{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KPSJ2UTK2Z3GAR5DX7KJDOGSEH","short_pith_number":"pith:KPSJ2UTK","canonical_record":{"source":{"id":"2009.10623","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-22T15:26:24Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"18c0383a082c3435514aa8352ead605b7ffa75448bd0d4236afa2e46b867991c","abstract_canon_sha256":"97f3d301236bafa9f140f439455c9a6ab0719543805570c0f9fe6b1a3ddbfa21"},"schema_version":"1.0"},"canonical_sha256":"53e49d526ad6766047a3bfd491b8d221f2c19c885f2fed850aab8083d53aa883","source":{"kind":"arxiv","id":"2009.10623","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10623","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10623v5","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10623","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"KPSJ2UTK2Z3G","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"KPSJ2UTK2Z3GAR5D","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"KPSJ2UTK","created_at":"2026-07-05T03:11:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KPSJ2UTK2Z3GAR5DX7KJDOGSEH","target":"record","payload":{"canonical_record":{"source":{"id":"2009.10623","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-22T15:26:24Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"18c0383a082c3435514aa8352ead605b7ffa75448bd0d4236afa2e46b867991c","abstract_canon_sha256":"97f3d301236bafa9f140f439455c9a6ab0719543805570c0f9fe6b1a3ddbfa21"},"schema_version":"1.0"},"canonical_sha256":"53e49d526ad6766047a3bfd491b8d221f2c19c885f2fed850aab8083d53aa883","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:25.967535Z","signature_b64":"d/uOthItvGzM2ZZL7mACT1o9ClBE3wEUSQPpM060Oo8zgxMH4+Aa7Hapb98ArxP14J/SQKaUUu97mj7FNAQOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e49d526ad6766047a3bfd491b8d221f2c19c885f2fed850aab8083d53aa883","last_reissued_at":"2026-07-05T03:11:25.967170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:25.967170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.10623","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VTd7ddFdNJUQUgTmvbN3bASrx2KiX8U9bb6sozq7a8HaZdXsvcehpwtXYUHafAeuduLLnyIhldx3u2tdl/xBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:26:47.713368Z"},"content_sha256":"f81a481b882622315da95b1c225907368a6070287718cc31cf23c608e247d95a","schema_version":"1.0","event_id":"sha256:f81a481b882622315da95b1c225907368a6070287718cc31cf23c608e247d95a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KPSJ2UTK2Z3GAR5DX7KJDOGSEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ferran Alet, Kenji Kawaguchi, Leslie Pack Kaelbling, Maria Bauza, Nurullah Giray Kuru, Tomas Lozano-Perez","submitted_at":"2020-09-22T15:26:24Z","abstract_excerpt":"From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations. However, since auxiliary losses are minimized only on training data, they suffer from the same generalization gap as regular task losses. Moreover, by adding a term to the loss function, the model optimizes a different objective than the one we care about. In this work we address both problems: first, we take "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10623","kind":"arxiv","version":5},"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/2009.10623/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":"2026-07-05T03:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPVn+oFSBynzFd87IlR9VPEXIXdwtFJhT2mc/11xobdG7zSHKk9HawONppkqxF0Lvord+YZDiYC5AqeOw6v5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:26:47.714271Z"},"content_sha256":"6dd874447c79cdb79cdae612a1ce1d16e1355890cc7c03cb8eb878942c68a8c1","schema_version":"1.0","event_id":"sha256:6dd874447c79cdb79cdae612a1ce1d16e1355890cc7c03cb8eb878942c68a8c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPSJ2UTK2Z3GAR5DX7KJDOGSEH/bundle.json","state_url":"https://pith.science/pith/KPSJ2UTK2Z3GAR5DX7KJDOGSEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPSJ2UTK2Z3GAR5DX7KJDOGSEH/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":"2026-08-12T16:26:47Z","links":{"resolver":"https://pith.science/pith/KPSJ2UTK2Z3GAR5DX7KJDOGSEH","bundle":"https://pith.science/pith/KPSJ2UTK2Z3GAR5DX7KJDOGSEH/bundle.json","state":"https://pith.science/pith/KPSJ2UTK2Z3GAR5DX7KJDOGSEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPSJ2UTK2Z3GAR5DX7KJDOGSEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KPSJ2UTK2Z3GAR5DX7KJDOGSEH","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":"97f3d301236bafa9f140f439455c9a6ab0719543805570c0f9fe6b1a3ddbfa21","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-22T15:26:24Z","title_canon_sha256":"18c0383a082c3435514aa8352ead605b7ffa75448bd0d4236afa2e46b867991c"},"schema_version":"1.0","source":{"id":"2009.10623","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10623","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10623v5","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10623","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"KPSJ2UTK2Z3G","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"KPSJ2UTK2Z3GAR5D","created_at":"2026-07-05T03:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"KPSJ2UTK","created_at":"2026-07-05T03:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:6dd874447c79cdb79cdae612a1ce1d16e1355890cc7c03cb8eb878942c68a8c1","target":"graph","created_at":"2026-07-05T03:11:25Z","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/2009.10623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations. However, since auxiliary losses are minimized only on training data, they suffer from the same generalization gap as regular task losses. Moreover, by adding a term to the loss function, the model optimizes a different objective than the one we care about. In this work we address both problems: first, we take ","authors_text":"Ferran Alet, Kenji Kawaguchi, Leslie Pack Kaelbling, Maria Bauza, Nurullah Giray Kuru, Tomas Lozano-Perez","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-22T15:26:24Z","title":"Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10623","kind":"arxiv","version":5},"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:f81a481b882622315da95b1c225907368a6070287718cc31cf23c608e247d95a","target":"record","created_at":"2026-07-05T03:11:25Z","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":"97f3d301236bafa9f140f439455c9a6ab0719543805570c0f9fe6b1a3ddbfa21","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-22T15:26:24Z","title_canon_sha256":"18c0383a082c3435514aa8352ead605b7ffa75448bd0d4236afa2e46b867991c"},"schema_version":"1.0","source":{"id":"2009.10623","kind":"arxiv","version":5}},"canonical_sha256":"53e49d526ad6766047a3bfd491b8d221f2c19c885f2fed850aab8083d53aa883","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e49d526ad6766047a3bfd491b8d221f2c19c885f2fed850aab8083d53aa883","first_computed_at":"2026-07-05T03:11:25.967170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:25.967170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d/uOthItvGzM2ZZL7mACT1o9ClBE3wEUSQPpM060Oo8zgxMH4+Aa7Hapb98ArxP14J/SQKaUUu97mj7FNAQOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:25.967535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.10623","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f81a481b882622315da95b1c225907368a6070287718cc31cf23c608e247d95a","sha256:6dd874447c79cdb79cdae612a1ce1d16e1355890cc7c03cb8eb878942c68a8c1"],"state_sha256":"d9439a85144ab937098c6badf9d6fee263c30678f1cfd44ece0592f9ca6eda82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ypWYneGU1migT2mmO5haLNdJ3zKx54zullcuAKSYMY100YJT3vsMoC/TeidQb2OLvW4WgdzoYg/8h74ZdF1CDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T16:26:47.741303Z","bundle_sha256":"3c4c4081de97b1f13cca8a8cd64ca35b9ba719a7d0837d5efa856bec9721b724"}}