{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZBPKTNYWJH3DYKH24ORCUOLQKW","short_pith_number":"pith:ZBPKTNYW","canonical_record":{"source":{"id":"2504.09818","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T02:39:26Z","cross_cats_sorted":[],"title_canon_sha256":"fbb0de8573a2065157c5613e3622fe65043017a274aabd6c875de530ef3fee59","abstract_canon_sha256":"a66b95bf5a5b6fbefb5d64a5a243ea638d4f5b85e34716dd468af72b6ba0e571"},"schema_version":"1.0"},"canonical_sha256":"c85ea9b71649f63c28fae3a22a397055aa2679993b8d6e0e905aa6c744e4bf63","source":{"kind":"arxiv","id":"2504.09818","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09818","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09818v2","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09818","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZBPKTNYWJH3D","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZBPKTNYWJH3DYKH2","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZBPKTNYW","created_at":"2026-07-05T10:53:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZBPKTNYWJH3DYKH24ORCUOLQKW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09818","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T02:39:26Z","cross_cats_sorted":[],"title_canon_sha256":"fbb0de8573a2065157c5613e3622fe65043017a274aabd6c875de530ef3fee59","abstract_canon_sha256":"a66b95bf5a5b6fbefb5d64a5a243ea638d4f5b85e34716dd468af72b6ba0e571"},"schema_version":"1.0"},"canonical_sha256":"c85ea9b71649f63c28fae3a22a397055aa2679993b8d6e0e905aa6c744e4bf63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:17.140850Z","signature_b64":"K7+9EymNztn23ujZVwdOBC1yn95zE7lQxx6DMjt26K7QWreVtQlJHDx0aPHdpYvMTPuTD9nI3qMW9iWwyz6gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c85ea9b71649f63c28fae3a22a397055aa2679993b8d6e0e905aa6c744e4bf63","last_reissued_at":"2026-07-05T10:53:17.140291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:17.140291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09818","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:53:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"joOr6vR92vZ9rSFAfcsBjsktydPMbkvva8JrQrUqXnKOBAMFLjlXswc+gpgmYs7iXTfyYd3uQeJ+AHplUol5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:26:28.674372Z"},"content_sha256":"8091b44a5ec57cf75e7458af6278bb84bd300ab2f77be4a4a8dce987ce39695d","schema_version":"1.0","event_id":"sha256:8091b44a5ec57cf75e7458af6278bb84bd300ab2f77be4a4a8dce987ce39695d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZBPKTNYWJH3DYKH24ORCUOLQKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transferable text data distillation by trajectory matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fanyi Du, Hailin Hu, Hanting Chen, Kai Han, Rong Yao, Wenyi Fang, Yifei Fu, Yunhe Wang","submitted_at":"2025-04-14T02:39:26Z","abstract_excerpt":"In the realm of large language model (LLM), as the size of large models increases, it also brings higher training costs. There is a urgent need to minimize the data size in LLM training. Compared with data selection method, the data distillation method aims to synthesize a small number of data samples to achieve the training effect of the full data set and has better flexibility. Despite its successes in computer vision, the discreteness of text data has hitherto stymied its exploration in natural language processing (NLP). In this work, we proposed a method that involves learning pseudo promp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09818","kind":"arxiv","version":2},"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/2504.09818/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":"2026-07-05T10:53:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SL10zvvu3qEDbwOZePMVw5HyTSVuwW/zfMvLiADWu4JJGlxADDFJ7litENBQ3PnQukKXwDvrJlEyFpuSJfsEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:26:28.674915Z"},"content_sha256":"a993627f726c8ae16d8dab5f234fab916f7cefbc89a48c22e994e182bda54461","schema_version":"1.0","event_id":"sha256:a993627f726c8ae16d8dab5f234fab916f7cefbc89a48c22e994e182bda54461"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBPKTNYWJH3DYKH24ORCUOLQKW/bundle.json","state_url":"https://pith.science/pith/