{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ECKHGXHJ7MUNYHPNH5G3KCAORS","short_pith_number":"pith:ECKHGXHJ","schema_version":"1.0","canonical_sha256":"2094735ce9fb28dc1ded3f4db5080e8c8cc29e8628144ea975ed556318c20888","source":{"kind":"arxiv","id":"2606.18856","version":1},"attestation_state":"computed","paper":{"title":"Approximate Structured Diffusion for Sequence Labelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Joseph Le Roux, Nadi Tomeh, Nicolas Floquet","submitted_at":"2026-06-17T09:36:34Z","abstract_excerpt":"Sequence labelling, a core task of Natural Language Processing (NLP), consists in assigning each token of an input sentence a label.\n  From a Machine Learning point of view, sequence labelling is often cast as a Linear-Chain Conditional Random Field (CRF) parametrised by a neural network.\n  While this approach gives good empirical results, CRFs assume a finite decision span (eg label bigrams) which can limit their expressivity and hurt performance when long-range dependencies are required.\n  We show we can leverage diffusion to train a CRF conditioned on an entire label sequence, with the cave"},"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":"2606.18856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T09:36:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec255e3c6c8cc48be418a00360b21f7aecc5d5c380a2982a4e0cfa54cf41ae9c","abstract_canon_sha256":"6b4c67d682fc1fa205cf1d218a972137ab3f8ef872fce2774a1bd61104dc0c32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:49.665574Z","signature_b64":"VL/9SkaNSDm0On302SdMH5RbWBX8ujfe3qTq6JrPqqifFjNSqs9A9acS40EpU3lWu/44NFKPRDHxFF8hV1CHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2094735ce9fb28dc1ded3f4db5080e8c8cc29e8628144ea975ed556318c20888","last_reissued_at":"2026-06-19T16:11:49.665205Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:49.665205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximate Structured Diffusion for Sequence Labelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Joseph Le Roux, Nadi Tomeh, Nicolas Floquet","submitted_at":"2026-06-17T09:36:34Z","abstract_excerpt":"Sequence labelling, a core task of Natural Language Processing (NLP), consists in assigning each token of an input sentence a label.\n  From a Machine Learning point of view, sequence labelling is often cast as a Linear-Chain Conditional Random Field (CRF) parametrised by a neural network.\n  While this approach gives good empirical results, CRFs assume a finite decision span (eg label bigrams) which can limit their expressivity and hurt performance when long-range dependencies are required.\n  We show we can leverage diffusion to train a CRF conditioned on an entire label sequence, with the cave"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18856","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/2606.18856/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":"2606.18856","created_at":"2026-06-19T16:11:49.665268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18856v1","created_at":"2026-06-19T16:11:49.665268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18856","created_at":"2026-06-19T16:11:49.665268+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECKHGXHJ7MUN","created_at":"2026-06-19T16:11:49.665268+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECKHGXHJ7MUNYHPN","created_at":"2026-06-19T16:11:49.665268+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECKHGXHJ","created_at":"2026-06-19T16:11:49.665268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS","json":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS.json","graph_json":"https://pith.science/api/pith-number/ECKHGXHJ7MUNYHPNH5G3KCAORS/graph.json","events_json":"https://pith.science/api/pith-number/ECKHGXHJ7MUNYHPNH5G3KCAORS/events.json","paper":"https://pith.science/paper/ECKHGXHJ"},"agent_actions":{"view_html":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS","download_json":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS.json","view_paper":"https://pith.science/paper/ECKHGXHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18856&json=true","fetch_graph":"https://pith.science/api/pith-number/ECKHGXHJ7MUNYHPNH5G3KCAORS/graph.json","fetch_events":"https://pith.science/api/pith-number/ECKHGXHJ7MUNYHPNH5G3KCAORS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS/action/storage_attestation","attest_author":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS/action/author_attestation","sign_citation":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS/action/citation_signature","submit_replication":"https://pith.science/pith/ECKHGXHJ7MUNYHPNH5G3KCAORS/action/replication_record"}},"created_at":"2026-06-19T16:11:49.665268+00:00","updated_at":"2026-06-19T16:11:49.665268+00:00"}