{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3QO2K7JLB5U6ITQSOBSVAMLKUT","short_pith_number":"pith:3QO2K7JL","schema_version":"1.0","canonical_sha256":"dc1da57d2b0f69e44e12706550316aa4c400ed36c73e739a6e9ef100a0b6ae10","source":{"kind":"arxiv","id":"2412.19652","version":5},"attestation_state":"computed","paper":{"title":"A Plug-and-Play Method for Improving Imperceptibility and Capacity in Practical Generative Text Steganography","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kaiyi Pang","submitted_at":"2024-12-27T13:56:51Z","abstract_excerpt":"Linguistic steganography embeds secret information into seemingly innocuous text to safeguard privacy under surveillance. Generative linguistic steganography leverages the probability distributions of language models (LMs) and applies steganographic algorithms during generation, and has attracted increasing attention with the rise of large language models (LLMs). To strengthen security, prior work has focused on distribution-preserving steganographic algorithms that minimize the gap between stego sampling and random sampling from the model. However, their reliance on model distributions, which"},"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":"2412.19652","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-12-27T13:56:51Z","cross_cats_sorted":[],"title_canon_sha256":"95abf137a1ce8fb4a6b700169a3336955111bd27c235aaecbbc55f709b26f10b","abstract_canon_sha256":"4b08ab929cdc0a6b6bc4f47a4d95ad508cd95b9f32a383c32afffdbd34429c14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:02.118935Z","signature_b64":"OZobXI3wiH9v2tRAoVXYsGgoWxGr+0O40numhSpTUu2kFxMd7podf1U+8s7T5yF2ENznSRtswkINz5WOfni9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc1da57d2b0f69e44e12706550316aa4c400ed36c73e739a6e9ef100a0b6ae10","last_reissued_at":"2026-06-29T01:15:02.118420Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:02.118420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Plug-and-Play Method for Improving Imperceptibility and Capacity in Practical Generative Text Steganography","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kaiyi Pang","submitted_at":"2024-12-27T13:56:51Z","abstract_excerpt":"Linguistic steganography embeds secret information into seemingly innocuous text to safeguard privacy under surveillance. Generative linguistic steganography leverages the probability distributions of language models (LMs) and applies steganographic algorithms during generation, and has attracted increasing attention with the rise of large language models (LLMs). To strengthen security, prior work has focused on distribution-preserving steganographic algorithms that minimize the gap between stego sampling and random sampling from the model. However, their reliance on model distributions, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19652","kind":"arxiv","version":5},"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/2412.19652/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":"2412.19652","created_at":"2026-06-29T01:15:02.118476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19652v5","created_at":"2026-06-29T01:15:02.118476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19652","created_at":"2026-06-29T01:15:02.118476+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QO2K7JLB5U6","created_at":"2026-06-29T01:15:02.118476+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QO2K7JLB5U6ITQS","created_at":"2026-06-29T01:15:02.118476+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QO2K7JL","created_at":"2026-06-29T01:15:02.118476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01827","citing_title":"Relatively-Secure LLM-Based Steganography via Constrained Markov Decision Processes","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT","json":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT.json","graph_json":"https://pith.science/api/pith-number/3QO2K7JLB5U6ITQSOBSVAMLKUT/graph.json","events_json":"https://pith.science/api/pith-number/3QO2K7JLB5U6ITQSOBSVAMLKUT/events.json","paper":"https://pith.science/paper/3QO2K7JL"},"agent_actions":{"view_html":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT","download_json":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT.json","view_paper":"https://pith.science/paper/3QO2K7JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19652&json=true","fetch_graph":"https://pith.science/api/pith-number/3QO2K7JLB5U6ITQSOBSVAMLKUT/graph.json","fetch_events":"https://pith.science/api/pith-number/3QO2K7JLB5U6ITQSOBSVAMLKUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT/action/storage_attestation","attest_author":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT/action/author_attestation","sign_citation":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT/action/citation_signature","submit_replication":"https://pith.science/pith/3QO2K7JLB5U6ITQSOBSVAMLKUT/action/replication_record"}},"created_at":"2026-06-29T01:15:02.118476+00:00","updated_at":"2026-06-29T01:15:02.118476+00:00"}