knowledge/semantic/chunks
Source: knowledge/semantic/chunks.parquet. Source vintage: Package vintage 2026-10-01; source path partition not dated; inspect record and rule clocks separately. Grain: Packaged source record; inspect schema and linked world method before aggregation. Snapshot: 7a53af6a9beb58928d4a64dc92db09c9db65433f9909f1a10d16e302adaf86ba.
Read the method for this source
Explore this source with typed OData queries · Filtering, grouping and evidence method
Schema and filter instructions · Count this selection · First records
| node_id Int64 | document_node_id Int64 | doc_id Utf8 | ordinal Int64 | source_sha256 Utf8 | chunk_sha256 Utf8 | byte_start Int64 | byte_end Int64 | char_start Int64 | char_end Int64 | text Utf8 | extractor_version Utf8 | chunker_version Utf8 | __row_id Int64 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 30 Filter to this value Explore graph node | 30 Filter to this value | cms-pfs-gpci Filter to this value | 0 Filter to this value | d753d17afd8b8480ba79e3502c184ec25ab63d4f6a9a69565c3a59babed864cd Filter to this value | 75e37c1af321f153d7fc3916b96a9807c8450dcd446468e7efc374dccf5b724a Filter to this value | 0 Filter to this value | 620 Filter to this value | 0 Filter to this value | 620 Filter to this value | source: cms-pfs-gpci state: available table_state: converted gavel vintage: 2026-01-01 upstream files: data.parquet, GPCI2026.csv gavel row count: 118 note: Addendum E, geographic practice cost indices by locality why not shipped: this world does not carry it. The source is converted and readable in gavel and no tool here reads it. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. 10 columns, including: MAC, STATE, LOCALITY_NUMBER, LOCALITY_NAME, PW_GPCI_WITHOUT_FLOOR, PW_GPCI_WITH_FLOOR, PE_GPCI, MP_GPCI, filename, vintage | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 30 |
| 31 Filter to this value Explore graph node | 31 Filter to this value | cms-pfs-rvu Filter to this value | 0 Filter to this value | 7d6b084bbff1f23d381a5b696cc6943a15f15e5b7a0cbadff7d517f3eb4e2e7f Filter to this value | cd35736d4067cbf567df299d376a1048c552aa52f6cae0f30bf9e772ce682471 Filter to this value | 0 Filter to this value | 636 Filter to this value | 0 Filter to this value | 636 Filter to this value | source: cms-pfs-rvu state: available table_state: raw_only gavel vintage: 2026-10-01 upstream files: rvu26d-updated-08-26-2026.zip why not shipped: this world does not carry it, and gavel holds no `data.parquet` for it either. gavel holds only the payload it fetched, under `_raw/`, and nothing was opened. Nobody converted the file. At vintage 2026-10-01 the source holds: rvu26d-updated-08-26-2026.zip. That is a conversion task in gavel and it is a different fact from a decision not to ship. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 31 |
| 32 Filter to this value Explore graph node | 32 Filter to this value | cms-physician-geo-service Filter to this value | 0 Filter to this value | f7a4052c22c5b1527e5568ed6b172191ca55cc4fd1dcd76388a20734700d0330 Filter to this value | 808482cec80141f64e167bc92b9a14562f6dd392c6a1d5cbaf66a9e7e700e4ca Filter to this value | 0 Filter to this value | 1040 Filter to this value | 0 Filter to this value | 1040 Filter to this value | source: cms-physician-geo-service state: available table_state: converted gavel vintage: 2024-01-01 upstream files: data.parquet, MUP_PHY_R26_P05_V10_D24_Geo.csv gavel row count: 268350 note: [commons/open] Medicare Physician & Other Practitioners, by geography and service. The same claims as the provider file, aggregated to state and to national, so it answers which codes are billed where without carrying a provider identifier. Fetched by `gavel_refresh commons`, resolver=dcat. why not shipped: this world does not carry it. The source is converted and readable in gavel and no tool here reads it. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. 17 columns, including: Rndrng_Prvdr_Geo_Lvl, Rndrng_Prvdr_Geo_Cd, Rndrng_Prvdr_Geo_Desc, HCPCS_Cd, HCPCS_Desc, HCPCS_Drug_Ind, Place_Of_Srvc, Tot_Rndrng_Prvdrs, Tot_Benes, Tot_Srvcs, Tot_Bene_Day_Srvcs, Avg_Sbmtd_Chrg, Avg_Mdcr_Alowd_Amt, Avg_Mdcr_Pymt_Amt, Avg_Mdcr_Stdzd_Amt, filename, vintage | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 32 |
