{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QRQT5I4VG5KG2YQUJMHVPOLWK3","short_pith_number":"pith:QRQT5I4V","schema_version":"1.0","canonical_sha256":"84613ea39537546d62144b0f57b97656f59ebdd4f1555757ffac1260db478375","source":{"kind":"arxiv","id":"2401.17904","version":2},"attestation_state":"computed","paper":{"title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baocai Yin, Bo Du, Chenyu Liu, Cong Liu, Dacheng Tao, Jing Zhang, Juhua Liu, Maoyuan Ye","submitted_at":"2024-01-31T15:10:29Z","abstract_excerpt":"The Segment Anything Model (SAM), a profound vision foundation model pretrained on a large-scale dataset, breaks the boundaries of general segmentation and sparks various downstream applications. This paper introduces Hi-SAM, a unified model leveraging SAM for hierarchical text segmentation. Hi-SAM excels in segmentation across four hierarchies, including pixel-level text, word, text-line, and paragraph, while realizing layout analysis as well. Specifically, we first turn SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach. We use"},"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":"2401.17904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T15:10:29Z","cross_cats_sorted":[],"title_canon_sha256":"b7cafef9a015cd3442879a38cefc795792e9f78f4d35de83b53555af2a229406","abstract_canon_sha256":"8590e6a0f3b35a2a5ccd3de73950a5fcba93677ca9085613f61fb32bbd06f9e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:41.911082Z","signature_b64":"Bs9wrqsaCVUEGWtkKGIlLWZeFDqg+64PSTcHF9odwsEtzpWxw+PcJOjmz8pEkC7GIC7B52v1gTOSzylRhg6WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84613ea39537546d62144b0f57b97656f59ebdd4f1555757ffac1260db478375","last_reissued_at":"2026-07-05T09:32:41.910566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:41.910566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baocai Yin, Bo Du, Chenyu Liu, Cong Liu, Dacheng Tao, Jing Zhang, Juhua Liu, Maoyuan Ye","submitted_at":"2024-01-31T15:10:29Z","abstract_excerpt":"The Segment Anything Model (SAM), a profound vision foundation model pretrained on a large-scale dataset, breaks the boundaries of general segmentation and sparks various downstream applications. This paper introduces Hi-SAM, a unified model leveraging SAM for hierarchical text segmentation. Hi-SAM excels in segmentation across four hierarchies, including pixel-level text, word, text-line, and paragraph, while realizing layout analysis as well. Specifically, we first turn SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach. We use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17904","kind":"arxiv","version":2},"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/2401.17904/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":"2401.17904","created_at":"2026-07-05T09:32:41.910633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17904v2","created_at":"2026-07-05T09:32:41.910633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17904","created_at":"2026-07-05T09:32:41.910633+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRQT5I4VG5KG","created_at":"2026-07-05T09:32:41.910633+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRQT5I4VG5KG2YQU","created_at":"2026-07-05T09:32:41.910633+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRQT5I4V","created_at":"2026-07-05T09:32:41.910633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03799","citing_title":"ConText: Driving In-context Learning for Text Removal and Segmentation","ref_index":82,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3","json":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3.json","graph_json":"https://pith.science/api/pith-number/QRQT5I4VG5KG2YQUJMHVPOLWK3/graph.json","events_json":"https://pith.science/api/pith-number/QRQT5I4VG5KG2YQUJMHVPOLWK3/events.json","paper":"https://pith.science/paper/QRQT5I4V"},"agent_actions":{"view_html":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3","download_json":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3.json","view_paper":"https://pith.science/paper/QRQT5I4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17904&json=true","fetch_graph":"https://pith.science/api/pith-number/QRQT5I4VG5KG2YQUJMHVPOLWK3/graph.json","fetch_events":"https://pith.science/api/pith-number/QRQT5I4VG5KG2YQUJMHVPOLWK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3/action/storage_attestation","attest_author":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3/action/author_attestation","sign_citation":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3/action/citation_signature","submit_replication":"https://pith.science/pith/QRQT5I4VG5KG2YQUJMHVPOLWK3/action/replication_record"}},"created_at":"2026-07-05T09:32:41.910633+00:00","updated_at":"2026-07-05T09:32:41.910633+00:00"}