ZBPKTNYWJH3DYKH24ORCUOLQKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBPKTNYWJH3DYKH24ORCUOLQKW/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":"2026-08-05T17:26:28Z","links":{"resolver":"https://pith.science/pith/ZBPKTNYWJH3DYKH24ORCUOLQKW","bundle":"https://pith.science/pith/ZBPKTNYWJH3DYKH24ORCUOLQKW/bundle.json","state":"https://pith.science/pith/ZBPKTNYWJH3DYKH24ORCUOLQKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBPKTNYWJH3DYKH24ORCUOLQKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZBPKTNYWJH3DYKH24ORCUOLQKW","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":"a66b95bf5a5b6fbefb5d64a5a243ea638d4f5b85e34716dd468af72b6ba0e571","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T02:39:26Z","title_canon_sha256":"fbb0de8573a2065157c5613e3622fe65043017a274aabd6c875de530ef3fee59"},"schema_version":"1.0","source":{"id":"2504.09818","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09818","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09818v2","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09818","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZBPKTNYWJH3D","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZBPKTNYWJH3DYKH2","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZBPKTNYW","created_at":"2026-07-05T10:53:17Z"}],"graph_snapshots":[{"event_id":"sha256:a993627f726c8ae16d8dab5f234fab916f7cefbc89a48c22e994e182bda54461","target":"graph","created_at":"2026-07-05T10:53:17Z","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/2504.09818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the realm of large language model (LLM), as the size of large models increases, it also brings higher training costs. There is a urgent need to minimize the data size in LLM training. Compared with data selection method, the data distillation method aims to synthesize a small number of data samples to achieve the training effect of the full data set and has better flexibility. Despite its successes in computer vision, the discreteness of text data has hitherto stymied its exploration in natural language processing (NLP). In this work, we proposed a method that involves learning pseudo promp","authors_text":"Fanyi Du, Hailin Hu, Hanting Chen, Kai Han, Rong Yao, Wenyi Fang, Yifei Fu, Yunhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T02:39:26Z","title":"Transferable text data distillation by trajectory matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09818","kind":"arxiv","version":2},"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":"sha256:8091b44a5ec57cf75e7458af6278bb84bd300ab2f77be4a4a8dce987ce39695d","target":"record","created_at":"2026-07-05T10:53:17Z","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":"a66b95bf5a5b6fbefb5d64a5a243ea638d4f5b85e34716dd468af72b6ba0e571","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T02:39:26Z","title_canon_sha256":"fbb0de8573a2065157c5613e3622fe65043017a274aabd6c875de530ef3fee59"},"schema_version":"1.0","source":{"id":"2504.09818","kind":"arxiv","version":2}},"canonical_sha256":"c85ea9b71649f63c28fae3a22a397055aa2679993b8d6e0e905aa6c744e4bf63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c85ea9b71649f63c28fae3a22a397055aa2679993b8d6e0e905aa6c744e4bf63","first_computed_at":"2026-07-05T10:53:17.140291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:17.140291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K7+9EymNztn23ujZVwdOBC1yn95zE7lQxx6DMjt26K7QWreVtQlJHDx0aPHdpYvMTPuTD9nI3qMW9iWwyz6gAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:17.140850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09818","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8091b44a5ec57cf75e7458af6278bb84bd300ab2f77be4a4a8dce987ce39695d","sha256:a993627f726c8ae16d8dab5f234fab916f7cefbc89a48c22e994e182bda54461"],"state_sha256":"52f1a9dcd9e5590d450fdef6fb84cbc0d60e72770a793a0a0e65ce070d5225f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+K65MSpVukbMNwjYH0Jd/GAZq8SFq+lUnKziPmybrCvdCvXIHPepgPK7nAq7jEwfyFYX7kkiLwLVBhugZhVvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:26:28.681301Z","bundle_sha256":"6075e0c69ea9eb43b2bd34e5dbc42d16135098263d69de58976fe541f27b5e07"}}