OIP system: PSYCH
PSYCH
A generated article for one OIP shelf. It lists every operation in this API/CLI/MCP/device/model/core subsystem, links each leaf article, and gives the ledger path for proof.
This page is the operating article for one build subsystem. It is generated from live directory rows. If a task belongs to this subsystem, scan the operations below, open the matching capability article, run only the exact object named there, and verify by receipt.
Kind: core. Capabilities: 9. Machine system map: /api/dispatch?map=PSYCH&format=markdown. Root: /a/oip.
Operations
PSYCH_READER_V1
The instrument. Reads a corpus of one subject and emits span-cited claim voxels. Never diagnoses, never counsels. Use when: POST /api/psych/run — one instrument, N models, one subject. Arguments: input = the corpus packet built by the psych API.. Human article: /a/oip-capability-psych-reader-v1. Machine doc: ?key=PSYCH_READER_V1&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_READER_V1.
PSYCH_ADVERSARY_V1
The refuter. Attacks one standing claim against the same corpus. Defaults to refuted. Use when: POST /api/psych/challenge. Human article: /a/oip-capability-psych-adversary-v1. Machine doc: ?key=PSYCH_ADVERSARY_V1&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_ADVERSARY_V1.
PSYCH_CONSTRUCT_V1
Criterion-by-criterion coverage of a named construct against the corpus. Not a diagnosis, and says so. Use when: POST /api/psych/run with instrument PSYCH_CONSTRUCT_V1 and vars.construct. Human article: /a/oip-capability-psych-construct-v1. Machine doc: ?key=PSYCH_CONSTRUCT_V1&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_CONSTRUCT_V1.
PSYCH_CONSOLIDATE_V1
Merges near-duplicate standing claims from many runs into one claim carrying every span. Use when: POST /api/psych/consolidate. Human article: /a/oip-capability-psych-consolidate-v1. Machine doc: ?key=PSYCH_CONSOLIDATE_V1&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_CONSOLIDATE_V1.
PSYCH_INGEST
Add corpus entries for one subject. Declared frame and state are owner-supplied, never model-inferred. Arguments: JSON {subject, entries:{title,date,frame,state,substance,text}]}. Human article: [/a/oip-capability-psych-ingest. Machine doc: ?key=PSYCH_INGEST&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_INGEST.
PSYCH_RUN
Run the instrument across N models over a subject corpus. Every emitted quote is server-verified against the stored entry before the claim is kept. Arguments: JSON {subject, instrument, models:], entry_ids:[] or limit}. Human article: [/a/oip-capability-psych-run. Machine doc: ?key=PSYCH_RUN&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_RUN.
PSYCH_CHALLENGE
Send standing claims to the refuter panel. Majority refuted marks the claim refuted. Arguments: JSON {subject, claim_ids:] or all:1, models:[]}. Human article: [/a/oip-capability-psych-challenge. Machine doc: ?key=PSYCH_CHALLENGE&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_CHALLENGE.
PSYCH_PROFILE
The standing picture: claims by dimension with cross-model agreement, challenge outcomes, and every span. Arguments: $1 = subject id.. Human article: /a/oip-capability-psych-profile. Machine doc: ?key=PSYCH_PROFILE&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_PROFILE.
PSYCH_METRICS
Corpus measurements computed in code, not by a model: volume, lexical range, sentence length, register markers, term first-appearance timeline. Arguments: $1 = subject id.. Human article: /a/oip-capability-psych-metrics. Machine doc: ?key=PSYCH_METRICS&format=markdown. Invocation history: /api/invocations?object_id=PSYCH_METRICS.