| 33 Filter to this value Explore graph node | 33 Filter to this value | cms-physician-puf Filter to this value | 0 Filter to this value | 18a5c6782e1db898c9d6c9c051360705cbffde32046beaa98a7b03a90a47870a Filter to this value | 93c00f8ae511ce6341db12a0ba86b6046e9e956e1bc88d3b4e8a718ea16dec71 Filter to this value | 0 Filter to this value | 1055 Filter to this value | 0 Filter to this value | 1055 Filter to this value | source: cms-physician-puf state: available table_state: converted gavel vintage: 2024-01-01 upstream files: data.parquet, PHY_R26_P05_V10_D24_Prov_Svc.csv gavel row count: 9781673 note: [commons/open] Medicare Physician & Other Practitioners, by provider and service. The FFS anchor every commercial rate is quoted against. Fetched by `gavel_refresh commons`, resolver=dcat. why not shipped: this world does not carry it. The source is converted and readable in gavel and no tool here reads it. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. 30 columns, including: Rndrng_NPI, Rndrng_Prvdr_Last_Org_Name, Rndrng_Prvdr_First_Name, Rndrng_Prvdr_MI, Rndrng_Prvdr_Crdntls, Rndrng_Prvdr_Ent_Cd, Rndrng_Prvdr_St1, Rndrng_Prvdr_St2, Rndrng_Prvdr_City, Rndrng_Prvdr_State_Abrvtn, Rndrng_Prvdr_State_FIPS, Rndrng_Prvdr_Zip5, Rndrng_Prvdr_RUCA, Rndrng_Prvdr_RUCA_Desc, Rndrng_Prvdr_Cntry, Rndrng_Prvdr_Type, Rndrng_Prvdr_Mdcr_Prtcptg_Ind, HCPCS_Cd, HCPCS_Desc and 11 more | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 33 |
| 34 Filter to this value Explore graph node | 34 Filter to this value | cms-pos-iqies Filter to this value | 0 Filter to this value | a087e181661fe0f3ce066f51259051f87be3c9d3c89b077db159f810edcf6b2d Filter to this value | acc421198c5ae5fe10376e2aef1ddbaaecc97600a58da7b94c1996a5745e9beb Filter to this value | 0 Filter to this value | 1250 Filter to this value | 0 Filter to this value | 1250 Filter to this value | source: cms-pos-iqies state: available table_state: converted gavel vintage: 2026-04-01 upstream files: data.parquet, POS_iQIES.DATA.Q2_2026.csv gavel row count: 77564 note: [commons/open] CMS Provider of Services file, iQIES: every certified SNF, home health agency, hospice and ASC with certification and change-of-ownership dates, control type, multi-facility organisation and the state Medicaid vendor number. SNFs are prvdr_type_id 20. Chain and identity backfill for cms-nursing-home-provider-info. Fetched by `gavel_refresh commons`, resolver=dcat. why not shipped: this world does not carry it. The source is converted and readable in gavel and no tool here reads it. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. 184 columns, including: prvdr_num, fac_name, prvdr_sbtyp_id, mdcd_vndr_num, orgnl_prtcptn_dt, prvdr_type_id, st_adr, city_name, ssa_cnty_cd, zip_cd, phne_num, crtfctn_dt, trmntn_exprtn_dt, state_cd, ssa_state_cd, state_rgn_cd, rgn_cd, fips_state_cd, fips_cnty_cd, cbsa_cd, cbsa_urbn_rrl_ind, acrdtn_type_cd, intrmdry_carr_cd, acptbl_poc_sw, fy_end_mo_day_cd, cmplnc_stus_cd, crtfctn_actn_type_cd, chow_dt, phrmcy_srvc_cd and 155 more | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 34 |
| 35 Filter to this value Explore graph node | 35 Filter to this value | cms-psps Filter to this value | 0 Filter to this value | 4718b6bea96f583549fbc757a7c21c61f23bc50c71c1c47035aa4cad8b4a9e22 Filter to this value | 5c440c0b7e2d3fd6b8599e0d94850052d3ddfe784e6749793edb12c3e73aee6f Filter to this value | 0 Filter to this value | 1070 Filter to this value | 0 Filter to this value | 1070 Filter to this value | source: cms-psps state: shipped table_state: converted gavel vintage: 2025-01-01 upstream files: data.parquet, Physician_Supplier_Procedure_Summary_2025.csv named by: pipelines/coverage-intelligence/build_psps_realization.py names the object carried in: data/psps_realization gavel row count: 14474585 note: [commons/open] Physician/Supplier Procedure Summary. Part B carrier and DME fee-for-service claims summarised by carrier, pricing locality, HCPCS, modifier, specialty, type of service and place of service. The only CMS file that carries submitted, allowed, denied and paid on one row. Fetched by `gavel_refresh commons`, resolver=dcat. 20 columns, including: HCPCS_CD, HCPCS_INITIAL_MODIFIER_CD, PROVIDER_SPEC_CD, CARRIER_NUM, PRICING_LOCALITY_CD, TYPE_OF_SERVICE_CD, PLACE_OF_SERVICE_CD, HCPCS_SECOND_MODIFIER_CD, PSPS_SUBMITTED_SERVICE_CNT, PSPS_SUBMITTED_CHARGE_AMT, PSPS_ALLOWED_CHARGE_AMT, PSPS_DENIED_SERVICES_CNT, PSPS_DENIED_CHARGE_AMT, PSPS_ASSIGNED_SERVICES_CNT, PSPS_NCH_PAYMENT_AMT, PSPS_HCPCS_ASC_IND_CD, PSPS_ERROR_IND_CD, HCPCS_BETOS_CD and 2 more | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 35 |
