{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LB5XO2C3CQ3D3SYVMJOCDPIP6E","short_pith_number":"pith:LB5XO2C3","schema_version":"1.0","canonical_sha256":"587b77685b14363dcb15625c21bd0ff106125423ba5f39ea1c9e159b28675f45","source":{"kind":"arxiv","id":"2501.16558","version":2},"attestation_state":"computed","paper":{"title":"Distributional Information Embedding: A Framework for Multi-bit Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CR","authors_text":"Haiyun He, Yepeng Liu, Yongyi Mao, Yuheng Bu, Ziqiao Wang","submitted_at":"2025-01-27T23:01:56Z","abstract_excerpt":"This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information into a pre-existing host signal, LLM watermarking actively controls the text generation process--adjusting the token distribution--to embed a detectable signal. We develop an information-theoretic framework to analyze this distributional information embedding problem, characterizing the fundamental trade-offs among three critical performance metrics: text qua"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.16558","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-01-27T23:01:56Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"544b646a5aba6352d9ac9e77f237b596ab26d91c9d176f4bda330a72582827a7","abstract_canon_sha256":"47157e6d448a9a8e9df01d7ffefea44f7a7ea27d071d1de6e4d68a2692266c9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:21.776737Z","signature_b64":"u9gPgGpZwAKTH35zrschbErWmhuGRfxWLfH6UCqdoc0eEJA3iqBcNdqasbNz2zWiVvf37aY9R3aSR9SQw3HNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"587b77685b14363dcb15625c21bd0ff106125423ba5f39ea1c9e159b28675f45","last_reissued_at":"2026-07-05T11:30:21.776291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:21.776291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributional Information Embedding: A Framework for Multi-bit Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CR","authors_text":"Haiyun He, Yepeng Liu, Yongyi Mao, Yuheng Bu, Ziqiao Wang","submitted_at":"2025-01-27T23:01:56Z","abstract_excerpt":"This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information into a pre-existing host signal, LLM watermarking actively controls the text generation process--adjusting the token distribution--to embed a detectable signal. We develop an information-theoretic framework to analyze this distributional information embedding problem, characterizing the fundamental trade-offs among three critical performance metrics: text qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16558","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/2501.16558/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.16558","created_at":"2026-07-05T11:30:21.776362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16558v2","created_at":"2026-07-05T11:30:21.776362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16558","created_at":"2026-07-05T11:30:21.776362+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB5XO2C3CQ3D","created_at":"2026-07-05T11:30:21.776362+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB5XO2C3CQ3D3SYV","created_at":"2026-07-05T11:30:21.776362+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB5XO2C3","created_at":"2026-07-05T11:30:21.776362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18333","citing_title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08826","citing_title":"Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E","json":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E.json","graph_json":"https://pith.science/api/pith-number/LB5XO2C3CQ3D3SYVMJOCDPIP6E/graph.json","events_json":"https://pith.science/api/pith-number/LB5XO2C3CQ3D3SYVMJOCDPIP6E/events.json","paper":"https://pith.science/paper/LB5XO2C3"},"agent_actions":{"view_html":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E","download_json":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E.json","view_paper":"https://pith.science/paper/LB5XO2C3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16558&json=true","fetch_graph":"https://pith.science/api/pith-number/LB5XO2C3CQ3D3SYVMJOCDPIP6E/graph.json","fetch_events":"https://pith.science/api/pith-number/LB5XO2C3CQ3D3SYVMJOCDPIP6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E/action/storage_attestation","attest_author":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E/action/author_attestation","sign_citation":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E/action/citation_signature","submit_replication":"https://pith.science/pith/LB5XO2C3CQ3D3SYVMJOCDPIP6E/action/replication_record"}},"created_at":"2026-07-05T11:30:21.776362+00:00","updated_at":"2026-07-05T11:30:21.776362+00:00"}