{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:26NRMAZN74IRZGO5AMTQ23OID5","short_pith_number":"pith:26NRMAZN","canonical_record":{"source":{"id":"1611.01714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-06T01:32:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7d52a8a7a931b4c28ce416895a61101ed6ba1f03bc9074f3b124f81bfd8b8f2b","abstract_canon_sha256":"7b354ddd1ee411b85ce046fe0d66e9bd401145a5a86ed5f17d6961db545237dd"},"schema_version":"1.0"},"canonical_sha256":"d79b16032dff111c99dd03270d6dc81f611cbf01b434e7ad91fc5cf89bfcb005","source":{"kind":"arxiv","id":"1611.01714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01714","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01714v1","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01714","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"26NRMAZN74IR","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"26NRMAZN74IRZGO5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"26NRMAZN","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:26NRMAZN74IRZGO5AMTQ23OID5","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-06T01:32:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7d52a8a7a931b4c28ce416895a61101ed6ba1f03bc9074f3b124f81bfd8b8f2b","abstract_canon_sha256":"7b354ddd1ee411b85ce046fe0d66e9bd401145a5a86ed5f17d6961db545237dd"},"schema_version":"1.0"},"canonical_sha256":"d79b16032dff111c99dd03270d6dc81f611cbf01b434e7ad91fc5cf89bfcb005","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:04.640277Z","signature_b64":"z9i7fIcTuEKNbXmslMbNRqDgQHmZBowfSNrvud50cUfllDhCtYzdAIkWZPCH7RAyxm1VlgTxEauBIr8kJbvgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79b16032dff111c99dd03270d6dc81f611cbf01b434e7ad91fc5cf89bfcb005","last_reissued_at":"2026-05-18T01:00:04.639632Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:04.639632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01714","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":"2026-05-18T01:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ieeOZ7LZntmOi+8nRQNBCfb3TkkETm6xYUdaAWD4F3Xy8hkvtlncNR02sZu5L3nQPo5Tg02FM2U3Zyiq9V79CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:23:20.260609Z"},"content_sha256":"3953a63a1b15b19ee50f24d9f51dfd85a6d2a55f328786bf2b2dbf879ec52fe8","schema_version":"1.0","event_id":"sha256:3953a63a1b15b19ee50f24d9f51dfd85a6d2a55f328786bf2b2dbf879ec52fe8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:26NRMAZN74IRZGO5AMTQ23OID5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Fine Tuning: A Modular Approach to Learning on Small Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ark Anderson, Artem Yankov, Court D. Corley, Kyle Shaffer, Nathan O. Hodas","submitted_at":"2016-11-06T01:32:39Z","abstract_excerpt":"In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural network or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01714","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":"2026-05-18T01:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+XPUgqEkI9wAqUh5Rsmho5WqH8rjf3HdRn1wdCfyLvNVYkX3toWK4f2tz0Rf3z5WM4j1SadV3QaBB9S3/Nx5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:23:20.261246Z"},"content_sha256":"f1269064fa15b366899efa00b793c88e71df0b0d4e427abe03399a3b5e019788","schema_version":"1.0","event_id":"sha256:f1269064fa15b366899efa00b793c88e71df0b0d4e427abe03399a3b5e019788"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26NRMAZN74IRZGO5AMTQ23OID5/bundle.json","state_url":"https://pith.science/pith/26NRMAZN74IRZGO5AMTQ23OID5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26NRMAZN74IRZGO5AMTQ23OID5/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":"2026-05-28T19:23:20Z","links":{"resolver":"https://pith.science/pith/26NRMAZN74IRZGO5AMTQ23OID5","bundle":"https://pith.science/pith/26NRMAZN74IRZGO5AMTQ23OID5/bundle.json","state":"https://pith.science/pith/26NRMAZN74IRZGO5AMTQ23OID5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26NRMAZN74IRZGO5AMTQ23OID5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:26NRMAZN74IRZGO5AMTQ23OID5","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":"7b354ddd1ee411b85ce046fe0d66e9bd401145a5a86ed5f17d6961db545237dd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-06T01:32:39Z","title_canon_sha256":"7d52a8a7a931b4c28ce416895a61101ed6ba1f03bc9074f3b124f81bfd8b8f2b"},"schema_version":"1.0","source":{"id":"1611.01714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01714","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01714v1","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01714","created_at":"2026-05-18T01:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"26NRMAZN74IR","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"26NRMAZN74IRZGO5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"26NRMAZN","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:f1269064fa15b366899efa00b793c88e71df0b0d4e427abe03399a3b5e019788","target":"graph","created_at":"2026-05-18T01:00:04Z","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":"In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural network or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as","authors_text":"Ark Anderson, Artem Yankov, Court D. Corley, Kyle Shaffer, Nathan O. Hodas","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-06T01:32:39Z","title":"Beyond Fine Tuning: A Modular Approach to Learning on Small Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01714","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":"sha256:3953a63a1b15b19ee50f24d9f51dfd85a6d2a55f328786bf2b2dbf879ec52fe8","target":"record","created_at":"2026-05-18T01:00:04Z","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":"7b354ddd1ee411b85ce046fe0d66e9bd401145a5a86ed5f17d6961db545237dd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-06T01:32:39Z","title_canon_sha256":"7d52a8a7a931b4c28ce416895a61101ed6ba1f03bc9074f3b124f81bfd8b8f2b"},"schema_version":"1.0","source":{"id":"1611.01714","kind":"arxiv","version":1}},"canonical_sha256":"d79b16032dff111c99dd03270d6dc81f611cbf01b434e7ad91fc5cf89bfcb005","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d79b16032dff111c99dd03270d6dc81f611cbf01b434e7ad91fc5cf89bfcb005","first_computed_at":"2026-05-18T01:00:04.639632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:04.639632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z9i7fIcTuEKNbXmslMbNRqDgQHmZBowfSNrvud50cUfllDhCtYzdAIkWZPCH7RAyxm1VlgTxEauBIr8kJbvgDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:04.640277Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3953a63a1b15b19ee50f24d9f51dfd85a6d2a55f328786bf2b2dbf879ec52fe8","sha256:f1269064fa15b366899efa00b793c88e71df0b0d4e427abe03399a3b5e019788"],"state_sha256":"8d76127fffe4c42c8338afc72fae719bad53d652090bd9cdf584cff527950567"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3dZKn0fID/ZIBrq7DfNNPGYLVwuomBgZBm0HlvpP+Q6VeawvxmmHc5XsZ0H7CMr+d8M8WAnJi02rQMVaMMmAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T19:23:20.264593Z","bundle_sha256":"af6d68da37d6c3ed067439c70aaa74d4fa1a0be4e071906295dc3ada7ad33d55"}}