| 36 Filter to this value Explore graph node | 36 Filter to this value | cms-team-drg-mapping Filter to this value | 0 Filter to this value | bf3b99df637b15111cdf998149099a95b4f94ee94009df11ffd026111a6c13c5 Filter to this value | 823f07989cb7f68a6b3f39f61739d5c357b45e2f7aaae1fcc1463d66a825ae70 Filter to this value | 0 Filter to this value | 641 Filter to this value | 0 Filter to this value | 641 Filter to this value | source: cms-team-drg-mapping state: available table_state: raw_only gavel vintage: 2026-04-15 upstream files: team-drg-mapping-specs.xlsx why not shipped: this world does not carry it, and gavel holds no `data.parquet` for it either. gavel holds only the payload it fetched, under `_raw/`, and nothing was opened. Nobody converted the file. At vintage 2026-04-15 the source holds: team-drg-mapping-specs.xlsx. That is a conversion task in gavel and it is a different fact from a decision not to ship. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 36 |
| 37 Filter to this value Explore graph node | 37 Filter to this value | cms-team-excluded-hemophilia Filter to this value | 0 Filter to this value | 40cd153659cf26872bed534d21e5e19432cd3409b068d72fc0d7b25946fcde3d Filter to this value | ce1cab18ff9e394103de88d0c6243a90d90da01b94cf2df3a27e1338daa48d41 Filter to this value | 0 Filter to this value | 550 Filter to this value | 0 Filter to this value | 550 Filter to this value | source: cms-team-excluded-hemophilia state: available table_state: converted gavel vintage: 2025-09-30 upstream files: data.parquet gavel row count: 41 note: TEAM PY1 excluded hemophilia clotting factor HCPCS. About 40 rows why not shipped: this world does not carry it. The source is converted and readable in gavel and no tool here reads it. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. 3 columns, including: HCPCS Code, HCPCS Code Description, vintage | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 37 |
| 38 Filter to this value Explore graph node | 38 Filter to this value | cms-team-excluded-mdc Filter to this value | 0 Filter to this value | 9f42618646ff463715d9a161f8f19ca8ec1bbf2d7367c2f9790b986330a541c9 Filter to this value | 2fd9157f7dade70c04367a80c552fdc528c673d3d7972d3b7277ee68b6cadc82 Filter to this value | 0 Filter to this value | 517 Filter to this value | 0 Filter to this value | 517 Filter to this value | source: cms-team-excluded-mdc state: available table_state: converted gavel vintage: 2025-09-30 upstream files: data.parquet gavel row count: 4 note: TEAM PY1 excluded MDCs: 02, 14, 15, 25. Four rows why not shipped: this world does not carry it. The source is converted and readable in gavel and no tool here reads it. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. 3 columns, including: MDC, MDC Code Description, vintage | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 38 |
| 39 Filter to this value Explore graph node | 39 Filter to this value | cms-team-excluded-part-b-drugs Filter to this value | 0 Filter to this value | 0b7b5c984e2097ccf6b4eb2f715561175c814722a52595c7452e53771ab30c4a Filter to this value | ffdab97af89b8d9ace49065b2b322d152ca700abfab1098380e2bbf4c83d19a7 Filter to this value | 0 Filter to this value | 616 Filter to this value | 0 Filter to this value | 616 Filter to this value | source: cms-team-excluded-part-b-drugs state: available table_state: converted gavel vintage: 2025-09-30 upstream files: data.parquet gavel row count: 479 note: TEAM PY1 excluded Part B drugs and biologicals by HCPCS with the reason (low volume, and so on). About 480 rows why not shipped: this world does not carry it. The source is converted and readable in gavel and no tool here reads it. `available` means fetched and staged by gavel. It does not mean validated, does not mean converted, and does not mean read by anything here. 4 columns, including: HCPCS Code, HCPCS Description, Reason for Exclusion, vintage | coverage-source-register/v1 Filter to this value | hammer-register-chunker-v3 Filter to this value | 39 |