{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HDXKGKBR42FMD4I2NT6GIP6FWX","short_pith_number":"pith:HDXKGKBR","canonical_record":{"source":{"id":"2507.12769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:01:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"05a164e7a0449389490d894894278c9856250202498accc61541c9faa531ce25","abstract_canon_sha256":"6a1b6e74a273fa5d9955dfde34105263a9c4214774ec094187f7e76e930f893c"},"schema_version":"1.0"},"canonical_sha256":"38eea32831e68ac1f11a6cfc643fc5b5e50cb86ac55d9221fee959a0fe185c99","source":{"kind":"arxiv","id":"2507.12769","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12769","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12769v1","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12769","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"HDXKGKBR42FM","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"HDXKGKBR42FMD4I2","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"HDXKGKBR","created_at":"2026-07-05T11:38:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HDXKGKBR42FMD4I2NT6GIP6FWX","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:01:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"05a164e7a0449389490d894894278c9856250202498accc61541c9faa531ce25","abstract_canon_sha256":"6a1b6e74a273fa5d9955dfde34105263a9c4214774ec094187f7e76e930f893c"},"schema_version":"1.0"},"canonical_sha256":"38eea32831e68ac1f11a6cfc643fc5b5e50cb86ac55d9221fee959a0fe185c99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:38.784802Z","signature_b64":"TDX1LRGX6wyMZUTpEHihSjUjiVMmz/+Mb+uT0RfpiuX7pkKjPFS3g5zeyNcHz6/p0cb3ptRhMQIGK9MguA/IBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38eea32831e68ac1f11a6cfc643fc5b5e50cb86ac55d9221fee959a0fe185c99","last_reissued_at":"2026-07-05T11:38:38.784296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:38.784296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12769","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":"2026-07-05T11:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/+LBvG+k3zd2bg72aDswZQ8hTbEXZMVkVD150ED0I/VvTaXCO8425DtM60fI8NNvOzPg3eVzMzQiDNYDGWUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:00:59.548815Z"},"content_sha256":"5592c399fb6a2f7702305f6cba7034d0cadd6f6f4234125b4691f5ebb2e029e5","schema_version":"1.0","event_id":"sha256:5592c399fb6a2f7702305f6cba7034d0cadd6f6f4234125b4691f5ebb2e029e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HDXKGKBR42FMD4I2NT6GIP6FWX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synergy: End-to-end Concept Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Keli Zheng, Zerong Xie","submitted_at":"2025-07-17T04:01:28Z","abstract_excerpt":"In this paper, we present Synergy, a language model that bridges different levels of abstraction in an end-to-end fashion through a learned routing mechanism. Focusing on low-level linguistic abstraction, we trained our model as a byte-level language model. Our model spontaneously learns to tokenize bytes, producing fewer concept tokens than Byte-level Byte Pair Encoder (BBPE) tokenizers while keeping comparable performance. By comparing with Llama3, we observed an advantage of Synergy under the same model scale and training dataset size. Further studies show that the middle part (the higher a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12769","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/2507.12769/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":"2026-07-05T11:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NPA/vIb2DWo6IFBq5LJbf0+xMbWAlEvnYUs72UD6aWeWwL+xS5UHZTlUB10uJHmu6uF1LSZUhnrKOaGToPyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:00:59.549336Z"},"content_sha256":"0ce268f3b10885dbb63e4fceec94cb24b7b1419f004d2fdc6e449a38f15948b5","schema_version":"1.0","event_id":"sha256:0ce268f3b10885dbb63e4fceec94cb24b7b1419f004d2fdc6e449a38f15948b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HDXKGKBR42FMD4I2NT6GIP6FWX/bundle.json","state_url":"https://pith.science/pith/HDXKGKBR42FMD4I2NT6GIP6FWX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HDXKGKBR42FMD4I2NT6GIP6FWX/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":"2026-08-06T20:00:59Z","links":{"resolver":"https://pith.science/pith/HDXKGKBR42FMD4I2NT6GIP6FWX","bundle":"https://pith.science/pith/HDXKGKBR42FMD4I2NT6GIP6FWX/bundle.json","state":"https://pith.science/pith/HDXKGKBR42FMD4I2NT6GIP6FWX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HDXKGKBR42FMD4I2NT6GIP6FWX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HDXKGKBR42FMD4I2NT6GIP6FWX","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":"6a1b6e74a273fa5d9955dfde34105263a9c4214774ec094187f7e76e930f893c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:01:28Z","title_canon_sha256":"05a164e7a0449389490d894894278c9856250202498accc61541c9faa531ce25"},"schema_version":"1.0","source":{"id":"2507.12769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12769","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12769v1","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12769","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"HDXKGKBR42FM","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"HDXKGKBR42FMD4I2","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"HDXKGKBR","created_at":"2026-07-05T11:38:38Z"}],"graph_snapshots":[{"event_id":"sha256:0ce268f3b10885dbb63e4fceec94cb24b7b1419f004d2fdc6e449a38f15948b5","target":"graph","created_at":"2026-07-05T11:38:38Z","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/2507.12769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present Synergy, a language model that bridges different levels of abstraction in an end-to-end fashion through a learned routing mechanism. Focusing on low-level linguistic abstraction, we trained our model as a byte-level language model. Our model spontaneously learns to tokenize bytes, producing fewer concept tokens than Byte-level Byte Pair Encoder (BBPE) tokenizers while keeping comparable performance. By comparing with Llama3, we observed an advantage of Synergy under the same model scale and training dataset size. Further studies show that the middle part (the higher a","authors_text":"Keli Zheng, Zerong Xie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:01:28Z","title":"Synergy: End-to-end Concept Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12769","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":"sha256:5592c399fb6a2f7702305f6cba7034d0cadd6f6f4234125b4691f5ebb2e029e5","target":"record","created_at":"2026-07-05T11:38:38Z","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":"6a1b6e74a273fa5d9955dfde34105263a9c4214774ec094187f7e76e930f893c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:01:28Z","title_canon_sha256":"05a164e7a0449389490d894894278c9856250202498accc61541c9faa531ce25"},"schema_version":"1.0","source":{"id":"2507.12769","kind":"arxiv","version":1}},"canonical_sha256":"38eea32831e68ac1f11a6cfc643fc5b5e50cb86ac55d9221fee959a0fe185c99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38eea32831e68ac1f11a6cfc643fc5b5e50cb86ac55d9221fee959a0fe185c99","first_computed_at":"2026-07-05T11:38:38.784296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:38.784296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TDX1LRGX6wyMZUTpEHihSjUjiVMmz/+Mb+uT0RfpiuX7pkKjPFS3g5zeyNcHz6/p0cb3ptRhMQIGK9MguA/IBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:38.784802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5592c399fb6a2f7702305f6cba7034d0cadd6f6f4234125b4691f5ebb2e029e5","sha256:0ce268f3b10885dbb63e4fceec94cb24b7b1419f004d2fdc6e449a38f15948b5"],"state_sha256":"876c0749c4790cdc1d93c7b46daff379aab54156900854c3784a4137c4e1e86b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTK5kY0BiZ/UFwoBp3U5p4pxR28hDPLLXaaZaE88hGGAgaaQ8ky6geHPxoc55JYZTfwvzHi3qmQt7ztlAMg8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:00:59.554980Z","bundle_sha256":"caa4207707bb35d274ae3837f5093c69ba2dffca0ff66d14c90d12d9a69a4b5b"}}