{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SSFVAIXJRV6LCHADFL7QO7C5TF","short_pith_number":"pith:SSFVAIXJ","canonical_record":{"source":{"id":"1705.07706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T13:14:11Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"309d6f7775abd0501ed1e28cd246adbc3ae61ef47975b61da5d490520ce8f3b1","abstract_canon_sha256":"ccf8210d113a21863afcb2fb97c1f218820d3d1092d598a1f350090396632662"},"schema_version":"1.0"},"canonical_sha256":"948b5022e98d7cb11c032aff077c5d9943ed2daae0ba81da11fdb72de11365c1","source":{"kind":"arxiv","id":"1705.07706","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07706","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07706v1","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07706","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"SSFVAIXJRV6L","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SSFVAIXJRV6LCHAD","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SSFVAIXJ","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SSFVAIXJRV6LCHADFL7QO7C5TF","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T13:14:11Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"309d6f7775abd0501ed1e28cd246adbc3ae61ef47975b61da5d490520ce8f3b1","abstract_canon_sha256":"ccf8210d113a21863afcb2fb97c1f218820d3d1092d598a1f350090396632662"},"schema_version":"1.0"},"canonical_sha256":"948b5022e98d7cb11c032aff077c5d9943ed2daae0ba81da11fdb72de11365c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:04.832873Z","signature_b64":"po7ZEqFdj8KMXqT2X/k066Uwgig+h0Gdm2OClt2fcYqLmXykmcFQ3+2LSdjaPZxwVAT2E7mHpzW0k0SBwHJ4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"948b5022e98d7cb11c032aff077c5d9943ed2daae0ba81da11fdb72de11365c1","last_reissued_at":"2026-05-18T00:44:04.832240Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:04.832240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07706","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":"2026-05-18T00:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YO+qPRegbYAGh9dCeQZmmjdRWVPPQ5AXsPkZo5WdsVfFeqnTNlaiHkIHtMGW73SKNpRIDRiOa2Fqx+nmUlGtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T04:07:44.686352Z"},"content_sha256":"e80768ab6d6b3fd0b54a758b427654ee9e4ff5a2a52851b05c57d7d997122441","schema_version":"1.0","event_id":"sha256:e80768ab6d6b3fd0b54a758b427654ee9e4ff5a2a52851b05c57d7d997122441"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SSFVAIXJRV6LCHADFL7QO7C5TF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Out-of-the-box Full-network Embedding for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Armand Vilalta, Dario Garcia-Gasulla, Eduard Ayguad\\'e, Ferran Par\\'es, Jesus Labarta, Jonatan Moreno, Toyotaro Suzumura, Ulises Cort\\'es","submitted_at":"2017-05-22T13:14:11Z","abstract_excerpt":"Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training is not an option. While previous contributions to feature extraction propose embeddings based on a single layer of the network, in this paper we propose a full-network embedding which successfully integrates convolutional and fully connected features, coming from all layers of a deep convolutional neural network. To do so, the embedding normalizes features "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07706","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":"2026-05-18T00:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R24TJ7UF/U1r9SRIypGdgZSR7cblocS3Tc/F+YBhKY/TmIf8tqeF70GbxVkJwppDepjdRALAS+gG7hjmMkbtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T04:07:44.686991Z"},"content_sha256":"128d48a02634e9400aff5fc8b90f04633bb191b72d25f01a2ac45ff4f5864b3f","schema_version":"1.0","event_id":"sha256:128d48a02634e9400aff5fc8b90f04633bb191b72d25f01a2ac45ff4f5864b3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SSFVAIXJRV6LCHADFL7QO7C5TF/bundle.json","state_url":"https://pith.science/pith/SSFVAIXJRV6LCHADFL7QO7C5TF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SSFVAIXJRV6LCHADFL7QO7C5TF/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":"2026-05-30T04:07:44Z","links":{"resolver":"https://pith.science/pith/SSFVAIXJRV6LCHADFL7QO7C5TF","bundle":"https://pith.science/pith/SSFVAIXJRV6LCHADFL7QO7C5TF/bundle.json","state":"https://pith.science/pith/SSFVAIXJRV6LCHADFL7QO7C5TF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SSFVAIXJRV6LCHADFL7QO7C5TF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SSFVAIXJRV6LCHADFL7QO7C5TF","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":"ccf8210d113a21863afcb2fb97c1f218820d3d1092d598a1f350090396632662","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T13:14:11Z","title_canon_sha256":"309d6f7775abd0501ed1e28cd246adbc3ae61ef47975b61da5d490520ce8f3b1"},"schema_version":"1.0","source":{"id":"1705.07706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07706","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07706v1","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07706","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"SSFVAIXJRV6L","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SSFVAIXJRV6LCHAD","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SSFVAIXJ","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:128d48a02634e9400aff5fc8b90f04633bb191b72d25f01a2ac45ff4f5864b3f","target":"graph","created_at":"2026-05-18T00:44:04Z","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":"Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training is not an option. While previous contributions to feature extraction propose embeddings based on a single layer of the network, in this paper we propose a full-network embedding which successfully integrates convolutional and fully connected features, coming from all layers of a deep convolutional neural network. To do so, the embedding normalizes features ","authors_text":"Armand Vilalta, Dario Garcia-Gasulla, Eduard Ayguad\\'e, Ferran Par\\'es, Jesus Labarta, Jonatan Moreno, Toyotaro Suzumura, Ulises Cort\\'es","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T13:14:11Z","title":"An Out-of-the-box Full-network Embedding for Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07706","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:e80768ab6d6b3fd0b54a758b427654ee9e4ff5a2a52851b05c57d7d997122441","target":"record","created_at":"2026-05-18T00:44:04Z","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":"ccf8210d113a21863afcb2fb97c1f218820d3d1092d598a1f350090396632662","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T13:14:11Z","title_canon_sha256":"309d6f7775abd0501ed1e28cd246adbc3ae61ef47975b61da5d490520ce8f3b1"},"schema_version":"1.0","source":{"id":"1705.07706","kind":"arxiv","version":1}},"canonical_sha256":"948b5022e98d7cb11c032aff077c5d9943ed2daae0ba81da11fdb72de11365c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"948b5022e98d7cb11c032aff077c5d9943ed2daae0ba81da11fdb72de11365c1","first_computed_at":"2026-05-18T00:44:04.832240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:04.832240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"po7ZEqFdj8KMXqT2X/k066Uwgig+h0Gdm2OClt2fcYqLmXykmcFQ3+2LSdjaPZxwVAT2E7mHpzW0k0SBwHJ4CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:04.832873Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e80768ab6d6b3fd0b54a758b427654ee9e4ff5a2a52851b05c57d7d997122441","sha256:128d48a02634e9400aff5fc8b90f04633bb191b72d25f01a2ac45ff4f5864b3f"],"state_sha256":"d1306f72acd6e390621b22b806be62d73ea3373fa14992a85a2234ca76c9d5f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YtRt9hFGzkgw/rlHc/G8FTs04dgTWMuRQg9jwJB4emEnuJR4D6jMiCQO4hGVzOy06dOyQKt5XIXNj+8pMXJNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T04:07:44.691083Z","bundle_sha256":"118b884cc1bb8cf86ffc0b43c641fff89a7372010fab617cf77754880dfd8919"}}