{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:N3TZSJ5DVO6HNXUOTEGPNZVBMA","short_pith_number":"pith:N3TZSJ5D","canonical_record":{"source":{"id":"2605.16379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T01:27:59Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"c557e5f898197b49bc6ebe4586a6e4a29d2e95b736db4aba223bb3092906a9d2","abstract_canon_sha256":"fe69b79b04134bf4781fc9420e72fc89008cde5d9be091f6f33e880471da289a"},"schema_version":"1.0"},"canonical_sha256":"6ee79927a3abbc76de8e990cf6e6a160193e465e42c973f425f41bd5a5b7c9a8","source":{"kind":"arxiv","id":"2605.16379","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16379","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16379v1","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16379","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"pith_short_12","alias_value":"N3TZSJ5DVO6H","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"pith_short_16","alias_value":"N3TZSJ5DVO6HNXUO","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"pith_short_8","alias_value":"N3TZSJ5D","created_at":"2026-05-20T00:02:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:N3TZSJ5DVO6HNXUOTEGPNZVBMA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T01:27:59Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"c557e5f898197b49bc6ebe4586a6e4a29d2e95b736db4aba223bb3092906a9d2","abstract_canon_sha256":"fe69b79b04134bf4781fc9420e72fc89008cde5d9be091f6f33e880471da289a"},"schema_version":"1.0"},"canonical_sha256":"6ee79927a3abbc76de8e990cf6e6a160193e465e42c973f425f41bd5a5b7c9a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:19.249532Z","signature_b64":"y2sBAor6HcjpffUsrl/ESLPQXq6tznTir9MRkgb/JKwOWfKf79FmwOoY0eGU2xB6MuQZvRyHLAj71STstIdGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ee79927a3abbc76de8e990cf6e6a160193e465e42c973f425f41bd5a5b7c9a8","last_reissued_at":"2026-05-20T00:02:19.248846Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:19.248846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16379","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":"2026-05-20T00:02:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftp/uvhKChlkPRthiKUJqtnE2EmTgbWGqLMW44gG7c3EmrM4gWgIKzwP1gHcurp/ybEOcG9d7afxO+2174TwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:06:06.500053Z"},"content_sha256":"3b32c183b6cf4ed532e3d130016d9656f3734d63a3c2cc0eb215a8087899658e","schema_version":"1.0","event_id":"sha256:3b32c183b6cf4ed532e3d130016d9656f3734d63a3c2cc0eb215a8087899658e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:N3TZSJ5DVO6HNXUOTEGPNZVBMA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Information-Theoretic Criterion for Efficient Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Hanyu Li, Xiaotie Deng, Zhengqi Sun","submitted_at":"2026-05-11T01:27:59Z","abstract_excerpt":"Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the generation-training loop is information-open, i.e., shaped by external signals (verifiers, environments, or rubrics) that inject task-relevant information beyond the model's current distribution. When the loop is information-closed (relying on the model's own outputs without such signals), the data processing inequality ensures that task-relevant information can only decre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16379","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/2605.16379/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.615102Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a233500c8b3697ab26c30d7b67bd98eb06f9c7a41a458d98a666a2e3445e01f1"},"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":"2026-05-20T00:02:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYiiAkTzTCi7TP4dqJfpke7gtu+uJ+thgjVwAALSyLA2j971YqxFFkoxgC1CVAXB9AXLisajhxNpHxd0BPO0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:06:06.500793Z"},"content_sha256":"f29bffa0727782f078c5d2e3c750a5c9e3adf745deb2c929ee6d25affc7ac2b8","schema_version":"1.0","event_id":"sha256:f29bffa0727782f078c5d2e3c750a5c9e3adf745deb2c929ee6d25affc7ac2b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3TZSJ5DVO6HNXUOTEGPNZVBMA/bundle.json","state_url