{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RRYSUBRFAASUTUEPGMWRP4AMUH","short_pith_number":"pith:RRYSUBRF","schema_version":"1.0","canonical_sha256":"8c712a0625002549d08f332d17f00ca1c2543b3c00ea6d372a0c270ee61b2022","source":{"kind":"arxiv","id":"2405.10474","version":1},"attestation_state":"computed","paper":{"title":"Rethinking ChatGPT's Success: Usability and Cognitive Behaviors Enabled by Auto-regressive LLMs' Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Liu, Xinzhe Li","submitted_at":"2024-05-17T00:19:41Z","abstract_excerpt":"Over the last decade, a wide range of training and deployment strategies for Large Language Models (LLMs) have emerged. Among these, the prompting paradigms of Auto-regressive LLMs (AR-LLMs) have catalyzed a significant surge in Artificial Intelligence (AI). This paper aims to emphasize the significance of utilizing free-form modalities (forms of input and output) and verbal free-form contexts as user-directed channels (methods for transforming modalities) for downstream deployment. Specifically, we analyze the structure of modalities within both two types of LLMs and six task-specific channel"},"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":"2405.10474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T00:19:41Z","cross_cats_sorted":[],"title_canon_sha256":"ebf1af50d01dccd15ccabefc1b2c059512a21215c9259b086141ab6dbb054f27","abstract_canon_sha256":"3c9dbe19deee5cd5ff83604f69442530802eff6633caf97165d46abed71e4e9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:00.513408Z","signature_b64":"sGjwrmUr7pQilt2ISJwple3jo/KwT/J1JxL80+Me7euYoU/fPpr+7nGR3ZM4cmDQkPRxwnj7WwiTOKpHjnfeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c712a0625002549d08f332d17f00ca1c2543b3c00ea6d372a0c270ee61b2022","last_reissued_at":"2026-07-05T08:20:00.513050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:00.513050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking ChatGPT's Success: Usability and Cognitive Behaviors Enabled by Auto-regressive LLMs' Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Liu, Xinzhe Li","submitted_at":"2024-05-17T00:19:41Z","abstract_excerpt":"Over the last decade, a wide range of training and deployment strategies for Large Language Models (LLMs) have emerged. Among these, the prompting paradigms of Auto-regressive LLMs (AR-LLMs) have catalyzed a significant surge in Artificial Intelligence (AI). This paper aims to emphasize the significance of utilizing free-form modalities (forms of input and output) and verbal free-form contexts as user-directed channels (methods for transforming modalities) for downstream deployment. Specifically, we analyze the structure of modalities within both two types of LLMs and six task-specific channel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10474","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/2405.10474/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":"2405.10474","created_at":"2026-07-05T08:20:00.513110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10474v1","created_at":"2026-07-05T08:20:00.513110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10474","created_at":"2026-07-05T08:20:00.513110+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRYSUBRFAASU","created_at":"2026-07-05T08:20:00.513110+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRYSUBRFAASUTUEP","created_at":"2026-07-05T08:20:00.513110+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRYSUBRF","created_at":"2026-07-05T08:20:00.513110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23365","citing_title":"\"I made this (sort of)\": Negotiating authorship, confronting fraudulence, and exploring new musical spaces with prompt-based AI music generation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH","json":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH.json","graph_json":"https://pith.science/api/pith-number/RRYSUBRFAASUTUEPGMWRP4AMUH/graph.json","events_json":"https://pith.science/api/pith-number/RRYSUBRFAASUTUEPGMWRP4AMUH/events.json","paper":"https://pith.science/paper/RRYSUBRF"},"agent_actions":{"view_html":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH","download_json":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH.json","view_paper":"https://pith.science/paper/RRYSUBRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10474&json=true","fetch_graph":"https://pith.science/api/pith-number/RRYSUBRFAASUTUEPGMWRP4AMUH/graph.json","fetch_events":"https://pith.science/api/pith-number/RRYSUBRFAASUTUEPGMWRP4AMUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH/action/storage_attestation","attest_author":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH/action/author_attestation","sign_citation":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH/action/citation_signature","submit_replication":"https://pith.science/pith/RRYSUBRFAASUTUEPGMWRP4AMUH/action/replication_record"}},"created_at":"2026-07-05T08:20:00.513110+00:00","updated_at":"2026-07-05T08:20:00.513110+00:00"}