b60042cd7534c7041f6b03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:6KZ7NCQA7KFPS6VMOOHVZHFFCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Boris Knyazev, Erhardt Barth, Thomas Martinetz","submitted_at":"2016-06-02T10:37:46Z","abstract_excerpt":"In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adopted from physics, boosts existing unsupervised methods by learning more discriminative filters. We take well established convolutional neural networks and train their filters layer-wise. In addition, based on previous works we design a network which extracts more than 600k features per sample, but with the total number of trainable parameters greatly reduced by introducing shar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00611","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":""},"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":"2026-05-18T00:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yZOXR3DHD2TzqY/rvG4J/qdhkZgFiARKvuf90WSpqQ41CSKtxmbDXSpa4k6fNqFoI1efcD8v5SPAcL2LpQ9rDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:29:37.162984Z"},"content_sha256":"d167207ed9b27aab6ad0157ae94692ff28e4279edbdde9e6ad561a4eb2571339","schema_version":"1.0","event_id":"sha256:d167207ed9b27aab6ad0157ae94692ff28e4279edbdde9e6ad561a4eb2571339"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KZ7NCQA7KFPS6VMOOHVZHFFCP/bundle.json","state_url":"https://pith.science/pith/6KZ7NCQA7KFPS6VMOOHVZHFFCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KZ7NCQA7KFPS6VMOOHVZHFFCP/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":"2026-05-27T07:29:37Z","links":{"resolver":"https://pith.science/pith/6KZ7NCQA7KFPS6VMOOHVZHFFCP","bundle":"https://pith.science/pith/6KZ7NCQA7KFPS6VMOOHVZHFFCP/bundle.json","state":"https://pith.science/pith/6KZ7NCQA7KFPS6VMOOHVZHFFCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KZ7NCQA7KFPS6VMOOHVZHFFCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:6KZ7NCQA7KFPS6VMOOHVZHFFCP","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":"a612fa7518d2883adfd915e7ffbc5f34650ec01eef2774242df2d5ac4cc7a6ac","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-02T10:37:46Z","title_canon_sha256":"e98cdf3f8afe2b6a8816e3106b7190d6db140dde0004d41cb1ccf3c877b4a1c4"},"schema_version":"1.0","source":{"id":"1606.00611","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00611","created_at":"2026-05-18T00:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00611v2","created_at":"2026-05-18T00:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00611","created_at":"2026-05-18T00:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"6KZ7NCQA7KFP","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6KZ7NCQA7KFPS6VM","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6KZ7NCQA","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:d167207ed9b27aab6ad0157ae94692ff28e4279edbdde9e6ad561a4eb2571339","target":"graph","created_at":"2026-05-18T00:47:59Z","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":"In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adopted from physics, boosts existing unsupervised methods by learning more discriminative filters. We take well established convolutional neural networks and train their filters layer-wise. In addition, based on previous works we design a network which extracts more than 600k features per sample, but with the total number of trainable parameters greatly reduced by introducing shar","authors_text":"Boris Knyazev, Erhardt Barth, Thomas Martinetz","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-02T10:37:46Z","title":"Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00611","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":"sha256:9c1f52b88a8b52eea2fdcdac533d768373eac79fa4b60042cd7534c7041f6b03","target":"record","created_at":"2026-05-18T00:47:59Z","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":"a612fa7518d2883adfd915e7ffbc5f34650ec01eef2774242df2d5ac4cc7a6ac","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-02T10:37:46Z","title_canon_sha256":"e98cdf3f8afe2b6a8816e3106b7190d6db140dde0004d41cb1ccf3c877b4a1c4"},"schema_version":"1.0","source":{"id":"1606.00611","kind":"arxiv","version":2}},"canonical_sha256":"f2b3f68a00fa8af97aac738f5c9ca513c04701ae3cdd75d31116529a679da0a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2b3f68a00fa8af97aac738f5c9ca513c04701ae3cdd75d31116529a679da0a0","first_computed_at":"2026-05-18T00:47:59.010623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:59.010623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f9WlKhM6YRRptR60fAGlUlouYoxA9AzWMN2VHqrm01pAaCLT5igzzOYXruOglSzHrOjTBeeGX9orY/t5zv2MDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:59.011108Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.00611","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c1f52b88a8b52eea2fdcdac533d768373eac79fa4b60042cd7534c7041f6b03","sha256:d167207ed9b27aab6ad0157ae94692ff28e4279edbdde9e6ad561a4eb2571339"],"state_sha256":"f5f43b73c88bccd7b604fd36e058df3c7875b2a5e7ecab9281456e482bdeb712"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vNsO7q3fks78gTy1OMlXnT9rrF8xlgNOh/6Z9JAm7bmclgNpBhTiGc6Z4HQtPkGPB+YGcbtoV4Ovu1gpoUyAAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:29:37.166265Z","bundle_sha256":"7285795aa5596989f41c1e83357ace9d56d1a9770417d84f765d8a3878d4e63f"}}