{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G6L7GWNWD2FRLNV63J7RGUWNCX","short_pith_number":"pith:G6L7GWNW","schema_version":"1.0","canonical_sha256":"3797f359b61e8b15b6beda7f1352cd15d1d675a5b66800e1317a1797d640fd24","source":{"kind":"arxiv","id":"2403.05766","version":3},"attestation_state":"computed","paper":{"title":"FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arshit Gupta, Daniele Bonadiman, Saab Mansour, Sailik Sengupta, Shamik Roy","submitted_at":"2024-03-09T02:27:45Z","abstract_excerpt":"Planning is a crucial task for agents in task oriented dialogs (TODs). Human agents typically resolve user issues by following predefined workflows, decomposing workflow steps into actionable items, and performing actions by executing APIs in order; all of which require reasoning and planning. With the recent advances in LLMs, there have been increasing attempts to use them for task planning and API usage. However, the faithfulness of the plans to predefined workflows and API dependencies, is not guaranteed with LLMs. Moreover, workflows in real life are often custom-defined and prone to chang"},"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":"2403.05766","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-09T02:27:45Z","cross_cats_sorted":[],"title_canon_sha256":"9aa29edd10fb6aa2c704c093a7a0d8297b1d702f4be3b725e25f08139df493b9","abstract_canon_sha256":"34ee12ba72875a2ddef763054324a3f47454c01c18c2f20bd4f311137b03e5b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:25.379579Z","signature_b64":"6rdNViTGNlcN5CSExVThiCAAN2VmetvllQEnD+rPmhF2wNiFkIOUfLT13tSBtHU/XeOpYH+qZkZcbpJF2uxVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3797f359b61e8b15b6beda7f1352cd15d1d675a5b66800e1317a1797d640fd24","last_reissued_at":"2026-07-05T08:27:25.379060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:25.379060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arshit Gupta, Daniele Bonadiman, Saab Mansour, Sailik Sengupta, Shamik Roy","submitted_at":"2024-03-09T02:27:45Z","abstract_excerpt":"Planning is a crucial task for agents in task oriented dialogs (TODs). Human agents typically resolve user issues by following predefined workflows, decomposing workflow steps into actionable items, and performing actions by executing APIs in order; all of which require reasoning and planning. With the recent advances in LLMs, there have been increasing attempts to use them for task planning and API usage. However, the faithfulness of the plans to predefined workflows and API dependencies, is not guaranteed with LLMs. Moreover, workflows in real life are often custom-defined and prone to chang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05766","kind":"arxiv","version":3},"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/2403.05766/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":"2403.05766","created_at":"2026-07-05T08:27:25.379130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05766v3","created_at":"2026-07-05T08:27:25.379130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05766","created_at":"2026-07-05T08:27:25.379130+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6L7GWNWD2FR","created_at":"2026-07-05T08:27:25.379130+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6L7GWNWD2FRLNV6","created_at":"2026-07-05T08:27:25.379130+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6L7GWNW","created_at":"2026-07-05T08:27:25.379130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08496","citing_title":"LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX","json":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX.json","graph_json":"https://pith.science/api/pith-number/G6L7GWNWD2FRLNV63J7RGUWNCX/graph.json","events_json":"https://pith.science/api/pith-number/G6L7GWNWD2FRLNV63J7RGUWNCX/events.json","paper":"https://pith.science/paper/G6L7GWNW"},"agent_actions":{"view_html":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX","download_json":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX.json","view_paper":"https://pith.science/paper/G6L7GWNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05766&json=true","fetch_graph":"https://pith.science/api/pith-number/G6L7GWNWD2FRLNV63J7RGUWNCX/graph.json","fetch_events":"https://pith.science/api/pith-number/G6L7GWNWD2FRLNV63J7RGUWNCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX/action/storage_attestation","attest_author":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX/action/author_attestation","sign_citation":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX/action/citation_signature","submit_replication":"https://pith.science/pith/G6L7GWNWD2FRLNV63J7RGUWNCX/action/replication_record"}},"created_at":"2026-07-05T08:27:25.379130+00:00","updated_at":"2026-07-05T08:27:25.379130+00:00"}