{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ACTK24V7Z7GJTJIM3FDK43NKVW","short_pith_number":"pith:ACTK24V7","canonical_record":{"source":{"id":"2505.14411","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T14:24:49Z","cross_cats_sorted":[],"title_canon_sha256":"86d2837d20a3f9ff7eade8fcdece0230eebbf81e4212acd95cac9055e54ca45e","abstract_canon_sha256":"76df1922a9e26496ca9ca1df3ebf4a4e1cc67f2e43b4ea6300030a02f8a34348"},"schema_version":"1.0"},"canonical_sha256":"00a6ad72bfcfcc99a50cd946ae6daaadab708e2058ac4433150af4b491fd970a","source":{"kind":"arxiv","id":"2505.14411","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14411","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14411v4","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14411","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"ACTK24V7Z7GJ","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"ACTK24V7Z7GJTJIM","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"ACTK24V7","created_at":"2026-06-02T02:04:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ACTK24V7Z7GJTJIM3FDK43NKVW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14411","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T14:24:49Z","cross_cats_sorted":[],"title_canon_sha256":"86d2837d20a3f9ff7eade8fcdece0230eebbf81e4212acd95cac9055e54ca45e","abstract_canon_sha256":"76df1922a9e26496ca9ca1df3ebf4a4e1cc67f2e43b4ea6300030a02f8a34348"},"schema_version":"1.0"},"canonical_sha256":"00a6ad72bfcfcc99a50cd946ae6daaadab708e2058ac4433150af4b491fd970a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:46.981433Z","signature_b64":"pWP8xkEOdC/EhXQHSq1XjCir9MRsaXxvy/4LBbRJT2SPM+60FGKh2s9mxHIWgqQSR9tcTQn9pQXmrImoMP5PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00a6ad72bfcfcc99a50cd946ae6daaadab708e2058ac4433150af4b491fd970a","last_reissued_at":"2026-06-02T02:04:46.980869Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:46.980869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14411","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9PZkOLf7NA4xOEDPLl+pRuoiQhvuzn1VVhZh2ajwt6K/LNT3sXvh7x/Jzl9gQIxhIcX488oNgQDwXoownn5wAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:17:23.450157Z"},"content_sha256":"757a079c51bf1b30352441173e71cbc03f9202965b2fbcba678dfa0174f8832d","schema_version":"1.0","event_id":"sha256:757a079c51bf1b30352441173e71cbc03f9202965b2fbcba678dfa0174f8832d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ACTK24V7Z7GJTJIM3FDK43NKVW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Byte Pair Encoding for Efficient Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Leon G\\\"otz, Leo Schwinn, Marcel Kollovieh, Stephan G\\\"unnemann","submitted_at":"2025-05-20T14:24:49Z","abstract_excerpt":"Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even simple patterns like extended constant values, resulting in substantial computational overhead. Inspired by the success of byte pair encoding, we propose the first pattern-centric tokenization scheme for time series analysis. Based on a discrete vocabulary of frequent motifs, our method merges samples with underlying patterns into tokens, compressing time series adaptively. Exploiting our finite set of motifs and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14411","kind":"arxiv","version":4},"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/2505.14411/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":"2026-06-02T02:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKgltpN7v1ZTxX0wm0bRVmilix1f4Y1XXtpMb87MJFvHIySi33UJzSUt8D9g9t7zoGcY/OpQ+Iheb4KW82c5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:17:23.450582Z"},"content_sha256":"a9aac169d047bbdad9ec28b5ef0b516c6003b3a57164dcf71ee9069026878968","schema_version":"1.0","event_id":"sha256:a9aac169d047bbdad9ec28b5ef0b516c6003b3a57164dcf71ee9069026878968"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACTK24V7Z7GJTJIM3FDK43NKVW/bundle.json","state_url":"https://pith.science/pith/ACTK24V7Z7GJTJIM3FDK43NKVW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACTK24V7Z7GJTJIM3FDK43NKVW/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":"2026-06-08T05:17:23Z","links":{"resolver":"https://pith.science/pith/ACTK24V7Z7GJTJIM3FDK43NKVW","bundle":"https://pith.science/pith/ACTK24V7Z7GJTJIM3FDK43NKVW/bundle.json","state":"https://pith.science/pith/ACTK24V7Z7GJTJIM3FDK43NKVW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACTK24V7Z7GJTJIM3FDK43NKVW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ACTK24V7Z7GJTJIM3FDK43NKVW","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":"76df1922a9e26496ca9ca1df3ebf4a4e1cc67f2e43b4ea6300030a02f8a34348","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T14:24:49Z","title_canon_sha256":"86d2837d20a3f9ff7eade8fcdece0230eebbf81e4212acd95cac9055e54ca45e"},"schema_version":"1.0","source":{"id":"2505.14411","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14411","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14411v4","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14411","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"ACTK24V7Z7GJ","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"ACTK24V7Z7GJTJIM","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"ACTK24V7","created_at":"2026-06-02T02:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:a9aac169d047bbdad9ec28b5ef0b516c6003b3a57164dcf71ee9069026878968","target":"graph","created_at":"2026-06-02T02:04:46Z","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/2505.14411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even simple patterns like extended constant values, resulting in substantial computational overhead. Inspired by the success of byte pair encoding, we propose the first pattern-centric tokenization scheme for time series analysis. Based on a discrete vocabulary of frequent motifs, our method merges samples with underlying patterns into tokens, compressing time series adaptively. Exploiting our finite set of motifs and the","authors_text":"Leon G\\\"otz, Leo Schwinn, Marcel Kollovieh, Stephan G\\\"unnemann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T14:24:49Z","title":"Byte Pair Encoding for Efficient Time Series Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14411","kind":"arxiv","version":4},"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":"sha256:757a079c51bf1b30352441173e71cbc03f9202965b2fbcba678dfa0174f8832d","target":"record","created_at":"2026-06-02T02:04:46Z","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":"76df1922a9e26496ca9ca1df3ebf4a4e1cc67f2e43b4ea6300030a02f8a34348","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T14:24:49Z","title_canon_sha256":"86d2837d20a3f9ff7eade8fcdece0230eebbf81e4212acd95cac9055e54ca45e"},"schema_version":"1.0","source":{"id":"2505.14411","kind":"arxiv","version":4}},"canonical_sha256":"00a6ad72bfcfcc99a50cd946ae6daaadab708e2058ac4433150af4b491fd970a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00a6ad72bfcfcc99a50cd946ae6daaadab708e2058ac4433150af4b491fd970a","first_computed_at":"2026-06-02T02:04:46.980869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:46.980869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pWP8xkEOdC/EhXQHSq1XjCir9MRsaXxvy/4LBbRJT2SPM+60FGKh2s9mxHIWgqQSR9tcTQn9pQXmrImoMP5PBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:46.981433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14411","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:757a079c51bf1b30352441173e71cbc03f9202965b2fbcba678dfa0174f8832d","sha256:a9aac169d047bbdad9ec28b5ef0b516c6003b3a57164dcf71ee9069026878968"],"state_sha256":"173650aeddd8f3626a980ca33f4bdc09ce31d3576f8fd38a380327123b2125ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGuOi4C6SJxYhjIaF7ezdcQWMP/+cyCVL/cRqixmJ1LqLIc49yTPknK3LV9W6czygLE2oenGtpc6jzBg7IALCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T05:17:23.452793Z","bundle_sha256":"5cdcc0a8e4183dd02e22e121eb6b1999c718239d5d5bd3d07197adbaebfcb201"}}