How to Build BibTeX Entries from Pasted Citation Fields
BibTeX packs invent DOIs. Keep every field on the paste. Missing pages stay missing.
The matching generator is the BibTeX Entry Pack from Pasted Citation Fields (No Invented DOIs) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Map each work before you emit an entry
Build BibTeX entries from pasted citation fields only. Never invent DOIs, page ranges, volumes, or venues. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Pasted citation fields (one block per work): [Fields]
Entry types I allow (comma list or DEFAULT): [Types]
DOIs I may use (exact list or NONE): [DOIs]
Citekeys I lock (or AUTO from author+year if present): [Keys]
Fields I must leave empty rather than guess: [Empty]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Max entries: [Max]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Leave DOI blank when DOIs is NONE
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: work count, Types, DOIs status, Keys policy, Empty list, Lang, Max. Forbidden: invented DOIs, invented pages, invented venues.
- Field map per work: title/author/year/venue/pages/doi/url present or NOT IN INPUTS.
- BibTeX pack: up to Max entries. Only fields present in Fields or DOIs. Missing required BibTeX fields print % MISSING: name.
- Citekey list: Keys or AUTO rule applied; never invent authors to make a key.
- Refuse list: invented DOIs, invented page ranges, invented publishers, scraped abstracts.
- Diff notes: phrases or fields cut because Banned or Never.
- Empty-policy note: quote Empty; confirm those keys stay absent.
- Compliance pass: Banned/Never hits. Entry count vs Max. Gaps list of five. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Refuse invented venues and publishers
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- BibTeX from Fields only. Not APA prose and not a lit-review summary.
- Never invent DOIs, pages, volumes, or venues.
- Stay at or under Max entries.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Print entry count against the max
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (bibtex from citation fields, no invented dois, bibtex entry pack) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.