{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S6R33SV4ANZFACS2WXOG7LTRG6","short_pith_number":"pith:S6R33SV4","schema_version":"1.0","canonical_sha256":"97a3bdcabc0372500a5ab5dc6fae7137880ba8caa255772452bbd31269866fac","source":{"kind":"arxiv","id":"2606.25460","version":1},"attestation_state":"computed","paper":{"title":"Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Eyal Cohen, Joseph Keshet, Rotem Rousso","submitted_at":"2026-06-24T06:42:29Z","abstract_excerpt":"Recent advances in sequence modeling have significantly improved ASR systems, bringing them close to human-level recognition accuracy and enhancing robustness across diverse acoustic conditions and languages. In contrast, Forced Alignment has not experienced comparable progress, and traditional HMM-GMM frameworks remain widely adopted and highly competitive.\n  To address this gap, we propose an end-to-end, fully differentiable neural architecture specifically designed for phoneme alignment. The model consists of an encoder that processes the input signal and a decoder that produces alignment d"},"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":"2606.25460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-24T06:42:29Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"053239836deada80e8d1ad4914b57cd174a95fef933d2b1cea22fd3cc88d99d1","abstract_canon_sha256":"5d3a50e199e3f4cfb1b9c39ae0aa00804227ad43ccda2be7ae3524775994e551"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:05.901337Z","signature_b64":"p9eufA4BBlRHI/apT4IHF/QOHKp+Ce+DVFD4M3bivJwII/4qCF2RZ5KMM5nMHK8z2uUAjfTv+1WGcfyXNjStDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97a3bdcabc0372500a5ab5dc6fae7137880ba8caa255772452bbd31269866fac","last_reissued_at":"2026-06-25T01:18:05.900926Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:05.900926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Eyal Cohen, Joseph Keshet, Rotem Rousso","submitted_at":"2026-06-24T06:42:29Z","abstract_excerpt":"Recent advances in sequence modeling have significantly improved ASR systems, bringing them close to human-level recognition accuracy and enhancing robustness across diverse acoustic conditions and languages. In contrast, Forced Alignment has not experienced comparable progress, and traditional HMM-GMM frameworks remain widely adopted and highly competitive.\n  To address this gap, we propose an end-to-end, fully differentiable neural architecture specifically designed for phoneme alignment. The model consists of an encoder that processes the input signal and a decoder that produces alignment d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25460","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/2606.25460/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":"2606.25460","created_at":"2026-06-25T01:18:05.900988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25460v1","created_at":"2026-06-25T01:18:05.900988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25460","created_at":"2026-06-25T01:18:05.900988+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6R33SV4ANZF","created_at":"2026-06-25T01:18:05.900988+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6R33SV4ANZFACS2","created_at":"2026-06-25T01:18:05.900988+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6R33SV4","created_at":"2026-06-25T01:18:05.900988+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/S6R33SV4ANZFACS2WXOG7LTRG6","json":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6.json","graph_json":"https://pith.science/api/pith-number/S6R33SV4ANZFACS2WXOG7LTRG6/graph.json","events_json":"https://pith.science/api/pith-number/S6R33SV4ANZFACS2WXOG7LTRG6/events.json","paper":"https://pith.science/paper/S6R33SV4"},"agent_actions":{"view_html":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6","download_json":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6.json","view_paper":"https://pith.science/paper/S6R33SV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25460&json=true","fetch_graph":"https://pith.science/api/pith-number/S6R33SV4ANZFACS2WXOG7LTRG6/graph.json","fetch_events":"https://pith.science/api/pith-number/S6R33SV4ANZFACS2WXOG7LTRG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6/action/storage_attestation","attest_author":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6/action/author_attestation","sign_citation":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6/action/citation_signature","submit_replication":"https://pith.science/pith/S6R33SV4ANZFACS2WXOG7LTRG6/action/replication_record"}},"created_at":"2026-06-25T01:18:05.900988+00:00","updated_at":"2026-06-25T01:18:05.900988+00:00"}