{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BV4R4EYXUAUXSE2PHBGXQ544L3","short_pith_number":"pith:BV4R4EYX","canonical_record":{"source":{"id":"2402.15404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T16:06:38Z","cross_cats_sorted":[],"title_canon_sha256":"73a3ebeb0d67156efbb1579562fabdeda4d5dacddc92afc6cd3460babd4b9817","abstract_canon_sha256":"bb81b0f45d1c64dfcf53875ee7e39a09364307d90ae323bb4ade17424853fda5"},"schema_version":"1.0"},"canonical_sha256":"0d791e1317a02979134f384d78779c5ef570574de4532ed22fb2cc52493d3b87","source":{"kind":"arxiv","id":"2402.15404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15404","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15404v1","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15404","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"pith_short_12","alias_value":"BV4R4EYXUAUX","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"pith_short_16","alias_value":"BV4R4EYXUAUXSE2P","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"pith_short_8","alias_value":"BV4R4EYX","created_at":"2026-07-05T07:48:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BV4R4EYXUAUXSE2PHBGXQ544L3","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T16:06:38Z","cross_cats_sorted":[],"title_canon_sha256":"73a3ebeb0d67156efbb1579562fabdeda4d5dacddc92afc6cd3460babd4b9817","abstract_canon_sha256":"bb81b0f45d1c64dfcf53875ee7e39a09364307d90ae323bb4ade17424853fda5"},"schema_version":"1.0"},"canonical_sha256":"0d791e1317a02979134f384d78779c5ef570574de4532ed22fb2cc52493d3b87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:40.104247Z","signature_b64":"RcU2INlmAr8nZ5hOAjpevykTrTG9DapjH6ncq8Nc8tPw2DA1feTMZlzsPMsf5MFfPLyMDujwZTAhUbhcFCHCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d791e1317a02979134f384d78779c5ef570574de4532ed22fb2cc52493d3b87","last_reissued_at":"2026-07-05T07:48:40.103837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:40.103837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15404","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":"2026-07-05T07:48:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SBXt6V/YWAU0n7YJVmIJWN3NwvSM37nkGHvRlCLedZ9BhCLSAzh+J3wFCXHh7gsCMiHAe12GsQuzafAziRXxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:27:14.168534Z"},"content_sha256":"339143b51bd620720afa5d3ff083a2afe9d500e2de207e127e2b7b6e398a67cc","schema_version":"1.0","event_id":"sha256:339143b51bd620720afa5d3ff083a2afe9d500e2de207e127e2b7b6e398a67cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BV4R4EYXUAUXSE2PHBGXQ544L3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Steinmann, Devendra Singh Dhami, Felix Divo, Kristian Kersting, Maurice Kraus","submitted_at":"2024-02-23T16:06:38Z","abstract_excerpt":"In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target. Actually, common belief is that multi-dataset pretraining does not work for time series! Au contraire, we introduce a new self-supervised contrastive pretraining approach to learn one encoding from many unlabeled and diverse time series datasets, so that the single learned representation can then be reused in several target domains for, say, classification."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15404","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.15404/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":"2026-07-05T07:48:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YqPKo7Ha8hj+cR5OaQsJFLdIQ4n+HMmgakYHYvO/87EGDcxhAOtEw/xTKSHNzMwcw/E9o2OIICh6uw9RT7EgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:27:14.169470Z"},"content_sha256":"a6720ead53c88671b391cb9453ecbd9405f5e829ab9aff3d5f369371478ba921","schema_version":"1.0","event_id":"sha256:a6720ead53c88671b391cb9453ecbd9405f5e829ab9aff3d5f369371478ba921"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BV4R4EYXUAUXSE2PHBGXQ544L3/bundle.json","state_url":"https://pith.science/pith/BV4R4EYXUAUXSE2PHBGXQ544L3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BV4R4EYXUAUXSE2PHBGXQ544L3/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":"2026-08-17T23:27:14Z","links":{"resolver":"https://pith.science/pith/BV4R4EYXUAUXSE2PHBGXQ544L3","bundle":"https://pith.science/pith/BV4R4EYXUAUXSE2PHBGXQ544L3/bundle.json","state":"https://pith.science/pith/BV4R4EYXUAUXSE2PHBGXQ544L3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BV4R4EYXUAUXSE2PHBGXQ544L3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BV4R4EYXUAUXSE2PHBGXQ544L3","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":"bb81b0f45d1c64dfcf53875ee7e39a09364307d90ae323bb4ade17424853fda5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T16:06:38Z","title_canon_sha256":"73a3ebeb0d67156efbb1579562fabdeda4d5dacddc92afc6cd3460babd4b9817"},"schema_version":"1.0","source":{"id":"2402.15404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15404","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15404v1","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15404","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"pith_short_12","alias_value":"BV4R4EYXUAUX","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"pith_short_16","alias_value":"BV4R4EYXUAUXSE2P","created_at":"2026-07-05T07:48:40Z"},{"alias_kind":"pith_short_8","alias_value":"BV4R4EYX","created_at":"2026-07-05T07:48:40Z"}],"graph_snapshots":[{"event_id":"sha256:a6720ead53c88671b391cb9453ecbd9405f5e829ab9aff3d5f369371478ba921","target":"graph","created_at":"2026-07-05T07:48:40Z","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/2402.15404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target. Actually, common belief is that multi-dataset pretraining does not work for time series! Au contraire, we introduce a new self-supervised contrastive pretraining approach to learn one encoding from many unlabeled and diverse time series datasets, so that the single learned representation can then be reused in several target domains for, say, classification.","authors_text":"David Steinmann, Devendra Singh Dhami, Felix Divo, Kristian Kersting, Maurice Kraus","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T16:06:38Z","title":"United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15404","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":"sha256:339143b51bd620720afa5d3ff083a2afe9d500e2de207e127e2b7b6e398a67cc","target":"record","created_at":"2026-07-05T07:48:40Z","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":"bb81b0f45d1c64dfcf53875ee7e39a09364307d90ae323bb4ade17424853fda5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T16:06:38Z","title_canon_sha256":"73a3ebeb0d67156efbb1579562fabdeda4d5dacddc92afc6cd3460babd4b9817"},"schema_version":"1.0","source":{"id":"2402.15404","kind":"arxiv","version":1}},"canonical_sha256":"0d791e1317a02979134f384d78779c5ef570574de4532ed22fb2cc52493d3b87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d791e1317a02979134f384d78779c5ef570574de4532ed22fb2cc52493d3b87","first_computed_at":"2026-07-05T07:48:40.103837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:40.103837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RcU2INlmAr8nZ5hOAjpevykTrTG9DapjH6ncq8Nc8tPw2DA1feTMZlzsPMsf5MFfPLyMDujwZTAhUbhcFCHCAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:40.104247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:339143b51bd620720afa5d3ff083a2afe9d500e2de207e127e2b7b6e398a67cc","sha256:a6720ead53c88671b391cb9453ecbd9405f5e829ab9aff3d5f369371478ba921"],"state_sha256":"9c4887dc0dfcbec8bb0862c9c19aed2e21c23a9342e6be22656b66c4153ce09e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Utt0k9Xdn7wLbmo9/8td7IiEe637sjpcfVcNFOAV0cDIId7+g1czv6hbPHKmmxOx/CS6d8NfGMRM8v84RxZBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:27:14.234463Z","bundle_sha256":"506927cdcf32835a6488d0cc09f16f18dd09ab429b66babe9e3f395ea6bf8525"}}