":"https://pith.science/pith/N3TZSJ5DVO6HNXUOTEGPNZVBMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3TZSJ5DVO6HNXUOTEGPNZVBMA/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":"2026-05-26T10:06:06Z","links":{"resolver":"https://pith.science/pith/N3TZSJ5DVO6HNXUOTEGPNZVBMA","bundle":"https://pith.science/pith/N3TZSJ5DVO6HNXUOTEGPNZVBMA/bundle.json","state":"https://pith.science/pith/N3TZSJ5DVO6HNXUOTEGPNZVBMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3TZSJ5DVO6HNXUOTEGPNZVBMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N3TZSJ5DVO6HNXUOTEGPNZVBMA","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":"fe69b79b04134bf4781fc9420e72fc89008cde5d9be091f6f33e880471da289a","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T01:27:59Z","title_canon_sha256":"c557e5f898197b49bc6ebe4586a6e4a29d2e95b736db4aba223bb3092906a9d2"},"schema_version":"1.0","source":{"id":"2605.16379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16379","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16379v1","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16379","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"pith_short_12","alias_value":"N3TZSJ5DVO6H","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"pith_short_16","alias_value":"N3TZSJ5DVO6HNXUO","created_at":"2026-05-20T00:02:19Z"},{"alias_kind":"pith_short_8","alias_value":"N3TZSJ5D","created_at":"2026-05-20T00:02:19Z"}],"graph_snapshots":[{"event_id":"sha256:f29bffa0727782f078c5d2e3c750a5c9e3adf745deb2c929ee6d25affc7ac2b8","target":"graph","created_at":"2026-05-20T00:02:19Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.615102Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16379/integrity.json","findings":[],"snapshot_sha256":"a233500c8b3697ab26c30d7b67bd98eb06f9c7a41a458d98a666a2e3445e01f1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the generation-training loop is information-open, i.e., shaped by external signals (verifiers, environments, or rubrics) that inject task-relevant information beyond the model's current distribution. When the loop is information-closed (relying on the model's own outputs without such signals), the data processing inequality ensures that task-relevant information can only decre","authors_text":"Hanyu Li, Xiaotie Deng, Zhengqi Sun","cross_cats":["cs.AI","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T01:27:59Z","title":"An Information-Theoretic Criterion for Efficient Data Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16379","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":"sha256:3b32c183b6cf4ed532e3d130016d9656f3734d63a3c2cc0eb215a8087899658e","target":"record","created_at":"2026-05-20T00:02:19Z","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":"fe69b79b04134bf4781fc9420e72fc89008cde5d9be091f6f33e880471da289a","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T01:27:59Z","title_canon_sha256":"c557e5f898197b49bc6ebe4586a6e4a29d2e95b736db4aba223bb3092906a9d2"},"schema_version":"1.0","source":{"id":"2605.16379","kind":"arxiv","version":1}},"canonical_sha256":"6ee79927a3abbc76de8e990cf6e6a160193e465e42c973f425f41bd5a5b7c9a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ee79927a3abbc76de8e990cf6e6a160193e465e42c973f425f41bd5a5b7c9a8","first_computed_at":"2026-05-20T00:02:19.248846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:19.248846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y2sBAor6HcjpffUsrl/ESLPQXq6tznTir9MRkgb/JKwOWfKf79FmwOoY0eGU2xB6MuQZvRyHLAj71STstIdGCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:19.249532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b32c183b6cf4ed532e3d130016d9656f3734d63a3c2cc0eb215a8087899658e","sha256:f29bffa0727782f078c5d2e3c750a5c9e3adf745deb2c929ee6d25affc7ac2b8"],"state_sha256":"f8301103b2d89317a0e67c5f81b284adc214764ebb1750ce1e78f6cc2c1c115c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gAQyJ4nUk47V5dzck16gJebAKt/5GijBydYCozIjX4pZpwdjY/hgn6tiIlP3Qmk6mTo/IBPhdA7cRMMUy020CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:06:06.504815Z","bundle_sha256":"318b9130be4c77c8c94ff791b2ba3bff755d10614a1b93a9a4249e96880621aa"}}